 Please make sure that you complete the register when you choose the list on the list of the modules there or the list of session and look for research analytics literacies for psychology. That is the session that we having for this afternoon. That is applicable to all those who are new to the UNISA environment and I think there is my name next to it, E-Boy. Just choose that. Okay, so let's begin. It's very, very soft. I can hardly hear. You can hardly hear me. And now. Yes. Is it much better now? Okay. Otherwise then also increase your volume on your side. I'm not sure. I can hear you fine so it might be her sound. Yeah. Okay. I can also hear you fine. Right. Okay. So the recording has started. Okay. So we are going to continue from where we left off. I know that on the WhatsApp someone said can we do the 2020 paper. I haven't seen it so I haven't even downloaded it because I have been in a session the whole morning. So I haven't even had enough time to eat because I'm eating in between my sessions and yeah. So we're going to follow what we have discussed. So we're going to continue with 2017, October, November where we left off. And we said because someone sent the 2019 so we're going to use the 2019 main example paper and I don't want to use the June or the October, November because now we're discussing the October, November. Maybe you can take the 2020 and discuss it yourself or work through it. And if you have any difficulties or questions, you can always chat, post the question on the WhatsApp group and then we can continue the conversation. Remember that WhatsApp group is created for you to be able to engage with other people and ask questions. So don't be shy to use that forum as well to ask questions because we have limited number of hours that I can assist you online. So let's continue the conversations on there as well. So welcome to your exam preparation. Let's begin. Madam Boy. Yes. Are we going to look at those question marks from yesterday as well? Yes. We started from where we left off and I know that we had two or three questions that we want to go back and revisit. We will do that as well. Let me share. So we're going to start with the questions that we had question marks on so that then we can continue. So I've made a mark on some of them and some we already did also answer but we had some question marks on them. So like question number 39. So we were not sure whether is it the effect size or the power of a statistical test or whether we need to be saying we said the lower significance value. So I have an answer for you and your answer is actually even in your study guide. It's on your I think page 85. So remember when we talk about the type one error which is your level of significance and that is where I said with your level of significance because it's a type one error of rejecting your null hypothesis when it's not true when it was not supposed to be rejected. So and I said this will not have effect on anything especially the level of significance because that you set as a researcher well in advance. Now the question that we asked was when a researcher do find some small differences between the mean based on the large sample and found that they differ significantly and to determine whether the outcome is of practical importance. Here they're talking about if I'm going to be making a decision and I know for example that that outcome I should reject the null hypothesis and the outcome that I get is to reject that null hypothesis because it's significant. Remember when it's significant we say if the p-value is less than alpha then we reject the null hypothesis because if our p-value that we have calculated if it's 0,00 which is less than our alpha of 0,05 if we have set the alpha of 0,05 we would reject the null hypothesis because then this is significant the p-value says this is statistically significant but we will still reject the null hypothesis and that is what is meant by the power of the test I reject the null hypothesis when it should be rejected if and that is our answer for option number 439. Our answer is option 2 that is that was one of those questions that we skipped the other question that we struggled to find the answer to was this one where it asked that what would you expect the probable value of the mean of a sample to be and in a normal circumstance if we if not when we are doing the the testing or the hypothesis but let's say we calculate a confidence level so which means there is an upper boundary and the lower boundary so we know what the value of the mean is and we know what the value of our mean our null hypothesis which here says if the null hypothesis is true then it means we're not rejecting the null hypothesis and we know when we calculate our z value here we said what did we get when we calculate the z value let me just go back and calculate it again because we said something like we can't it's undefined and when it I think it was I think it was 8.838 somewhere there yes I think so as well I think so now my calculator is acting up on me okay so so it means we can't find the p value on that so therefore it means our null hypothesis we cannot see in terms of the values that we are they are given here we could not determine whether whether we go into the reject or not reject but here they say if the null hypothesis is true so therefore it means yeah they're telling us if we're not rejecting the null hypothesis what would we expect the probable value of our mean b so in order for us to be able to find that and that's why I wanted to use my calculator in order for us to do that we know that the answer cannot be 25 sorry I just want to to my calculator my calculator has went some way I just want to open my calculator quickly sorry about that okay back to normal so if we say our sample mean is 20 if we say it's 20 then the top part will be zero so therefore it means our z value will be equals to zero and therefore it means our z our probability will be 50 percent of the probability of this and then we and if we use alpha of 0.05 for a 50 percent then we are going to reject the null hypothesis as well so it's either we can choose but if we say our mean value is not equals to 20 therefore we're saying it can either be 25 and we know with 25 it cannot be defined so the correct option on this one would be it can either be any of them which is not 25 because with 25 it's not and it cannot be not equal it cannot be more than 25 or it can also be not equals to 20 so therefore the answer should be option number three and then the other one that we put a question mark on was 44 and we did also find the answer for that we found it on the book as well so to say it will be the ability of a test to detect whether there is a significant relationship because we went and looked at it because for the effect size for the relationship we said we use the r-squared not the effect not the d cohead cohead d effect but we can use the r-squared which is the ability to test if there is a significance relationship even if it does not exist because it's the r-squared even if it's 0 comma 15 it will still find which values influences your dependent variable as well and quick question how would we know whether we have to use the coin formula or not yeah you see so in terms of the options that they give you here so with the with the effect size of the the cohead d it talks to whether is the effect smaller or larger in terms of the differences that are there so here they're not talking about the differences and also they will also refer to also whether if your sample sizes are increasing or decreasing as well your sample size or your your standard deviations so it has to be in relation to those so since they are not mentioning any of actually they are mentioning the sample size yeah but if you read the the sentence that talks to the sample size it says irrespective of the sample size and we know with that one we need to look at the sample size based on the law of large numbers the bigger the sample size the effect your model will have so that is why this one is not correct but because also they here they also included the relationship if they didn't include any question that based on the relationship wouldn't have even what you looked at the R squared which is also calculating the effect size as well because with the difference between the two is that the other one is done on the numerical values and whereas on two numerical values whereas with this one is made up on one variable one group one variable something like that um and that is how you can differentiate between the two okay so the other question is I think 45 we did find the answer to it because we said based on the information given we can use the sample information to calculate the z score even though we know with the reservations that we can't do that but that is the information that we are given but we can use that to find that probability and we can say whether where that probability falls and we did calculate that and we found that it was 0 comma 1 and that is why we said it is greater than 0 comma 1 um and it cannot be between 0 and 0 comma 1 it has to be more than because the question was say if the items are 10 or more so it means it has to be bigger than 0 comma 1 so and that's where we ended up so we're continuing from there so question 45 46 46 under which condition would a researcher use a t test and I think we did do this remember that under which conditions will a researcher use a t test for a hypothesis testing about an unknown population mean under which conditions one the value of the is the value of what number one yeah the value of the population standard deviation should be unknown this one he says the standard error which is not correct in which this one says it should be known which is incorrect as well based on base your answers to question 47 249 on the following scenario suppose that the memory span of adult is normally distributed with the mean of seven items and the standard deviation of two items the researcher is investigating the impairment of memory among people who have been diagnosed as suffering from course Corsak off yeah that's the first time I hear that Corsak off a syndrome a neuropsychological a neurological disorder linked to chronic alcohol abuse he intends to test his prediction on a sample of 50 persons who were diagnosed as suffering from this syndrome so we need to also identify what we're given here so if I go to the question first before I answer the questions so we need 47 to 49 47 48 hypothesis hypothesis and what test okay since I don't want to identify things that I don't need there so we need to test the this prediction on the sample of the person who was diagnosed with from this syndrome okay so the first thing that you need to ask yourself is there's two samples or one sample one sample right are we given are we given a population or a sample standard deviation we are given population standard deviation and the mean so we know that our mean is seven and our standard deviation is two so it means we know what our population is the values for our population and the researcher is investigating the impairment of memories amongst the persons who have been diagnosed as suffering from this syndrome he intends to use this test to predict on a 50 sample persons so we need to also ask ourselves yeah they don't mention or we need to also in our mind think they don't say anything about one is bigger than the other or he thinks that something is greater or more than or less than or anything like that so we're going to assume yeah we're going to do a two test which is equal so let's go answer the question based on the information that we've got at remember that I've already analyzed the whole question or the whole paragraph because now I know what I must look for so the first one says I need to state my null hypothesis my null hypothesis based on the information I already have an idea in terms of what my null hypothesis will be I have my mean so my null hypothesis should stay state with the population parameter and should be equal so my null hypothesis should state number two two three I mean option two option two yes the mean hypothesis should state that the mean is equals to seven but anyway the null hypothesis regardless of whether we we actually have also decided then the null hypothesis always contains an equal sign so this one wouldn't have been correct and this one wouldn't be correct in any way whether we know what we need to be discussing or what null hypothesis should be so number 48 says which of the following is appropriate statement to use for testing the above prediction regarding the mean memory span so since we know that from our question there we know that we're doing a equal which is a two take so what will be our alternative number two number three it will be number three because if my null if my null hypothesis says equal then my alternative will say not equal but if the researcher would have said the memory span of we ever we ever is less than then I would use the less than so we know in the you must be very careful as well in the alternative hypothesis it does not contain an equal sign anywhere where you see alternative hypothesis there should not be any sign with an equal sign like equal less than or equal or greater than or equal it should not be there so that one would have been automatic disqualification and then you are left with the two and to determine whether one of one of the two is correct you go back to the sentence anywhere on the sentence if there is a less than then you would have used the less than if there was a greater than and there is a greater than here you would have chosen that one but because there was no such thing there then we use the not equal so that means number three is the right one miss boy yes so just on the on the question where you said if we automatically we can assume that they when we don't see more than or greater than or less than we can already assume that it's equal to yes is that general assumption that we make yes because let's say for this sentence they would have said let me put it this way they would have said something like a researcher is investigating the impairment of the memory among the people who have died or who have been diagnosed as suffering from this and maybe they would have added like because it's more it's more than the average population or something like that so they would have added something that to that effect to say more than the average there's the memories their memory span is more than the average which we know that the average is seven so with that then it will give you an idea or they would have said is less than the average span of like less than the average span of adults memory whatever the thing is so you will get that in the question or in the statement that now we're doing a one-tail test or a directional test or doing a two-tail when it's quiet it's muted we don't find those kind of ways that tells you that one is superior than the other or one is bigger than the other then you must assume that that is not equal when you go to the alternative thank you okay so 40 why did i skip all of them 49 testing the above prediction on a sample will require a test so based on the information that you have yeah in your alternative hypothesis what type of a test are we doing number two we're doing a uh okay so some people might get confused as well so they there are actually two questions that are or two answers they that are correct but because we're talking about the statistical test so we need to also remember that with the statistical test we're talking about which tail of the area are we going to be making a decision so that will be a two-tail test two-tail statistical test and when they ask about what hypothetical test or hypothesis test are we doing we're doing a non-directional test okay the two yeah so this is for the entire hypothesis and this is for when you go make a statistical decision for the test and this is the hypothesis so this is the overall so overall says i am doing a non-directional test because it's both sides of the spectra the lower side and the upper side it's two-tail and the test when i'm going to make a decision i'm going to be looking at two-tail of them because when i get my p-value my p-value needs to be divided into the two two sides the lower side and the upper side okay a pharmaceutical company claims that a new slip they are marketing will put people to sleep in less than 15 minutes the researcher wants to test whether if the average time before people sleep after using the pill matches their claim she uses the following hypothesis can you see the discussion that we had previously you see i just went and highlighted that less than because they mentioning less than look at how they put the hypothesis testing your null hypothesis claims that the mean is equals to 15 the alternative will claim that the mean is less than 15 and it's because i got it from here if they didn't have that less than in there they will say uh the marketing will put people to sleep in 15 minutes then this would have been not equal because they say in less than five minutes 15 minutes then it is less than in your alternative suppose she tests this on a random sample of 40 research participants who suffer from insomnia she finds that the mean time before the members of the sample fall asleep are after using the pill is 14.3 so that is the sample mean the sample mean of 14.3 with the standard deviation which is the sample standard deviation of 3.2 a subsequent t test produces a two tail p value of 0 comma 0 3 4 5 so we have our two tail p value and the level of significance was set at 0 comma 0 5 what is the absolute value or what is the value of the one tail one or directional p value so what you need to always remember is a two tail two times the p value gives you a two tail and a p value for one tail when you go to the table and you go find the p value you will find one p value and if it's a two tail you're going to multiply that two the two when you go to the table you go find the p value or wherever they calculated it they give you the p value and if you multiply that p value you get two tail p value if you multiply it by two so therefore it means if they give you two a two tail so it means there are two p values that they they have on there that's what you always need to remember there is two of them in the in the two tail so in order for you to take the value of a two tail p value and calculate a one tail p value therefore it means this will be the two tail come on flipping it's writing on top of the other two tail p value divided by two in order for you to find a one tail value when you are given a two tail value that will be the two tail value divided by two i hope it makes sense so in your mind you need to always remember that a two tail p value there are two of them in that therefore it means for a one tail p value if you are given a two tail p value you are going to take that two tail p value and divide it by two half it so that you can get one side of the p value because with a two tail p value it will give you half of this side and half of this side both of them they make out one p value the site of 0.025 and the site of 0.25 if you add them together they will give you a p value of 0.05 which is one p value divided into two so there are two of them that is a two tail so in order so this will be a two tail p value that will be your two tail p value which is that side of that site making up the two value if i am doing a one tail so let's say i'm only oh that one was the less than so if i'm only looking at this site if i'm only looking at this site then i'm looking at 0.025 so if i take this one value there so let's use that as an example now i'm going to move it from here i'm going to put it here 0.0345 so therefore it means this site and that site they are i need to divide them by two so it's 0.0345 divide by two this site is 0.01725 and this site so this will be mine or whatever you can leave it this positive it doesn't matter and this site is 0.01725 so you can see that for a two tail because this is a two tail for a two tail there are two p values actually so the one site on the upper on the lower side and one on the upper side which makes up that p value if i'm looking for one site which is only the site of the less than based on my question so therefore it means if i look at this it means i'm looking for this site which is 0.01725 that is my p value so which means it's option number two understood is it clear confusing very clear for me happy happiness happiness okay so let's move on to the next one a researcher wants to compare the mean of non-verbal reasoning score of a sample n is equals to 25 students with that of the general population according to the literature the non-verbal reasoning test which he uses was standardized to a population mean of hundred and the population standard deviation of 10 so we are given the population standard deviation that is always very important to always remember when you read the questions especially when it's about testing that is very important because it will also give you much much deep insight in terms of what you need to be doing or what questions can follow after that what is the value of the standard deviation of the sampling distribution of the mean which is my sampling distribution question which will be required to calculate the z test statistic so remember they are talking about the sampling standard deviation or the standard deviation of a sampling distribution here they are asking you what will be the standard error so standard deviation of a sampling distribution is your standard error which is given by the population standard deviation divided by the square root of n what is our population standard deviation is 10 what is our n square root of 25 calculate and tell me what is the answer which is equals to two which is option three so and I see that in this question paper the standard error is been asked three times now question 55 or 52 what does it mean to say the difference between the mean of group a and b is statistically significant what does it mean to say the difference between the mean of group a and group b are statistically significant so one also say one we will say is true with number one because remember the p value and we did this not so long when the p value is less than your alpha you reject the null hypothesis so in most cases your p value will be significant at 0 comma 0 0 in most statistical application therefore it means we will reject the null hypothesis and we will say the alternative is true so that is why that will be true because if there's also when we state the null hypothesis we say there is no difference between the means and then when we state the alternative we say there is a difference and if they are different it means they ask there is a statistical significance that there is a difference the alternative is true okay based on your answer to question or base your answer to question 53 and 54 a market researcher is asked to conduct a study to examine people's reaction to a movie trailer he draws a random sample of 20 males and 20 females who saw the trailer he asked them to indicate how likely it is that they will go and see the movie on a seven point scale where one indicates not at all and seven indicates definitely he wants to compare to establish whether the males and females differ in their intention to see the movie based on their exposure to the trailer suppose the researcher finds that the mean and the standard deviation for each group in the sample is as follows so now you need to ask yourself the following question are these group dependent or independent male and female so they are independent dependent so now we're talking about independent groups so we need to find it the difference between the two independent groups we also need to look at what you are given are we given a standard population standard deviation or sample we're given all sample so it means we're going to be using a t distribution so before that we also need to look at the questions to make sure that we understand fully how to unpack the whole question so we have 53 and 54 53 as for the hypothesis and 54 is asking what is the appropriate test so we already did some of this up to 54 so we can go back to 53 need to go back and read your question and see if your question so this is where you can get some of the answers that you are looking for he wants to compare to establish whether males and females differ in their intention so they he never said or they never mentioned anything about men being more than the opinions of men being more than females or the opinions of female being less than male or things like that there is nothing like that so what is it that we want to test here when we go and do a hypothesis testing what will be our statements that we need to do conduct the null hypothesis will state three the null hypothesis will state that they are equal or made by the mean of males and mean of females and the alternative will state that they are not equal because on yet it's about equality we're checking whether they are equal so that will be option three this one would have been an automatic disqualification because we don't state the hypothesis in relation to the sample statistics we only use the population parameters question number 54 which is the appropriate t test or t statistic to calculate to evaluate the significance we know we already answered some of it so it should be easy is it one two or three number one it will be number it will be number one because we have two groups males and females and they are both independent groups remember to always ask yourself those questions does one influence the other no am I taking from the same population and creating the groups where they do a pre-test and then they do a post-test that is a dependent group where I take two different things two different variables then it's not dependent but if I'm taking from the same I give them the before and the after that is the dependent group so you always need to remember that and it's also explained in that decision tree the logic that you need to always apply question 55 a researcher is asked by a motivational speaker to establish whether a workshop on assertiveness training is effective the researcher decides to use a particular questionnaire which tests an individual level of assertiveness he presents the questionnaire to each of a sample of 50 participants in the workshop before it begins and once again after it has ended to the same participant when analyzing these results the researcher should use a statistical test for the I've already gave you the answer to this number two that will be number two comparison of means for two dependent group because we have the before the workshop and the after the workshop 56 which is the type two error in statistical significance rejecting the null hypothesis when it infects true not rejecting the null hypothesis when it is infect false and rejecting the alternative when it is infect true remember that is that decision day he's saying at two error we rejecting the hypothesis we reject H0 when we should be when it's not supposed to be H0 is not rejected H0 should be rejected so let's see what is the right question or what is the right answer is number two not rejecting the null hypothesis when it is false question 57 two samples may be regarded as independent when there is no systematic relationship between the composition of one sample to the other they were drawn at different occasions they are both totally random one that will be number one because they should not be any bearing between the two sample whether even if they were selected when they should not have any relation 58 a sample of 70 people are tested on a test for assertiveness before and after the workshop in which they are in which they are given assertiveness training which of the following is the most appropriate formula for comparing the mean assertiveness score before the training with one after thereafter number two number two nope number three number three remember here we're talking about dependence so this one is to calculate the in the independent events when you have your sample one in your sample two totally independent males and females this is when you have one sample when the population standard deviation is not known this is when you have dependent sample because you have the before the before and the after in order for you to create the test statistic you need to calculate the difference between the two to see if there are any differences so that is the independent so which means number three that will be correct answer there base your answer to the question 59 60 on the following scenario a researcher compares a sample of children from a special school for gifted with the group of children randomly drawn from other schools on the test which measures the creativity of the children on a nine point scale she wants to know whether the children from the school for gifted children is likely to have greater level of creativity planning to test this at alpha of zero comma zero one based on the sample she finds the following so she all the measures their sample statistics the size the mean and the standard deviation of the children and they also calculated the pooled base which include also the pooled standard deviation what is the appropriate alternative scenario so going back to the question read what the question they want to test is there any way in that question are they mentioning things like greater than more than number three if not it's greater than to test that greater level so therefore it means we're looking at number three so that is the first thing that you always need to go and look at is there in the question are they asking she wants to know whether children from the school are likely to have greater level so which means it's more than so there we go number three so we're basing this information on the two question she can place the test statistic which she found that it's four comma one nine six and uses a computer program to determine that the p value is zero comma zero zero zero two for the two sided testing which is highly significant she is however concerned that this significant result may be due to the relative large sample size so she decides to calculate the effect side the effect size which is the coins deep to determine whether the results are meaningful meaningful or irrespective so she decides to calculate the coins deep using this formula so if we go back because I think that's what we need to be calculating and then once we have calculated it we need to determine whether that is correct so going back we need to take the mean of x1 minus the mean of x2 that's what we have so you must take 55 or 5.5 minus 4.9 and we need to take this pooled standard deviation which is one excuse me yes I see the on page 17 it continues same question continues yes yes yes I'm getting the I'm getting the values to calculate this okay because we need to calculate it so that we can use this information so I'm saying get this value x1 which is 5.5 minus x2 which is 4.9 divided by 1 which is this formula here so just get those values do you have them do you have the values the answer is 0.6 so okay so do you will be four point what was the value four point five point five minus four point nine five point five minus four point nine divide by one what what did you get 0.6 0.6 yes so what is the answer based on the calculated effect size the researcher can conclude that the practical the practical implication of her finding is so can you say medium it's two it's medium so it is two okay 61 a scatter plot is a graphical representation of the relation between so if I have my x and my y and my scatter plot it's interval and ratio isn't it so it would be two so number one says two variables measured on a nominal scale which not two variables measured on a ratio and interval within a single a single group in two groups of subjects measured on an interval or a ratio on a single variable that will not be correct because this are two variables from the same group so if this is the age and we want to find the emotional intelligence IQ they come from the same group group so the answer is option two because this says it comes from two groups using single variables so so it means you say you want to see how age and age are due because there are two very the two groups so group age one or age nine and age eight so it will not make sense to do that because what are you trying to achieve with that nothing nada you can do that so it has to be option number two because it comes from a single group but using two variables that is very important and the variable needs to be numerical sorry the the the data needs to be numerical this is a categorical do you want to say something I was just saying it's difficult it's tricky it's very tricky I am yes so you just need to make sure that you use like I am using visuals also to make sense of some of these questions do that as well it's going to save you a lot of time a researcher will calculate a correlation coefficient which is R in order to establish what what is the correlation of coefficient tells you one the effect size of the test statistic because the two means were compared to be significant the size of the relationship which exists between two continuous variable which particular variable is distributed according to the z distribution one two three two because coefficient of correlation tells you the strength and the relationship of two variables numerical variables which is two question 63 which of the combination of the options below can be substituted in the following sentence to describe the situation when a significant negative correlation is found between two variable x and y which of the following combination so a person who scores on the variable is likely to have once that score on the variable so now you need to think about so x and y because it says negative correlation I just draw this to remind myself say when the values of that this one increases the difference of this one so let's see a person who will have a score of a high value so that will be three a person who has a score on x value score likely to have a high value of y two because the others this one says when x is high y is high as well so it's not correct this one say when x is low y is low also not correct so only number two will be correct so drawing this might also help with the reference to how you want to answer the question a researcher wants to establish whether the type of employment so yeah we're looking at the relationship between employment category and gender the employees can be categorized as manager human resources administrative maintenance information technology and the agenda are male and female that will be a question because we are looking at the categorical variable based on your answers 65 and 66 on the following scenario a group of hospitalized patients who have been diagnosed as suffering from dementia are treated with a certain drug over a period of time these drugs were prescribed to improve their mental alertness a researcher studies a random sample of 30 patients who have been on this drug for a varying amount of time hoping to establish a relationship between the number of days of the treatment drug and the patient's score of their mental alertness so yeah we're talking about two numerical values which is the correct way or the correct formal way to express the appropriate null hypothesis for this research and here we're talking about the relationship between two numerical values so it means the sample the sample statistic will be r because it will be the correlation coefficient from the sample test the population statistic will be fee I don't know what how you pronounce it but it will be fee like a ph i fee so how do we express this if you didn't know we express it in terms of that fee because that is your population parameter so this will be your population so r is your sample parameter so we cannot use r we cannot use the mean because here we're talking about the relationship between two numerical values which is an appropriate test to determine the significant relationship between the number of days that the drug was administered and the score of their mental alertness test obtained from this sample of patient to the person's product moment correlation which is the Pearson product moment of correlation which is the r 67 what would the expected frequency in cell ax cell ax which is that what is the expected frequency for the following contingency table and I'm not going to read the whole sentence so calculating the expected frequency we say row total let me not write it there because you need to create the totals so while I'm writing the formula have a catechia of completing the table and writing the total so tough I want the total for year and the total for day and the grand total so you can stay away from creating total from all everything so create the total so we will have to calculate the expected frequency by using row total times column total oh come on divided by the grand total so have you calculated the total this is 10 that is nine that's seven and this is 12 and 19 19 or I thought I am the only one who did it wrong so now we want to calculate the expected frequency for this ax so row total there are 10 column total 12 divided by the grand total which is 19 what do you have number two number two 6.32 that is number two happiness good oh 68 we almost we almost done three questions done with this one then we move to the next one if there is no relationship at all between two variables no relationship at all between two variables what would be the most likely value of your Pearson correlation coefficient r which is zero this would have been a perfect negative relationship this would have been a moderate relationship a contingency table which is the same as what we used here a contingency table represent what one two or three the distribution of frequencies the frequency count of each variable of a number of possible outcomes the frequency counts if each outcome measured in two nominal scales of variables when they are cross classified number three three will be number three last one end of paper which is all for a sec yes 69 yes uh we're just trying to make sense out of that okay let me help you make sense out of it the first one says is the frequency distribution of a variable this is a summary table a summary table because it will just have the category and then it will have your count or your frequency that is that one table the second one it says is the frequency count of each number of possible outcomes of an experiment that would be the same if this is your x variable which is your outcome variable which zero outcome comes up one outcome comes up two outcomes comes up three outcomes come up and you can calculate how many frequencies are there uh maybe the number of time when I roll it die in one does one doesn't come up I get two times when I roll it again and one doesn't one comes uh one comes up one time uh there are four of those and when I roll it how many times does two come uh sorry remember we're talking about zero uh one one comes up twice let's say there are three scenarios and so forth that is that number two number three it says a frequency count of each outcome measured on a two-dimensional variable so we have two variables we have a gender and we have absenteeism I like that absenteeism when they are cross-classified so this is a let's say staff members staff numbers are recorded here and this is recorded the agenda and this is recorded we recorded their absenteeism they are way absent or not absent yes and no yes and no something like that let's assume and we say this is females and males and female they were yes and so now taking the two variables which is what they say there when we have two nominal variables but we cross-classify them let's cross-classify them so yeah I have my no absenteeism absenteeism and my yes absenteeism yeah I have my female and my male that is cross-classification of those variables you see the difference okay yeah I was just you know what do you call it uh what's the weight that nominal scale thing just threw me off a bit okay and I'm sorry thanks thank you the last question which of the following values given is the closest to the probable value of the Pearson product coefficient correlation of x so you need to calculate ah those who don't know how to calculate ah let's do that oh it means I must log in onto the system so now let's see if I can log in so that I can share my screen uh let's see am I able to connect meeting sorry I need to join I must mute my device sorry okay let me mute this side can you can you can you can you hear me now sorry sorry can you hear me now yes yes that's so we back and you are able to see my screen my cut and then we remove that and so I'm going to capture the the information the data on my calculator but before I do that I need to take my phone to state mode so you press mode and you will press the state and because I'm looking for the number the linear regression I'll just press number five so my table is there but it has old data don't worry about that I will clean it up to clear my calculator I just need to you press shift and clear and then that's gone so shift then AC off then they are gone so I need to put in oh I must go back to my calculator mode state okay come on what's wrong with me let's do that mode I have messed up okay sorry mode state and linear and I can capture my data I will start capturing my x values first one equal two equal three equal four equal five equal six equal seven equal eight equals then I will go up with my arrows up up up up until I get to the first one then I go to the left or to the right and then I start eight equal seven equal sorry just a quick one the what you call it that table how did you get that table okay I'll come back again seven equal six six equal five equal four equal three equal two equal and one equal so we have all the values I can just press the AC button and it looks like it's gone but it's not gone then in order for me to get to the state I will press the shift and button number one way it says ASTAT on top of the button number one so shift one and you get STAT and as you can see we have all these other variables then I can go to the summation you can see all those summations this verb var will give you the var but we're not looking for that we're looking for the regression so I'll go to the regression and I'm looking for r because that's what we are looking for so it says my battery is low let's plug it in so I'm looking for r I'll just press r and r is equals to minus one so that is my answer so depending on what calculator you have if you have your calculator on your phone and going to use that so I'm going to start again so shift clear on so that it clears all my information on my calculator then I go mode and you press where it says ST let me see what you see in front of you you see where the gray thing is highlighted press that my calculator didn't clear my linear regression thing so mode and then you press the STA button it's still not clearing so let me take it back to the normal calculator and it closed so mode STA and then you get this menu do you see there is the linear regression you see that okay number five where it's gray now if I click on it then you get the table so since I now I have all these values I can delete them so you can just press the delete delete button and clear your calculator from any of those values so now you can capture the values so what did we have I think they were going down so it's one two three four five so you just say one and then press equal two equal three equal four equal five equal six equal seven equal eight equal and you're going to use your arrows these are your arrows go up until you get to number one which is one and then you're going to use the other arrow which is the left arrow the top one the smaller the normal arrows so to be on the y variable and because it's going down so now I start with eight eight equal seven equal six equal five equal four equal three equal two equal and one equal in a way we didn't even have to do the calculation I just want to show you that you have got that possibility that you can use um and then once you have stored all your values you just press the ac button that the orange one ac button there and you press the shift button which is that button the shift button and once you have pressed the shift button you press one sorry shift and at the top here when you press shift it should have an s that shows you that your shift is activated and then you press one it's like on your on your computer when you press shift you placing it on a capital letter or you'll be pressing any other letter that is on top so you're doing the same thing so you will need to scroll because you will be on the data the data will be the table that you used and you get all this other option the summation if you want to do the summations to find the answer for the summation the variable if you want to calculate the mean the standard deviation mean and max to do the quatao the distribution if you want to do the distribution but we're not interested in that we're interested in this to calculate the slope the intercept you can use those values to calculate r you just press the r button and press equal oh my table is empty so there's something wrong that i did uh let's see the i max my data my table is empty i've cleared my table but that is the the thing that you need to be uh doing but let me show you because i don't think they expect you to do a lot of calculations like that when you look at this you can just do it like this quickly when you are busy when you're on your on your exam you just say because your x values they're going up to one two three four five one two three four five i can go like that so you say one and eight maybe it's somewhere there two and seven they will all come down anyway three and four five i'm not matching so let's assume this was eight because i'm i'm just doing it rough rough let's do it this way so you should be able to see that seven six so what do we have here three and six and four and five so four and five that's awesome that is four and five and five and three three can assume that is there so as you can see that this is a perfect so let's put a five this is r is equals to minus one because it's negative you can assume that that is that so if the values here was one and one two and two three and three then you can say it's zero because it you will be right you will be doing this zero oh sorry it will be a perfect one so if it's like this so then the the values will go up like that if it's if they correspond when it's zero it will be one one one one one and then this is two three four five six seven so it means your thing will be like this your graph will look like that or if it's one two three four it will be like that so that one will be r is equals to zero whereas this one will be r is equals to one so you can just draw your graphs rough rough but anyway that is equals to one i could have looked at this and say but when x increases y decreases that should be a negative and this is a perfect negative relationship because it increases with the same rate at the same rate as it declines at the same rate so it would be negative one you can you get it that way all right so let's move on to the next paper i think the difficulty with your paper is in the beginning because it's too much theories there and i think we spent too much time there because we didn't know most of the answers we had to google them when we come to the statistic part it was easy and quick so let's go to the beginning of this one so we're looking at may june 2019 let's see if we can finish this one so yeah we've got the way you need to also tell me whether these statements are right or wrong because i won't know most of this a psychological theory is best defined as what do you know what psychological theory is is it a description of human behavior about our based on observation is it an explanation of their relationship among psychological construct is it a statistical inference based on measurement of a sample so i know that this one won't be right oh number one i think it's one the correct answer number one is the correct answer and she also this one i won't be able to assist you because i still have to understand what the construct is an abstract concept with such as intelligence anxiety and locus of control are said to us when we measure them which measurement is in fact to us number two number two so they are constructs and if we apply them as measurements they are referred to as variables oh yes now i understand what constructs are okay now i understand not that i fully understand but i think i get an idea a psychologist conducts a study in which she measures the reaction time of students during a psychometric test she proceeds from the assumption that a fast reaction time is a good indication of high intelligence this implies that reaction time is used as a way to intelligence is it and a construct operationalize or sample number one one the only one that's a verb is number one so it must be one yes because i think you take reaction time you operationalize it to create a new variable because reaction time will be a construct isn't it yes so you take a construct you do operations on it and it becomes a variable intelligence and then yes can you hear me can't hear you okay sorry i lost connection to my network it says bad network connectivity so we might struggle a little bit but as long as you can hear me must i reshare my screen or is it still visible it's still visible it's still visible on my side okay let's see how it goes okay so okay so that will be number one okay so question number four when we refer to a latent variable uh it means the variable is number three hidden what did we say we said a latent variable uh variables that are hidden or visible is it hidden it's hidden so that will be number four three okay the variable has an effect on the variable number three number three the independent variable has an effect on the dependent variable consider the hypothesis girls have better verbal ability than boys and they will perform significantly better than boys on a verbal ability test if we represent the mean verbal ability test of girls which is new girls and the mean the mean of the verbal ability score of boys as new boys the following should be the appropriate statement of the hypothesis with regards to the alternative hypothesis is better than number two it will be two number two better than so yes so it says girls are more than boys so that will be number two number seven says a psychologist is conducting a study about how the behavior of a university student can be affected by the way in which they conceive of themselves okay so we did this yesterday we did this yesterday yes a real question provides an e definition to a construct which was option number three yes we did this a construct can be regarded as hypothetical that's number two number two number two number two number two today is seeming like we are flowing which statement about the aims of psychological research is the most appropriate number number three number three number number three the goal is to test the psychological theories yes operational definition enable us to a make observation of the constructs to link construct to observable phenomena is it number three not b or is it both of them is it both of them we make observation of the constructs and we also link the construct to an observable phenomena that's what you're saying is number three both of them are number three are you still not sure we can go correct number three number three I say number two number two you say number two because apparently you can't observe constructs you have to first and now maybe I'm talking nonsense no you can't construct you can't yes link them to an observable phenomena yes that's just yes I'll also go with two because constructs can't see it can't observe so we have two and three as answers so let's go to our freaky google constructs where will I find constructs then it means I need to go right at the beginning of your study guide because I think that's where you can observe a construct but you can't measure it because you can observe let's say um anger you can observe and see if someone's angry but you can't measure anger so then you have to operationalize it to be able to measure it but you definitely can observe it I feel according to me you could be right there yes I also want to say that it's on page 304 of the study guide um I can't find the actual answer but the topic is on page three yeah I am I'm on the topic so I'm guessing everybody also can see constructs there I am so constructs psychologists develop explanation for human behavior and experience to do this they often make use of abstract concepts that serve as explanation so those are abstract concepts abstract concepts so let's go and see where they define what these constructs are where do constructs come from okay is there any way where they just oh here these are constructs so let's see so probably uh imagine trying to see these things uh sorry Lizzy on page five in that block at the top it says um the third line it cannot be observed directly um you must remember then now I'm I'm using 2012 study guides okay okay I know it is the same okay one page five at that box there at the top okay I don't have that so somebody but I don't think so okay let's look at this one way I am at that everybody has is looking at because I don't think it's changed a lot so imagine trying to look at this what would you look like where oh how big are they what color are they which they refer to those like your intelligence anxiety job satisfaction so it is obvious that this general ways do not refer to physical object but have an abstracted out of an experience of human behavior to serve as an explanation for certain aspects of the behavior concepts such as this are sometimes referred to as constructs they are in a sense made up concepts that we can use to explain things like behavioral patterns that can but we can observe but cannot see themself at least not directly so we can observe them okay so what does the question say make an observation of a construct yes I think yes link constructs to an observable phenomena I think yes again so option three was the right one where do they talk about operationalization or operation is it in the same that do they have a section where they cast it yes in the new module I think it's on page five so straight after constructs then it's a section on theories and then it's a section on measurements which includes operationalization okay so I did see measurements it's in that section of measures how constructs are made visible through measurement I will give you um sorry just give me two seconds let me follow this okay have you found the answer are we happy with number three yes yes I'm happy with that okay yes I'm also happy with that yes yes the answer is three okay this one we also did yesterday empirically means is based on three observations yeah number three yes right and industrial psychologists believe that having a good education will increase the chances of workers getting promoted in the private sector he decides to investigate this by using a sample of hundred employees at a company which one of the following is most appropriate way to formulate the hypothesis the research hypothesis so now he believes that education increases the chances of workers getting promoted good education so we need to find which one is the appropriate one there is a relationship between education and promotion employees high level of education and more than employees with lower level of level of education employees with high level of education are more likely to be promoted number three number three three number three because it says it increase the likelihood of the new promotion which of the options though are not true the probability values which we call them the p values are always this is just true so if you say two is correct then you are telling me if I get a p value of 20 I am right that's what you are saying telling me because it says it's three equals to zero so greater than zero and above so that is not true and we cannot talk about normally distribution we can still get the probability of a not distributed probability which is not normally distributed so the only one is because it's between zero and one quickly they say which of the options below are not true are not oh I know it's you gosh are not true so it's one no it's two it's one though guys two it's two not one two guys two will not be which one of the following options below are not true the probability values yeah the question is very tricky so it will not be true if we say they are greater than or equals to zero because then they would not be true just just hold on if you're saying it will not be if it's greater than or equal to this wouldn't 0.05 be greater than or equal to zero yes 0.01 will be greater than or equals to zero exactly there 20 will be greater than or equals will be greater than or equals to zero 100 percent 100 percent but we know that a probability can not be more than one but wouldn't 0.01 satisfy that statement as well no 0.01 will satisfy that statement and 20 will satisfy that statement but 20 will not make that statement true exactly but there's no mentioning of 20s or any numbers here no no but it says 20 that's the same thing there's no mention of 0.01 you are making it up I'm just saying that's also satisfied that statement I'm not speaking about the exact numbers yes so it satisfied that statement that is why I'm saying greater than the statement greater than zero will make any number that is bigger than zero or one be correct for this statement because that's what it says it says it's greater than or equals to zero so it means any number can be even 100 which is not a p-value p-values which are probability values are always between zero and one so they need to be only between that so all probabilities are between zero and one not more than that not outside of it are they always normally distributed though it should always be normally distributed to have the bell form yes not really but because like for example like your chi square test it's not a normal distribution because it is a left a right skewed test but you can find the p-values of that test but it can be correct either because you have a minus one or minus minus number as a being less than one as well yes and usually the z score is minus one but you never get the p-value that is minus one yeah so also that so that is a very tricky one which option of which option which of the options below are not true very tricky options because we know that p-values are always between zero and one but are they are they always normally distributed they are not normally distributed like I said for a chi square test it's not a normal distribution and it's not normally distributed it is a left skewed distribution they are not they are not normally distributed but they can be normally distributed but they can never be greater than one but the question is saying are always which means it has to be always normally distributed and here it says the question also it says they are greater than zero so it means any value bigger than zero or equals to zero will still be the probability so that is why I'm saying in terms of this maybe we should not overthink it I don't know who doesn't overthink things and then can you can help us resolve this question 18 let's not waste so many times on it because I don't have an answer for you as well whether is it one two or three questions based on the discussions that we have now I'm now even more confused I saw something on page 66 page 66 okay so on your side 66 might be something else on my page what is the meaning of that page like it just it's the solutions to some of the questions asked in the study guide and it says probability values fall in oh no never mind I thought it might be something but I don't think Lizzie I also think maybe for us in terms of what we're doing it would be number two because they have only taught us basically about the normal distribution we're not really learning about other distributions so I think they kind of raised the question for our coursework not necessarily like um oh I don't know how to phrase what I mean but you know we only learning about normal distributions in our coursework so I think the answer that they're looking for is two even if it might not be a hundred percent correct or two is correct but one can also be correct but also three can also be correct oh my goodness I think we need a cup of tea um yeah let yeah let me also because it's two o'clock so we we're living at five so we still have 30 minutes to go before we say let's break 14 wait I'm thinking now four o'clock yeah you see that question actually they made it very tricky by putting it in that way where they say which one is not always and then they also put it always so it's very confusing very very much because p values we calculate we get to talk about the p values once we get the normal distribution so when after this set scores we can calculate the p-vings if could have also been like an typing error you know maybe there was a section that was supposed to say there is one and two correct or is two and three correct or one and three correct you know that they maybe just didn't add in I mean that happened yeah I agree with you because the first sentence says which options which means it can be more than one yeah yeah so maybe it was just like an assigned or exam typing error it says which of the options not which options oh it's like which one of the options which one of them okay yeah okay so let's not waste time on something that we're not gonna even find the answer in the book for now so we can move on so question 13 if it comes up in the exam you go piggy piggy my Bellani better than and then you just choose something like that so yeah because I'm I don't want us to yeah to waste time on that one so now let's move to 14 we will break at half past so that I can go have my coffee or tea as well a class representative is chosen from a class with the 10 boys and 15 girls by writing the names of all of the learners in the class on the slip of a paper slips of paper putting those into one box it seemed like we did this one time asking their teacher to draw one name blindly what is the probability of selecting a boy two three three three three okay number three wait number three number two number three what's the probability of selecting a boy so how many satisfy a boy there are 10 25 so that will be 10 out of 25 so that's number two if they would have said what would be the probability of selecting one person that it would have been one over the 25 a boy or a girl or if they would have said isn't a boy uh meaning one meaning of boys the probability of selecting a boy what are the chances that a boy will be picked up will be one 10 out of the 25 okay if I select one boy out of that the chances will be I will pick a boy how many times 10 divide by 25 whatever that times is okay understood and introductory statistics has nine males and 15 females studying for a bsc degree as well as eight males and 12 female studying a ba if one student is selected randomly from the class what is the probability of selecting a ba student number two wouldn't it be one because you'd say 12 plus eight females and males are all studying ba and you're looking for ba a one ba student needs to be selected so it's one of the three students number one 20 out of 44 number one number two number one they are 20 ba students number one number one isn't it the same as what what frequency something that we did about frequency the expected frequency also no that is number one how many females studying bsc 15 females is 15 15 females how many females studying ba 12 is 12 how many males studying bsc nine how many females a males eight total eight 44 27 for females what is the probability that one student will be collected randomly selected from the class and what is the probability that that student is a ba student regardless of gender regardless of gender and they are 20 over 44 remember regardless of gender that will be those ones that will be 20 optional 24 that is why I told you it's very good to use a contingency table you can visualize your answers very easy the table represents a frequency count of the number of items that each person from a random sample of research capacity that students can remember out of the list a number of items remembered are those ones number of persons frequency are those ones if x is the number of items likely to be remembered by a random person what would be the probability of more than seven items being remembered if one calculated this probability using the relative frequency approach so what you need to do is go to the seven because they say greater than it does not include seven so it means we're looking for those ones you need to also add all of them so that you can know how many they are so calculate the total so calculate total four plus eleven plus they think did they give us no they didn't they are so cruel you know lectures are very cruel I should give you there are hundred frequency or hundred number of people participating so calculate the total do you have how much or how many it can be 32 what total are you calculating you need to calculate the number of persons total 100 plus 11 plus 13 plus 18 plus 22 plus 17 plus 96 so it's hundred that's what you need to be calculating now they say we must use the relative frequency formula to calculate that so since we calculated the probability of more than seven so we need that so you say nine divide by a hundred plus six divide by a hundred that will give you the probability that you are looking for which is the same as saying nine plus six divide by a hundred number two zero point one five one five zero point one five consider the following table here we have the mean of student x and the mean of class and they are subject abc and the standard deviation for each in which subject did the student indicated as x in that column this second column do best relative to the rest of the class very difficult by just looking at this so you need to calculate z scores for each one of them z score for a which will be 50 minus 40 you can use the percentages if you want divide by five and that will give you your z which is two and you need to do for the other one which is 55 minus 50 divide by five which is one and 60 minus 50 divide by two which is one which is one so they say which one do they do best related to that which means which one has the biggest score because let's go then it means they are more than the rest so which is one number one which is a one so a is the right one to choose so if they would have said below then you would have selected both of them but other than that they would have swapped the values and made sure that one has the value closer or below or something like that so the mean of the standard normal distribution is always while the standard deviation is always so what they are saying is describe the distribution of normal distribution that's normally distributed with the mean of zero and the standard deviation of one study the histogram below given where they have the max of a group of student in the same class and the base on the horizontal class limits so the groups assume we use this histogram on a basis of making a decision or making a prediction which of the following is best estimate of the probability that a student score will be between 40 and 60 so here they are asking you to go find the probability that is so you need to go find the probability that x lies between x lies between 40 and 60 so now the challenge here is the following we need to know how much how many we have what is the frequency so if this is 10 this is 20 and what is this i'm gonna say this is 40 and this is 10 and this is 20 and the following 10 plus 20 plus 40 plus 10 plus 20 plus that did you find the answer is 100 okay so since we need to find the probability of those two so you need to say that because I'm not going to apply the basic rule that we have yet uh 10 plus 20 just 30 is the answer that you are looking for when a sample is randomly selected from a population the sampling error depends on you remember what the sampling error is two your sampling error is your population standard deviation divided by the square root of n number two will be can be number two it depends on the size of a sample because we use n small n population exactly exactly what you okay so 21 and asymptotic property of a normal distribution cap cap refers to the fact that there two and points in the number three are based on this scenario the mark between oh sorry the mark obtained for a psychology assignment by all students who completed it is 35 and the standard deviation is 15. John received 45 for his psychology assignment. Please each of you Mike Tiani please you are disturbing us Tiani please. Okay so if the score are transformed into a standard normal distribution would John Z score for his mark b what would his score be so we need to calculate z mean minus the mean divided by the standard deviation so our x is always given because there is our x because we want to know what John is in relation to 35 over the standard deviation of 15 what is the answer 10 over 15 equals 0.67 so the option one is correct what will be option one 23 referring to the scenarios above what is the probability of a student chosen at random getting a score of 45 or better three yeah number three I don't know who was calling me on on teams okay so we we need to go calculate the probability so we know z says 45 or better so 45 or better means greater than 45 or better means greater than so it means when we go find the probability because that's what we are calculating the probability that our x is 45 I don't have to even calculate it because we did calculate this 35 divided by 15 we know that it is we need to find the probability that z is greater than 0.67 we calculate any day so this 45 it's the same as what we have calculated there so I don't have to so we need to go find this value on the table remember we looking for the greater than if it's positive we go to the smaller side if it's negative we go to the larger side that's to remind me when I go visit the table so let's go to the table use this side the table so 0.6 0.67 that is 0.67 and we looking for the smaller site 0.25 0.2514 0.2514 suppose that a and b are mutually exclusive events that is whether a is true will have no effect on the truth of b the probability that a and b can both be true that is said to be both can or care is given by which of these formulas number three nope number two it will be number two because it says also there has no effect on b so it can be number two okay it is number two because it cannot be this because also this is not true for multiplication it's if one is dependent on the other if I'm not mistaken yeah but this this is not true because I cannot let me charge my pen because so you must remember the following for a joint probability I think it's two ma'am no it's two two is correct so I'm just making sure that people understand this for the probability of a or b which is either one of them have any it's given by the probability of a plus the probability of b minus the probability of a and b with the flicking back on that is one if a and b are mutually exclusive then the probability of a or b will be equals to the probability of a plus the probability of b that is for mutually exclusive events because the probability of a and b will be equals to zero so for mutually exclusive event that is the case for conditional probability when a has no effect on b when a and b are independent of one another they have no effect on each other and that is what they are saying there on that other statement whether a is true will have no effect on the b therefore it means also they are independent then for mutually for joint probability of a and b will be given by the probability of a times the probability of b understood because for a conditional probability the probability of a and b will be given by the conditional probability of a given b because b has a bearing on what happens to a but in this instance they say they both cannot affect one another so therefore if they can they are independent as well so only option three is correct this would have been correct if they were not mutually exclusive but because they are mutually exclusive this statement there is incorrect they've been correct only on that base the first one is not correct because this should state or not end and only number two is correct okay study the following figure which is the normal distribution care with the specific data so they told us what the sample mean is our sample standard deviation is and they say we need to find the probability that x is greater than 145 so it means we're going to be calculating z value way is 11045 minus 150 divided by the standard deviation there of five what do you get one minus one minus one minus one yes it's minus one so you need to be very careful as well because the sign says it's greater than so now when the sign says greater than remember that if it is positive we go to the smaller side if it's negative we go to the larger side okay even though the sign says greater than we need to always bear in mind that the greater side is on the side and we're going to find the probability for the side when it's positive in the smaller side when it's negative for the larger side so let's go sorry miss Elizabeth sorry I just have a question and so I see your coloring in the the right hand side tail although the z was negative minus one yeah yes so I'm coloring in the biggest side because the sign says greater than if the sign was less than so all you will notice that on all of them I'm coloring because of the side so let's go back yes I see that um but but in this case shouldn't the left hand tail be sorry nope nope no remember you're not basing your answer based on what you get as on a z thing your your coloring is based on the sign of your question the direction of your question tells you where the site the coloring will be okay so when it is less than the shading will be on the less than side therefore also bear in mind if the answer is negative it will be on the smaller side if it is positive it will be on the larger side miss Lizzie I don't understand that because the standard deviation is minus one the z is minus one so okay on the left of the mean no no no no no no no no remember the side the the shading on the side of the table that you're going to be okay wait let let me open something else maybe did you guys attend my last session last week Wednesday or this week Wednesday or somewhere I can't even remember when was it Tuesday Tuesday no okay let me open the Tuesday slides okay so you need to remember the following when you're not going to base your answer for the probability on on your on the value that you get on the z right we base it on the sign the sign will tell you so if we looking for okay I'm gonna stop stop here if you're looking for the z value of less than if you're looking for the z value of a less than it means we're looking for this this side the shaded area this side you see where the red is because of that's less than not what the answer of the z value is based on the answer of your z value then you need to make your decision like this based on the answer of your z value if your z value is negative therefore it is on the side it's negative you're going to use the smaller side on your table if it is positive if your z value is positive then you use the larger side and I'm not making up all this let's go to your normal distribution table when is the normal distribution discussed where do we get to get to the go to the table okay so I think you do have uh I hope they do explain that on here somewhere let's hope so let's hope so let's hope so okay so here they explain the t value don't don't they explain how do you get your p values where do they explain your thing don't they explain it don't they give you an explanation on what I'm explaining to you is it not page 56 page 56 there should be a note somewhere where they help you unpack where are you going to find or make a decision so this talks to the hypothesis I'm not looking for the hypothesis I'm looking for miss boys yes I think if you have appendix day I don't know if it might not assist on page 163 yes on page 163 let's hope on page 163 if I do have 163 on yeah appendix a appendix c you said d appendix d yes appendix there we go yeah we go here we go okay so now do you see uh in terms of the side not in terms of the p-value in terms of the sign tells you where your your less than is see in terms of the sign if it's negative or positive where your z values the shaded area even though I'm shading on the other side because I'm shading the greater than side because of where I want to tell you so if you look at this the shading of a negative for me I'm to make sense of the table as well I just use if I if I'm looking for the greater than and my sign is negative then I'm looking for the larger area can you see that this is a larger area because you're shading for a negative will start from the negative side therefore you are looking for the larger area so I'm guessing from my side I am confusing you by only shading the side where the sign is but I'm still applying the same logic because if you look at let's take the less than if you look at the less than what I'm saying is if it if the z value answer is if your z value answer is negative then we go into look at the smaller portion so what it says is if it's less than and that will be the answer that we're looking for if it's greater than so therefore if it's bigger so I needed to change the shading instead of shading this for a positive I should be shading from here to there so that's what you are saying I should be helping you by looking at it in this way so then when I'm shading this side from the positive side to that side I'm looking at the larger side which is one and the same thing that I am saying instead of me shading the area instead of me shading this whole positive area I'm saying for the positive side I'm going to look at the larger side which is the same thing as what you have okay so let me write what I have there for the less than I'm gonna write it there for the less than if my answer is negative I'm going to the smaller side negative smaller area if it's positive larger area positive larger area so now let's come to your example here I'm looking for the less than less than negative smaller area that's what I'm saying less than positive larger area that's what I'm saying it's just that when I'm drawing the shades it's where you get confused but we're saying one and the same thing whether you're you're looking at shading it further or not but my shading is based on on this because it says I'm looking at the less than side so if my if my less than area because I'm looking for the probability of less than if my z value so you you are saying I need to wait until I get my z value so if my z value is negative so I'll go because here is zero in the middle if my z value is negative then I must come and shade the negative side that is for the negative if my z value is positive so I must come here and shade from the positive side and shade like that that's what you want me to do with all my examples so that you don't get confused is that what you're saying I must do I'm even more confused now but I don't want to be maybe I'm the only one I don't know you're also confused now okay so now I don't know which one you will okay I must use in order for you to be able to understand this better so what I'm saying is what they're explaining here with the type of shading for me when I'm making sense of it I'm looking at the sign and then I decide in terms of my z whether is it in the negative or in the positive and where do I go on the table that's how I make sense of your tables because I'm not familiar I'm not too familiar with the table but I had to find an easy way of me remembering how your tables work my table can I quickly come in to understand yes explain my thinking here is they can come in as well my thinking is you get the z value and then you go to your table you draw the line where the value is and if you know you have to be looking for a smaller area you shade that if you know you have to be looking for a larger area you shade that area I understand both ways that you you try to explain I think the other side is as I'm saying now get your z value go to your to your graph and then if you have to shade if you have to look for the smaller area shade only the smaller area then it doesn't confuse I'm not sure if I'm explaining the way yes I understand now what you're saying yeah okay so let's let let me explain it that way then so 145 minus 150 divided by five we got one that we got minus one yes but now we're going to draw the graph I need to remember that so because we're looking for the greater than and since the answer is negative it always helps me negative one so it means I'm gonna start shading from here yes it's and go there exactly because you're looking for the bigger part that's the shaded part right okay then you understand it much better if I do it this way so this is minus one yes I see the minus one on the graph so the lift of the mean it makes sense okay so then you know that you're looking for the larger side so okay I must use this method so that you understand okay in future I know now I don't want to confuse you I don't want to confuse you okay so we know that we need to go to the larger side so as long as you understand where we need to be at so we need one so these are zeros zero point one zero point one and this is one and we're looking for the larger side so if I go up the table with larger side is number two column number two to the left from the right so which is zero comma eight four one three oh yeah okay now I understand so if we get another question that does this I will do it in this method thank you so much I will also change my slides as well so that yeah because I was not sure I would try to make some anxiety was sky high suddenly okay so question 26 oh yeah we didn't even take a break okay let's do question 26 and 27 and then we will take a five minutes break boo is doing research on the IQ scores of students as means that the IQ will on average be greater than that of an overall population he states the hypothesis as such after drawing a random sample of 50 finds that they have a mean IQ of 107 and the standard deviation of five if it was the case that the null hypothesis is actually through what would the expected mean of the sample be and this is the same as what we did the previous time yes they were really given us the standard deviation of five isn't it yes but they want to know what would be the expected mean of the sample be which is almost similar to the same question that we did previous time number three more than number two and I think number three the last time we chose more than the mean of a population did we be or did we choose the same I think we should say not equal we said not equal to right yeah I can't even remember that I think it was I think we we settled four it was 40 44 what did we choose because we chose three I think not equal to because we looked at the side yes because of the sign on there hypothesis because we said if if the hyper null hypothesis is actually true therefore it means this is not true so it will be not more than oh not more than oh it will be more than yes so the level of significance indicates okay number one number one look up this on there study guide and when a statistical test yield a large p value which of the following statement is more likely to be correct now you need to remember that the decision says if the p value is less than alpha we reject the null hypothesis that's the decision rule so if the p value it's greater than or equals to alpha we do not reject the null hypothesis so therefore it means type the null hypothesis is true so if the p value is larger what will be the statement it will be number two check 29 the central limit theorem implies that for large samples the the sampling distribution of the mean across many repeated sample will be approximately to normal the distribution of the sample values for a specific variable will be approximately normal for a very large sample the sampling error for the repeated measurement of random variables will increase as the population increase number three three because we're talking about the central limit theorem where it will say if my what happens when I increase my sample or my standard deviation I hear number number one number three did anyone say number two number one someone said number one I think it's number three central limit theorem the distribution of the sample means will become more normal as the sample size increases so that the larger and larger samples the shape of the distribution of the sample mean will also become increasingly normal in a form number one so number one say sampling distribution of the mean across many repeated sample size will be approximately normal the distribution of the sample values for a specific variable will approximately be normal for a large sample size and the sampling error of a repeated measurement increase will increase with the population increase no we're not talking about the population can increase your population is the increase in terms of your sample the number of samples that you have so only number one is correct the size of a significance depends on the size of a level of significance depends on number two depends on number two value determined by the researcher when doing one sample as okay we do this one last one and then we take a break when doing one sample statistical test the value to reject the null hypothesis implies that the difference between the calculated sample mean and its expected value as predicted under the null hypothesis is due to the failure to reject the null hypothesis implies that the difference between the calculated mean and its expected value as predicted under the null hypothesis is due to would it not be one and I would think because it talks to what you called the whether there's any relationship or not dependency or not so in the null hypothesis we say they are independent exactly and in the alternative it states they are dependent and if we don't reject the null it means they are independent yes so if we're not rejecting the null hypothesis we state in that that is true so they it will depend on due to the independent variables because that is not due to the probabilities not due to the chance and it's not going to be due to the dependent variable because then we are rejecting we are not rejecting the null hypothesis okay so let's take a five minute break we'll be back exactly at five minutes at five o'clock I just want to go grip no time you see what time are we going to tonight uh no way tonight I'm going to be resting because no no no I mean what time are we are we working till tonight yet from I thought it was just for five is it until five are we are we very with that is it three hours yeah oh this is up to you I think there's a day spirit here but it's totally your business yeah okay if we if you want us to finish the paper marvelous yeah what I will do is uh yeah what I will do is we will have to get off this channel because then that is another thing so we'll have to get off the UNISA channel and go to the private one because then we need to stop del Cody because they monitor the times as well I can't go beyond that I didn't check the time that we're finishing at five so let's let's conclude the session and then we will join again give give me some time let's let's restart this the session on my private uh session uh at half past five is it fine that's fine perfect then I can go a little bit and rest a little bit and you get my husband in the eye at least four minutes I will post that I will share the link on uh on the WhatsApp so let me just close off yes uh yes I am going to post it please don't go before you you do the register otherwise I will also post it on the WhatsApp group for those who can't see the chat let me go find the register first the WhatsApp number please okay I will share the WhatsApp link uh the link just now um okay so let me close off before let's so that I can close the recording properly age you know this is uh and I must thank you guys thank you for being here tonight and for an awesome discussion and good luck with your exams bye thank you thank you bye thank you so much