 And after the session, it might take a some hours because it will depend because our session will end at eight and then, yeah, I will see when will I upload them if you have subscribed to my YouTube channel, you will get a notification when it gets uploaded. Please also, when you go and look at the recordings because I actually assist statistics students mostly. So there will be a lot of videos that I post on statistics. So don't get confused. Just go to the playlist. Under the playlist, there should be psych 3704 and you will only have the videos that relates to your modules there. So don't try and go and read the one that starts with STA 1610. Those are my statistics module classes. Okay, so let the games begin. Question number one, the process of finding a new a way to measure construct so that you can be represented by a variable. What is the answer to that question? Oh, that's the other thing. I don't give answers because I don't know the answers myself as well. So you can. Number one. Number one finding a way to measure it's number two. I would say number two as well. It's number two, ma'am. The answer. Number two is operationalization. Are we all happy? That's number two. Yes, the mean range variance and standard deviation are examples of. Number two. Examples of a descriptive analysis because descriptive analysis describes your data. And the mean gives you the location of the data the range gives you range variance and deviation standard deviation gives you how did how diverse is your data how far apart your data is from the. So it also gives you the location but in terms of discretion or variability. Are we doing. I did say that what paper we're doing is October November 2017. And I think it's you are able to see right there. A theory is a, or N is it number one? Number three. Number three. Because a theory accounts for facts. And it will explain why facts are as they are observed. Happy. Do we all agree? Yes. Remember, you need to you need to talk to me so that if people don't agree, we need to go and find information about that. So I'm going to assume for those ones like this. I don't know. I know certain things, but you guys need to assist me. The process of selecting a subset of population for a survey is known as is it known as a calculation. Number two sampling. So when we have a population, we can just create a sample by selecting. Your sub or a subset of your population. There's somebody whose mic is on and there's a background noise. We can't hear you. If you have a, if your background is not conducive enough to. Oh, sorry. Now it's me. I will put it on mute. Just give me a sec. Sorry about that. Okay. And inference is one, two, three, an explanation of why certain things are as they are observed to be an educated guess about how certain phenomena may be interrelated. Three, a generalization from a sample to a population which have a high probability of being true. One, two or three. It's three inference we make. Three is crazy about the population based on the sample. Okay. Number six, empirical or empirically means based on is it on theory, observation and faith. It's based on observations. Which of the following best describe latent. And this is one of those things that I don't know what is it. Because I know one should describe something that is hidden one should describe something that is not not hidden, which one is manifest. Number seven is two hidden. Let's make notes somewhere. Let's see to help those who don't know. So a light elated is invisible can be constructed by manifests. And a manifest is visible and can be observed. Okay. So now I know I need to remember that also for future. So the one that will be number two. So in a way it says a latent will be your dependent variable. Isn't it is the one that you want to also predict based on the observations. It's something that you don't like things like anxiety. You can see or depression. You can see. But you can predict or IQ or intelligence or emotional intelligence. You can see it but you can estimate. Yes. Okay. Now I got it. Okay. A psychologist number eight a psychologist has a theory that visualized perceptual ability influences the max. Oh, gosh, wait, let me read it again. A psychologist has a theory that visual perceptual ability influences the max that the learners will get in mathematics. In this example visual perceptual ability is what variable is it a dependent independent and hidden. Number two. It will be independent because it influences what the micro do so that will be your X observation and that will be your Y. That is your input. This is your outcome. And that is independent variable. When a construct is measured, the resulting quantity is referred to as variable as a variable. The mean is the sum of all the observations. The standard error is the deviation of the mean of the observations from the means. What number is this? A psychologist. Yes. I don't know if it's my connection but I can hardly hear you. You can hardly hear me. I don't know if it's. Yeah, I don't know if it's only me. And now, can you hear me? So you want me to speak loud? I am as loud as I can be actually. It's clear on my side. Yeah, I think it might be your connection. Okay, what I would suggest is to check the connection. Yeah, check your settings and increase your volume. Maybe. I'll put on earphones as well. I think sometimes they help. Okay, so question 10. Maybe it's the way that it's going. Oh, okay. Okay, so question 10. A psychologist is interested in studying the interaction between small groups of four to five people in each group. He suspects that the interaction between the groups can be described in a similar term to the interaction between the individual groups in order to be able to do a scientific study of this. A question. You would like, you would have to provide A or N definition of the called interaction. He's interested in studying interaction between small groups in each groups. He suspects that the interaction between such groups can be described similar or in a similar time to the interactions between individual group in order to do a scientific study of this. Question. I would like to provide definition of the called interaction. So is it A? Can I jump in there for interaction? Yes. I would say looking at the at C, interaction would be a construct. Lady that says to me C would be a construct and I only see construct in number one. So my answer would be number one there. My answer would also be number one because for the researcher to start, there needs to be a research question for a research to operate. I agree with that. The research question must be established before research starts. So the question would read if we select number one in order to be able to do a scientific study of this. A research question would have to provide an operational definition of the construct. Does it read much better? Yes, definitely it does because this one would have said if I take this one to do a scientific study of this experimental, you would have to provide a research definition of statistical interaction. No, doesn't sound right. Hypothetical question. No, also doesn't sound right because I have to provide an empirical definition. No, also doesn't. So number one is the right answer. And also based on what everybody has just said in order to identify which one will be correct because interaction will not be a statistical parameter. It can be, but in this instance, it's not because you're not going to define those ones that you can define your construct because it's those observations that you made. Okay, so question 11. The variable manipulated by the researcher in an experiment is called the. Is it an independent or is it a dependent? I would say two. I'd say two as well. It is called an independent variable because he will have to manipulate your independent variable when you use them in your model or any way where you want to test or you want to predict an outcome, which your outcome would be your dependent variable. The 10 population refers to. Number one. Number one, yes. Number one. One is correct because this one set is the subset and this one says the set of all variables because all variables from part of the group and we're not interested in the set of variable we interested in the set of the population, which is all set of all elements of interest and all elements of interest have variables that are characteristics that defines those. It's all that set. So it cannot be that. So number one is correct. The symbol X bar refers to while the symbol mu refers to. What when you answer this question, think of it this way, we have a population which is big and then we have a sample which is more. Always when it talks to the. Like symbols, always think of it complex simple. So complex complex in a way that you can even pronounce it simple in a way that you can actually even make sense out of it to say oh this letter represented X. So the simple X bar refers to and while the mu refers to. Number one. Number one. Number one. Number one. This is your sample mean, which is your simple X bar. And your Greek letter so I could have just said Greek. We use Greek letters. New is your population mean. That would have been correct, but this is wrong and that is not a standard deviation. A standard deviation is sigma for the population. Oh, that is the sample for the sample standard deviation is s. That would have been an s and for the population variance that would have been a sigma squared. You need to also know that that is a variance is sigma squared. That's population standard deviation would have been just the sigma. In probability theory. The number of distinct events that could possibly occur during a performance of an experiment is referred to us. Number three. Number one. Number one is not correct. Number three. Number three talking about the number of is a collection of all events. correct number 3 talking about the number of it's a collection of all events if you watch the last session that we had together I don't know when did we have it when we dealt with probabilities we spoke about the sample event which is a collection of all events in a simple uh sorry those who don't know me uh I don't have a good handwriting so you will bear with me you will just listen to my voice it's a collection of all events that is a sample space question 15 the table below gives the frequency distribution so this is a summary table of numerical information of exam of number of students in a psychology exam mark so they gave the range which starts at 40 and the above and ends at above 81 and they have your frequency count the question is what is the probability that a student will get a mark between mark between 51 and 70 51 and 70 which is those two together or maybe I should have extended the table this way what is the probability that a student will get a mark between those two so in a lecture what they are asking you is you need to add all these values calculate what we call here total so did you calculate you need to do the calculations so add them 8 plus 12 plus 20 plus 30 plus 22 plus 18 what do you get 110 now we need to come here and calculate the percentage actually not a percentage we need to calculate a relative frequency oh I need to get to the just of things so we need to come here and calculate what we call the relative frequency and we can use this relative frequency as our probability so how do we calculate that you need to add you need to say 8 divided by 110 what do you get it's 0 comma 0 7 I'm going to leave it at 2 decimal because I see our probabilities here as are two days in two decimal then we need to say 12 divide by I'm going the the long route anyway so but I'm just demonstrating the concept because we didn't cover this during our sessions 12 divide by 110 and that will be 0.11 0.11 you need to round off correctly as well because the answer there was 0.109 so if I round it off it will be 0.111 and then 20 divide by 20 divide by 110 you will say 20 divide by 110 0.18 0.18 the next one 30 divide 30 divide by 110 0.27 30 divide by 110 0.27 I'm not going to complete the whole table so you get the you get the just of things you understand what we were doing there so when you do all of them and complete that the total here at the bottom should be equals to one the answer for this should be equals to one and remember that the sum of all probabilities are equals to one so when you get one day you know that you have done the right calculation you can go ahead and do 22 divide by 110 and 18 divide by 110 and get the answer and add all the relative frequencies and see if you get one but I'm going to stop right there so that we can move on so what we need to do right now is to answer the question that we asked so the question says we need to find the probability that the mark which I'm going to connect my x value lies between 51 percent and 70 percent so if that is the case so therefore it means I'm going to have to find the relative frequency of my value where it is equals to 51 and 60 percent plus my relative frequency where it is 61 where x is equals to so I can put these things in the don't forget the percentages as well where x is equals to 61 percent please forgive me for my handwriting okay let me rewrite it nicely sorry my bad because I I can't even see what I am writing let's let's write it maybe I will second time around it will appear right working on a pdf it's difficult than when you work on a powerpoint okay it did remove that so we need to find the probability where x is between 51 percent to 60 percent plus we need to add because it says between 50 and 70 plus where x is equals to 61 percent to 70 percent which then we did calculate that remember I said these are our probabilities so we're going to take 0 comma 1 8 0 comma 1 8 plus we need to add 0 comma 2 7 and that will be 7 plus 8 is 5 carry 1 2 plus 1 is 3 plus 1 is 4 comma 0 you can take your calculator also calculate it which is 0 comma 4 5 or alternatively because I showed you the long way of doing it alternatively we could have just said I'm going to show you another way of doing the same thing let me use the site without complicating your lives so but you know that you need to share with people different ways and they need to select whichever one they feel comfortable with so because they said we need to find the probability of x lying between the two values so we could have went and got the values which is 20 plus 30 and divide that by 110 and the answer that we will get here would have been 50 divide by 110 do the calculation what is 50 divide by 110 0 comma 4 5 yeah 50 divide by 110 it will be 0 comma 4 5 0 comma 4 5 option one or option two those number one or number two whichever step you want to follow there is no right or wrong way of doing meds there are many ways to skin a cat so I've shown you one and the other one so choose whichever one you feel comfortable with I've shown you the statistical way of doing it and the easy way of doing it as well so the complex way and the simplest way but I needed to do the complex way first okay so that is one number 16 a test for short term memory capacity is normally distributed with the mean of 100 and the standard deviation of 10 what is the probability that a person is chosen at random now that's the other thing in your exam you need to also be in mind when you answer your question how do you identify what question and what you need to do with that question so how would how did I know that with this question when they are asking me about the probabilities I need I needed to do this it's because when they talk about frequency distribution and they ask about the probabilities I know that they are talking about discrete probabilities so and as long as they give me a table with my x observation and my frequency and they're asking me to calculate my probability which will be my probability of x then I know that this is my discrete probabilities now moving to this one it's also asked about the probabilities I need to know when they start talking about normally distributed and they give me the mean and the standard deviation then I need to know that yeah we're talking about the normal distribution and when they talk about normal distribution and they ask me about the probability what comes to my mind it means I need to also use the table we did cover this the last time we met so I hope you still remember we need to first calculate the z score because we need to first standardize the equation or the units of 125 we also need to bear in mind the sign of the question because it says what is the probability that a person chosen at random will have a score of 125 or more so it means greater than and when it's greater than there are a couple of things in your mind that you need to also remember when you go to the table what will happen if my answer is negative what will happen if my answer is positive what must happen you need to also have that in your mind so it says we need greater than and we know our formula it's the x bar minus the mean divide by the standard deviation our mean given our standard deviation given and our x always is the question so I want you to do the calculation so our x is 125 minus the mean of 100 divide by the standard deviation of a 10 do the calculation leave your answer to two decimals if possible let me know how much you get 2.5 2.5 2.5 okay so it seems everybody is getting the same 2.5 I'm gonna just put a zero there at the end then we need to go to the table but you also need to remember the following our sign says greater than so when it's greater than and our answer is positive which side of the table must we look for the smaller portion the smaller portion which is which is yes so let me show those who didn't attend and they didn't watch the recording so if it's greater than you can just throw like for example if you forgot you can just draw your normal distribution table or graph so it says greater than so it means it will fall on this side so if it is positive it will be from the smaller side if it's negative it will be larger side so we're gonna go to the table we're gonna scroll up that's where we find the tables so in this instance you should have another you can have another thing open next door to check your table maybe I should have opened another exam paper so we are here on their probability table we're looking for 2.50 so I must go to the two so this is 0.00 so we need to find 2. this is once and this is 2.03 2. we're looking for 2.5 right 2.5 so that is 55 so that is what we're looking for so where is we looking for the smaller portion or larger portion sorry smaller smaller portion so we're looking for the last column so we're not looking for that one so we can go to the last column which is that should be our answer 0.0062 let's go back to the question I'll open another exam paper and leave it there for so that we don't have to scroll so many times we can just save time oh there you go so the answer we found was quick question yes so if the the question remains same everything remains okay the question remains the same but x let's say it's less than 100 where it will give you a negative answer and they still want or more and meaning our answer will be negative so we'll only be we'll be looking at the the larger portion since that the answer is negative yes so if if the answer here was minus yes sorry on a pdf my thing it does that all the time I don't know why it flicks so sorry it will come back maybe let's see doesn't want to come back oh there we go give it some time okay so I don't know okay but you get the idea so when it's negative then you go to the larger portion so if it's negative there you are you will go to the larger portion so I'm not going to entertain that flicking around so the larger portion yeah we can move on yeah so that would yeah okay so moving on to number 17 suppose the weight of population military recruits are normally distributed with the mean of 64 and the standard deviation of eight different samples for these recruits each with the sample size of 16 are drawn we would expect the standard deviation of the sample means which is the standard error to be so yeah they're asking you to find the standard error so you also need to remember that remember now also we're still in the population so the minute they start introducing concepts like standard error then we moved away from normal distribution we are now in the sampling distribution of the means because then now we're talking about multiple samples on the other one when we were talking about normally distributed we were only talking about when we have only one thing here we say we have different samples so this is your sampling distributions so because we're talking about multiple samples then they're asking you to calculate the standard error if they were not asking you to calculate the standard error they would have asked you to calculate the z I'm just gonna write the z formula oh yeah z formula it says the sample mean it will find me minus the population mean divided by the standard error which is your population standard deviation come on while we started nicely and this happens it is Friday for this thing I guess so my my PC is telling me it's six o'clock you shouldn't be doing this so standard deviation divided by the square root of n it will come back okay so this part at the bottom of this formula gosh that part is what we call there standard error just give me a sec let me stop sharing and I'll come back and share again I'm not sure if it is my PC or the system itself I just want to see if I'm not sharing if things don't flick things don't flick so it's only when I am sharing then I don't know how to to handle that okay let's see so okay so this thing doesn't want me to to show you so what you see there at the bottom that's what I wanted to write there is your standard error so this is your standard error which is your standard deviation of the sample means so that's what they're asking you to calculate so in order to calculate that you just need the standard deviation of eight so because I wanted to write it here the square root of n standard deviation of eight divided by the square root of 16 do you know how to use your calculators on your calculator you have the square root button so I don't know the answer is two yes because the square root of 16 is four divided eight divided by four eight goes two times and the answer is two don't understand this and I can't write it down when it's flashing hey yes it's very disturbing and irritating you see the the the one that you wrote first and the the z formula first you put an s at the bottom is is s equal to sigma over the square root of n sigma it's not an s or on your side do you see it as an s is a sigma um oh is that a sigma yes so it's not visible nicely it looks like an s let's extend that my handwriting it's good that you are asking because my handwriting yes it's terrible I thought just because it's jumping my eyes are also jumping okay it looks like an s sigma that says that's your standard deviation I don't know why he's doing that why is it behaving like that okay so that is 17 18 oh we still have a long way to go we are only on 18 a marble is the visual things like this then you must know that this is basic probabilities if one marble is drawn at a box oh at random from the box what is the probability that it will be read so we need to add up all of them so that we know what our sample space is in this instance what our n is so each day six plus four plus five is equals two how many there are 15 that is our sample space and we know that the probability of x being read because they say only if one marble is read so we can say where x rate is one only one marble that is given by oh not the probability again but it's given by x number satisfying the outcome divided by how many there are 0.4 the answer is two 0.4 there are six red marbles over over 15 over 15 number two 0.4 0.4 okay there are 19 females and eight males in the in a group of psychology student after 19 females only four have no brothers while three of the males are only are the only children if a student is selected at random from the group what is the probability that it will be a female with no sibling now remember that time when we were doing the probability I said I like to use contingency tables as well because yeah we can have our females and our males and we can say there are 19 females and there are only eight males because that is our total but they also said brothers and no brothers brothers and no brothers so only four females have no brothers or sister so let's see no brothers or sister four of them that will be there while three of the males are only children are the only children which is exactly the same which is exactly the same which is no brother or sister if a student is selected at random from the group what is the probability that it will be a female with no sibling remember satisfying females no sibling divided by the total remember that will be a joint probability a probability of female and no sibling I don't know how to write that but we know that inside we create joint probabilities outside IO as that's where you calculate your simple probability what is 19 plus eight 27 so that will be four divided by 27 which is option number three three is it possible to not go to use this to not use table because I'm looking at the question and just by saying 19 plus eight it's 27 remember you don't have to use the table it's just to help you understand what the question is talking about so that then you don't have to always scratch your head so if they would have said what is the probability of females with siblings you would have done 19 minus four because here they say only has no brother and sister so therefore it means the remaining has at least a brother or sister a sibling yeah so it would have been 15 so you see you are able to just quickly populate and calculate what is missing and use what is missing to answer the question yeah so here we could have just taken the four and divided by 19 plus eight as well which is what we did here that's I didn't mind without using the table yes so yeah I'm just giving you tools as well so whichever one you feel comfortable with the easiest so you don't have to waste remember I told you in the beginning you have almost like 60 to 70 questions you're writing a two hour exam you don't have to find alternative ways of answering questions find the one that is easiest and then move to the next one move to the next one okay question 20 a variable is normally distributed with the mean of 50 and the standard deviation of 10 if this variable is transformed to a standardized normal distribution what will the value of the mean and the standard deviation of this distribution be so here they're asking you what are the properties of a normally distributed number one yes I say that with the mean of zero and the standard deviation of one there is nothing you can do about it because they just want to know what will be the mean and the standard deviation of this distribution hey 21 the probability of an event can be determined by remember we're talking about the probability one the set of all possible values of statistics when all possible values of a fixed size are taken from the population observing the number of times that an event occurs divide by the number of times that it could possibly occur during a specific experiment the distribution of means obtained from all possible samples which can be established by applying a central limit theorem one two or three I'm guessing but I said two that's one okay so why one is incorrect one is incorrect because it talks about the statistic and the possible values of a fixed taken from a population that would explain something else is not explaining the probabilities number three it's also not correct because it talks about the distribution of the sample means so this is a definition of sampling distribution because it talks about different sample size that can be established from a central limit theorem remember the central limit theorem will tell you when you increase the value of your standard deviation let's go back there when you increase the value of this standard deviation what happens to this when to the probability when you increase the value of your mean or your sample what happens that's what central limit theorem will do oh and going back there while we're still at that so this is the formula we use to calculate the sampling distribution of the mean z score and use this to find the probability as well and in the hypothesis we also use the same formula okay let's go something moved okay so that and that is not true what makes number two true is it talks about an event happening remember probability is a study of chances is a study of events okay probability that something will okay an event will happen and that's the correct answer is number two by convention the total area underneath the normal care is set to equal is it zero is it the standard deviation is it one we also dealt with this on Tuesday but the total area is your probability the area underneath the care that is this shaded area it's going as one and split it in to half the site will be 50 percent and that site will be through somebody's unless it's my bc later that's later okay yeah the mean and the standard deviation of a set of tests are 20 and 8 so this is our mean and this is our standard deviation if the z score which corresponds to the test score is 14 that's the set score or the test score of 14 is calculated which in which of the interval listed below will it fall so probably here they want you to go and find calculate the z or calculate the probability very difficult to tell which of the intervals so if we take our z score let's just calculate our z score because we used our z score to compare so we say the mean x bar minus the mean divided by the standard deviation so our x bar our x is 14 minus the mean is 20 and the standard deviation is eight calculate minus zero comma seven five so which interval will it fall in number two the distribution of sample means which is sampling distribution for the number of sample drones from the same population can be determined because of is it one the z distribution two isn't the central limit theorem three is it the statistical inference i would guess and say three i would guess and say two let's go to do do you have i keep on talking about sampling distributions and all that do you guys talk about sampling distributions on your in your module yes you do page 57 page 67 is it page 67 on your site told you there will be some places where we go back and look at and it's specified by we have shown this that the distribution of the sample means can be obtained for a very simple and specific question fortunately the general characteristic of the distribution of sample statistics such as the mean are specified by mathematical call central limit theorem it follows as such if a sample random sample of any selected from okay the sampling distribution of mean obtained from all possible sample is approximately normally distributed from all possible sample is approximately normal with the mean and the standard deviation the central gives you a precision of the distribution that will be obtained if you selected every possible sample okay so we have our answer and our answer is option number two and then we come to a symptotic property of a normal kef oh so what does that refer to the fact that so an asymptotic property of a normal kef refers to the fact that one number two the kef is barely kept to the endpoints of the kef gets closely to the x without touching it or three the kef is symmetrical it is number here number two symmetrical it will refer to that the mean and the median are equal the belly kef will just just talk to the distribution of the mean of zero and the standard deviation of one the asymptotic manner will tell you that this kef always come closer to the x exists but it will never touch the x exists that is an asymptotic property consider a hypothesis which describes a possible relationship between two variables now we're talking about a relationship between two variables the null hypothesis refers to which specific kind of a relationship between the two variable oh yeah right number one no relationship number two positive relationship number three significant relationship number one number one okay and that will be number one because when we state the hypothesis testing the null hypothesis will state that there is no relationship which means they are independent with the flicking flicking this they be me in the independent and your alternative will state that there is a relationship which was and now it was which will mean that they are dependent oh yeah right maybe probably in my afterlife I was supposed I'm gonna be a doctor I don't even have to independent independent statistical hypothesis are statements about one the population parameter two sample statistic three z distribution when we state the hypothesis testing do we use the sample or do we use the z distribution or do we use the population parameter when we always use population parameter for example when we state that for a null hypothesis we state that the mean is greater than 100 we use the population we don't say the null hypothesis says the mean bar is greater than 100 or we don't say the mean the z distribution is greater than 100 we don't do that we don't do that we use population parameters that is correct suppose we had have stated that the null hypothesis the mean is equals to 10 and the alternative the mean is less than 10 so you always remember that your null hypothesis always have an equal sign and your alternative helps you to make the decision because the sign in your alternative will tell you what type of a test you're doing are you doing a directional test or are you doing a non-directional test okay find the sample mean and find that the sample mean corresponds to the z of minus three this means that the corresponding p value would be so also based on what we have we can also go with our normal distribution and say if it's negative we use smaller portion negative smaller portion positive larger portion so now we have our z we need to go find the probability which is our p-ring we find it on the table the z score is minus three so therefore it means we go into go to the z normal distribution table and look for three without the minus because the minus helps us in knowing whether are we going into the smaller portion or the larger portion or if I can remember this we're looking for the smaller portion so it's the last column so you take your three and you go to the smaller section which is zero comma zero zero one three it is equals two I don't know why I'm giving you all the answers now and not letting you do this or tell me okay happy thank you yes ma'am moving a hypothesis which the alternative states that the mean is greater than 50 is a hypothesis and requires a statistical test I'm guessing number three you are correct three it is number three because it's a one directional test and when I'm saying it that way so I've already said it's a directional test which requires a one tail test it's number three the level of significance of a statistical test which is an alpha value refers the p-value such as the calculated from their test statistic indicates the maximum risk that the researcher is willing to take for a for making a type one error is used to indicate the probability of making an error by not rejecting the null hypothesis I think it's two I think it's two you think it's two let me open the note and I think it's something that we did right in the beginning did we no I didn't do it with you guys okay so I didn't do it with your class I did it with the IOP class it can be number three or number two let's let me just double check that um when do we make type one error so I want to open the notes it's the statistics so many notes so many notes that one error occurs when the null hypothesis is wrongly rejected so we type one error is when the null hypothesis is rejected but is true so what does the question is asking it says it indicates the probability of making an error by not rejecting the null hypothesis is the question about the is the question about the the error type or is it indicating what that p-value represents it asking you about no it's asking you about the error type because the level of significance let's let's go there where would we find it let's go for such fine from your notes fine where is fine there is fine we looking for the level of significance type one error I can find it it's not gonna find I'm not gonna find it there I think type 11 of significance what did we do this which section of the research analytics we did this in our session one maybe we can check page 105 page 105 oh it's on page 84 on the study guide page 84 yeah page 85 the second paragraph there we go so so the level of significance the alpha represents the maximum risk that we are willing to take to make a type one error of rejecting the null hypothesis so let's go there it's used by the probability of making it so that won't be right this will be the correct one because it's the same as is the maximum risk that the researcher is willing to take to make a type one error by rejecting the null hypothesis making a type one error which that one will be because this one is broad because it says making an error you can make either a type one error or a type what type two error which is type two type two error I know that it's a beta significance and type one error is alpha so the right answer is option two the answers are in the study guide I told you I'll open your study guide we'll always make reference to it so that we don't make any mistake when applying a statistical test if the p value is larger than the significance we the alternative so the decision this is the decision rule you always need to remember that we do not reject it the decision the decision to reject number two yeah so the decision rule says if the p value is less than alpha we reject the null hypothesis if the p value is greater than or equals to alpha we do not reject the null hypothesis we do not reject the null hypothesis but now we not talking about the null hypothesis so this is the rule but we're not talking about the null hypothesis they're talking about the alternative so based on the decision rule based on the decision rule it says if the p value is larger than the level of significance which is the second part if it's if it's bigger than the level of significance it says we reject the null hypothesis so if we do not reject sorry it says we do not reject the null hypothesis if we do not if we are not rejecting the null hypothesis therefore it means we are failing to do what should there alternative accept fail to reject no we fail to reject no no no no no we do not accept if it's not number one we do not accept we do not accept because we're not rejecting the null hypothesis so okay so we're saying the null hypothesis is true yeah if it's greater than therefore it means we're saying the alternative is not true oh now we're talking about the alternative yes we're talking about the alternative so if we're not rejecting the null hypothesis therefore we are we are not accepting the alternative so we do not accept the alternative so always need to go back to the room because that will give you a the base in terms of how you can answer the question because yeah they asking in relation to the alternative so if we were rejecting the null hypothesis if it was less than then we would have um sale uh one of the two either we fail to reject the alternative or we accept the alternative because we will be rejecting the null hypothesis okay now we go to type two era type two era okay is when this is one of the other section that i am i have forgotten about it because we did this in my first year of stats and now we no longer talk about it and the stats that i assist we don't even look at the type eras so it has been very long so a type two era let's first look at the question what the options are a type two era okay is when one the null hypothesis is rejected when it should not be rejected that won't be true number two the null hypothesis is not rejected when it should be rejected that sounds familiar the alternative hypothesis not accepted when it should be accepted number two it should be rejected type two era is not rejecting the null hypothesis when the null hypothesis is not true so that is straightforward it's not rejecting when it should be rejected yeah which one number number two number two number two number two uh good people can we take i need to go drink water can we take five minutes just we have been going on for almost one hour thirty minutes we still have one hour thirty minutes left are you going to drink just what ha i also need to use the bathroom okay see you at one time i'm also going i'm also going to stop the recording so that then this can be uploaded as part one and then we'll go and do part two later on okay so it's 632 now what time are we coming back uh at six let's let's uh let i'm i'm also going to change the kids had eaten wait