 Hello, I welcome you all once again to my channel, Explore Education and Dr. Ashmi Singh, Assistant Professor, Department of Education, Mrs. Kannagalsri College, University of Allahabad. And now, I am going to discuss the concept of descriptive statistics, okay? And the lecture will be in bilingual mode and it must be useful for all the students. So first of all, descriptive statistics, okay? We have been talking for so many days about statistics, measures of central tendency, measures of variability, measures of position, measures of correlation. All of these are part of descriptive statistics. But we haven't studied the heading of descriptive statistics, so I am trying to cover all of this so that you know what descriptive statistics are. It is very easy. Descriptive statistics, means those statistics that help in the description of the data in the ink, are all part of descriptive statistics. Once again, in the last video, I have discussed descriptive statistics and inferential statistics in the middle of the video, you can go there and see them. So let's start. What are descriptive statistics? Where should we start? So they are saying that in today's society, decisions are made on the basis of data. In today's society, what we take as a rule is based on data. Today's data is the new oil, data is the new currency, all of this is said. Meaning, data is so important. Most scientific or industrial studies and experiments produce data and the analysis of these data and drawing useful conclusions from them became one of the central issues. So they are saying that a lot of scientific and industrialists who use these kind of experiments and use these kinds of experiments produce data and they produce data for the eyes. And from the sources of those eyes, we reach to great heights. And this is the main issue of today's society. The field of statistics is concerned. Then when we talked about statistics, what is descriptive statistics? So we have to take a scientific example of which we collect, organize, analyze, and draw conclusions from those data. These are the statistics. That we organize the eyes, arrange them in an organized manner, arrange them, and reach the nishkarsh. Because only the eyes don't say anything. You have to categorize it, analyze it, organize it. And these are the science statistics. Statistical methods help us to transform data to knowledge. What are these scientific methods? What does it do? It creates knowledge from the eyes. Meaning, the eyes don't say anything. But what is coming out of the eyes of the nishkarsh? The knowledge that is being created is the work of statistical methods. Statistical concepts enable us to solve problems in a diversity of contexts, add substance to decisions, and reduce guesswork. These are our observations of the statistics. The concepts help us in dealing with problems and reduce guesswork. Meaning, they can be explained in a way. Definitely, this is how we reduce guesswork with a bulk. The discipline of statistics stemmed from the need to place knowledge management or a systematic evidence base. Earlier works on statistics dealt only with the collection, organization, presentation of data in the form of tables and charts. So, we are saying that the initial work in the statistics was only that we collect, organize, and present in the form of tables and charts. But now, it is much more complicated and complicated. So, this is the issue of statistics. Now, if we talk about descriptive statistics, they are saying that statistical methods are used in almost every discipline. We have to study all of them. Social, wherever you do research, wherever the data is used, whether it is agriculture, astronomy, biology, business, communication, economics, education, electronics, so geology, health sciences, any field of science and engineering, the statistics will be the same as the talk of the eyes. The first of these is to assist us in designing experiments and surveys. These statistics help us in experimenting and surveying. We desire our experiment to yield adequate answers to the questions that prompted the experimenter survey. We want to get the right answers to the questions that prompted the experimenter survey. We would like the answers to have good precision without involving a lot of expenditure. So, they are saying that they help us in two ways. One is that we want our decisions to be more subtle. And the other is that the statistics help us to organize, describe, summarize, and display the data. So, these are descriptive statistics. Which means that we want to display the statistics of the eye's organization, the eye's vision, the eye's awareness in the beginning, and the statistics that help us in all these things are descriptive statistics. The part of the vision of the vision of the eye is used in the vision of the eyes. And when we talk about inferences, when we talk about predicting, when we talk about making a future, when we talk about generalizing, that part is of inferential statistics. When we take out some inferences, we are saying that these statistics are in drawing inferences and making decisions based on data. We say that based on this data, we have reached the vision of the eye, we have drawn the inferences, we have predicted, these are inferential statistics. The rest of the parts where you are describing the data, organizing, summarizing, classifying, and displaying, are all part of descriptive statistics. Now, the part of the descriptive statistics is the part of descriptive statistics. So, if we start with data, we start with the data classification, we can classify the data in many ways, like quantitative data, qualitative data. So, what is quantitative data? Our observations are measured on a numerical scale. Non-numerical data that can only be classified into one of the groups of categories are said to be qualitative and categorical data. They are saying that either data will be quantitative, meaning it will have a limit, or it will be qualitative where there will be no numbers. So, the qualitative ones are also called categorical. And the quantitative data is on a numerical scale. When it comes to the scale, listen to it again, what was the nominal, ordinal, interval, and ratio scale? So, what was the nominal scale where only the name works? There are some names, like the names of the children in the class, so what is the numerical scale? We do not know what is the name of each name, what is the difference between the two. This is not known. So, this is the numerical scale. And the other qualitative data is generally classified into one of the groups of categories are said to be qualitative and categorical. Then they are saying that you can further categorize qualitative data in nominal and ordinal data. Look, nominal data means only by name, meaning you know something, that is nominal. But ordinal data means you know their order, who is above and who is below. Data characterized as nominal have data groups that do not have a specific order. In nominal, there is no order, who is above and who is below. It does not matter. Anyone can write in any form. For example, an example of this could be state names or names of the individuals or courses by name. For example, you are given the name of some states, some people, some courses. So, what is their order? Write in any form. But the ordinal data is in a specific order. Either it will be increasing or increasing, or it will be decreasing. One example would be income levels. For example, the level of income. So, the level of income is less than 5000, 10,000, more than 25,000. So, if you put it in an increase or decrease, then that is ordinal data. Where only names are given, that is nominal data. Okay? So, let's talk about data. Let's talk about sampling. We have not talked about sampling yet. We have to cover sampling separately. But since it is data, what you do is, we have talked about that we have to take out data from the population. We have to take out samples from the population. So, sampling is the way to take out samples from the population. Hmm. This was a lot. It must have been a small font. But you will see it on your computer screen. You will understand. It says, this sample is obtained by collecting information from only some members of the population. We cannot study the whole population. So, we collect data from some samples. So, what should be done? A good sample must reflect all the characteristics of the population. So, a good sample should be done that keeps all the characteristics of the population. Samples can reflect the important characteristics of the populations from which they are drawn with differing degrees of precision. And what are the samples? That they keep all the characteristics of the population inside themselves. It is possible that you could not choose a very good sample. A sample that accurately reflects its population characteristics is called a representative sample. That sample that reflects all the characteristics of the population is called a representative sample. That means, it represents the population. A sample that is not representative of the population characteristics is called a biased sample. And that sample, which does not reflect the characteristics of its population, is called a biased sample. That means, it is from the past. A sample selected in such a way that every element of the population has an equal chance of being chosen is called a simple random sample. The easiest sampling is the most popular sampling which is called a random sampling. It means that every individual or every element of the population has equal probability that it can be selected. So, they will call it a random sample. These are some of them. Later, they will cover it in detail in some other detail. Then they are saying that equivalently each possible sample of size n has an equal chance of being selected. In this, every sample, that means, every element of the population can be selected. Okay, this is a random sample. Then what is the systematic sample? A systematic sample is a sample in which every kth element in the sampling frame is selected after a suitable random start for the first element. Systematic means that you chose the first sample under a random sampling. But after that, you chose that after that, you will take every 11 samples or every 25th, 50th, any kth element that you have chosen. So, this systematic sampling is done. Then, if we list the population elements in some order and choose the desired sampling fraction, we can do this too that we can take alpha vertical, take every A, B, C, anything. Then, what is the stratified sample? Look, in your sample, if there are both male and female, there are both rural and urban, if there is such a category in your population, then you will have to do stratified sampling. Stratified means, you make a standard in it. That you have to take so many male and so many female. Otherwise, it is possible that all the males or all the females or the second category will be very less represented. So, we have to do stratified sampling. Stratified sample is a modification of simple random sampling and systematic sampling and is designed to obtain a more representative sample but at the cost of a more complicated procedure. Stratified sampling is a way of sampling. It is better than simple random and systematic but gives a better result. But it is a little complicated. Then, stratified sampling is done. Now comes cluster sampling. What is cluster sampling? The sampling unit contains groups of elements called clusters instead of individual elements of the population. In this, it is like a geographical part. We assumed that we would take this part and take this part and take this part. So, instead of individual clusters, this cluster is done. Then cluster sampling is also called area sampling. That is why it is called area sampling. Here as well, we have discussed the design of some of the sampling. There is a lot of sampling. It is also about what is going on in qualitative and what is going on in quantitative. We will talk about that later. But, there is a little way of telling that there will be sampling in descriptive statistics because it is related to data. Then, graphical representation of data. In your course, frequency, distribution, graphical representation is not discussed separately because it is very easy and you can easily understand it. Graphical representation of data is not understood by looking at the data. But when you represent it on a graph, it is understood that the graph is increasing, it is decreasing, what is the calculation of it, what is the correlation. So, this is the graphical representation. There is nothing in it. I will tell you this quickly. The source of our statistical knowledge lies in the data. The statistical knowledge that is needed is in the data. Once we obtain the sample data values, one way to become acquainted with them is to display them in tables or graphically. When we get data, we close it or present it graphically. So, it is understood. Okay. So, the most important thing is that the most common graphical displays are frequency table, pie chart, bar graph, Pareto chart, and Historia. So, a group of bars whose heights represent the frequencies of respective categories is called a bar graph. What is bar graph? When it becomes a long bar, you will know that in this year, there were so many signs, then there were so many, then there were so many, increasing, decreasing, decreasing. Who makes pie chart? When you take a circle, and there are some parts, 20% is in Hindi medium, 25% is in English medium, then it is known that it is different in colors. So, it is understood as pie chart. It is known that what is its representation. Similarly, frequency table is a table that divides the data set into a suitable number of categories. Right? You can make a frequency table. So, how much part is being covered in which table, according to you, it will be known that there is more or less part. Similarly, there are histograms. Histograms can be used only for quantitative data. These are only used for quantitative data. Histogram compresses a data set into a compact picture that shows the location of the mean and modes of the data and the variation in the data, especially the range. Right? So, you can easily understand this without any explanation. You just have to remember that bar graph is called histogram, it is called pie chart, it is called in every book. Just to tell you that it comes in descriptive statistics, graphical representation of data. Why? Because it is burning the data. Okay. Now, we have read all the things. That is why, first of all, I have written the dates here. Measures of central tendency, we have read that the maps, the maps of the central probability whose tendency is that it is the center and the center, the center wants to be mean, median mode. We have read Madhya, Madhika and Bahulak. Then what? Measures of variability. Measures of central tendency, we do not know how much data is showing, how far it is from Madhya, how many out layers are there. So, for that, we have to read deviation. How much data is written. Mean deviation, average deviation, standard deviation, that is Madhya, Manak, Chaturthansh, Vichlan and Paras. We have also read that. Then, measures of position. We do not know what is the position of data. What is the relative position? That means, how many people are above it, how many people are below it. So, how much, how much percentage, for that, percentile, in every 100, in every 10, quartile, in every Chaturthansh, and percentile rank. We have also talked about this. Then, measures of correlation. Then, the data, the variables, how are they correlated? Are they positively correlated? Are they negatively correlated? Or are they not showing any correlation? For that, we have to read correlation. We have read a lot of methods, like spearman's rank, product moment correlation, partial correlation, multiple correlation, bi-serial correlation, point-bi-serial correlation. I am not telling this separately. You have read all of them. And in this way, this part of descriptive statistics is covered. So, descriptive statistics means, those statistics that are in the description, in the classification, in the analysis, in the displaying, they are all in the descriptive statistics. And those that help us in prediction, they are in the inferential statistics. Okay, so I did not cover this holistically separately. And you read the graphical representation yourself. It is very easy. There is nothing that you cannot understand. You have to see how x-axis goes on the graph, how y-axis goes on the graph, who is called a graph, who is called a histogram, that's it. Okay, so in this way, I have completed the first two units of your course and the remaining units I have covered progressively. Okay, I will cover progressively. So, thank you. And don't forget to like and subscribe my channel, Explore Education. I have done from my side.