 Dear students, we have completed the univariate descriptive analysis. Now we are going to start a bivariate and multivariate descriptive analysis. In order to do so, we have to learn trastabulation in order to perform this analysis. Trastabulation is a method to quantitatively analyze the relationship between multiple variables. This can be between two variables and this can also be between two to more than two variables. So when we look at this relationship between two variables, we call it bivariate trastabulation. And when we look at it between two to more than two, we call it multivariate or multiple trastabulation. Why is trastabulation done? Trastabulation actually facilitates our understanding. This is a very good method to understand how two variables interact with each other. And before using the inferential statistics, we can interpret the data with the help of this, how data interacts with each other. If we talk about trastabulation in SPSS, we go to analyze, analyze the descriptive statistics and in this you have the option of cross-tap. Here you will click on it. So whatever variable you do in cross-tapulation in SPSS, we can do it at the nominal, ordinal and scale level. And we can make a table of cross-tapulation between any of these variables. So here I have selected gender and education level and I am going to make a table of cross-tapulation. I will click on it. If I click on it, I will have a table of this kind. On one side there is gender and on the other side there is education level. Here I have the data telling me that the male's enrollment in the bachelor program compared to the female enrollment into the bachelor program is very significant. If we look at the master's level and the MFIL level, then this data trend changes. That is, if we look at the master's level, then the male and female enrollment master's level does not make much of a difference. We can call it 60-40 or 55-45. And if we look at the MFIL level, then we see a lot of female enrollment as compared to the male enrollment for this data set. But on the bachelor's level, there is a lot of difference here. That is, it is almost double of the male enrollment is the double of the female enrollment. So in this sample, when we looked at gender and educational level, we found out that the chances of higher education are comparatively less as compared to the male students. Similarly, if we look at the multiple cross tabulation, then we can add a variable in layer 1. Here I have gender in the row, in the column I have registered voters. That is, whether your vote is registered or not. And we have put an educational level in layer 1. And if I click on OK, then you will have something like this table in which there are three variables. That is, educational level, bachelor's, master's, MFIL, then female and male and registered voters. On the bachelor's level, we see that the number of female and male voters is less than registered. And the male voters are also less than registered. That is, most of the votes are registered in female and male groups. Similarly, if we look at the master's level, then we also see this trend here. Female and male have more proportions than registered voters. And on the MFIL level, we also see that the number of registered voters is more. This shows us that across the educational level, both for the male and female, the vote of the youth is registered. That is, the youth, if we talk about it in particular, we see there that most of the votes are registered in 858 and not in 387. So this multiple cross tabulation is very helpful for you when you have a lot of variables. In that, you can see the interaction of different variables. How to inform one variable to another variable. So instead of conducting a statistical test, and at some time, if you have to report a policy brief, then you don't go for a statistical test. In fact, you try to explain the frequency and percentage to the right people. In that context, this is a significant and useful technique of cross tabulation that we use in quantitative data analysis.