 Hello everyone, today I'm going to be lecturing on chisker analysis. We use chisker analysis when you have to deal with categorical variables. As we all know by now, categorical variables fall into different categories or groups. It's like you're classifying data points according to their underlying characteristics. For example, we could have a category of eye color. Under that category, we could have categorical variables like brown, blue, black, green, and so on. Another example can be college admission results. In this case, the two categorical variables would be accepted, hee-hee, or rejected. An applicant either accepted or rejected, not both at the same time. So applicants belong to one of the two categories. It is really important with the categorical variables that they be separate. A data point cannot belong to both at the same time. When we analyze these kinds of categorical variables, we use a different approach from analyzing continuous variables. Now, before we get into the details of chisker analysis, we need to understand some fundamental or important mathematical concepts behind a contingency table. A contingency table which is a matrix or a rectangular array of frequencies in rows and columns as it's showing right now is a table showing frequency counts under different conditions. The word contingent is very similar to dependent or conditional. So the numbers of counts in each cell in a contingency table represents, for example, the number 13 represents the condition under sound sleep, yes. And taking vitamin, yes. So in this example, the first column here represents a participant took vitamin and they had a really good sound sleep.