PSY 2116 Lecture Notes - Lecture 12: Contingency Table, Analysis Of Variance, Sampling Distribution
Document Summary
Test to see whether there"s a relationship between two categorical variables. Compares the frequencies observed in certain categories to the frequencies expected in those categories by chance. Can"t use the mean because we do not have any variables that have been measured continuously. Calculating mean of categorical variable = meaningless because the numeric values you attach to different categories are arbitrary, the means of those numeric values depend on how many members each category has. Therefore when measuring only categorical variables, we analyze frequencies. Frequencies: analyze # of things that fall into each combo of categories. Combine 2 variables by creating contingency table (similar to factorial anova) 2*2 design creates 4 different groups (cells) Chi square looks at observed frequencies in each cell, compares them to frequencies you"d expect to get in each category. Chi square is calculated by adding error from each model (each cell and then checking it against the chi-square distribution.