Harold Nelson
2024-06-04
The method of constructing a contingency table given in the text is cumbersome and doesn’t give a convenient result. It is much better to use the CrossTable() function from the gmodels package. I will show an example based on the comics dataframe, which you can download from Moodle.
##
##
## Cell Contents
## |-------------------------|
## | N |
## | Chi-square contribution |
## | N / Row Total |
## | N / Col Total |
## | N / Table Total |
## |-------------------------|
##
##
## Total Observations in Table: 18730
##
##
## | comics$publisher
## comics$align | DC | Marvel | Row Total |
## -------------------|-----------|-----------|-----------|
## Bad | 2724 | 6352 | 9076 |
## | 10.136 | 4.748 | |
## | 0.300 | 0.700 | 0.485 |
## | 0.456 | 0.498 | |
## | 0.145 | 0.339 | |
## -------------------|-----------|-----------|-----------|
## Good | 2697 | 4310 | 7007 |
## | 95.372 | 44.677 | |
## | 0.385 | 0.615 | 0.374 |
## | 0.451 | 0.338 | |
## | 0.144 | 0.230 | |
## -------------------|-----------|-----------|-----------|
## Neutral | 551 | 2093 | 2644 |
## | 101.404 | 47.502 | |
## | 0.208 | 0.792 | 0.141 |
## | 0.092 | 0.164 | |
## | 0.029 | 0.112 | |
## -------------------|-----------|-----------|-----------|
## Reformed Criminals | 3 | 0 | 3 |
## | 4.361 | 2.043 | |
## | 1.000 | 0.000 | 0.000 |
## | 0.001 | 0.000 | |
## | 0.000 | 0.000 | |
## -------------------|-----------|-----------|-----------|
## Column Total | 5975 | 12755 | 18730 |
## | 0.319 | 0.681 | |
## -------------------|-----------|-----------|-----------|
##
##