Binary, Ordinal, and Categorical Data Analysis - Agricultural Statistical Data Analysis Using Stata - page 218

individual with this gene is crossed with a homozygous recessive indi-
vidual, all of the individuals in the first generation (F 1 ) will exhibit
the dominant characteristic. However, when these crossed individu-
als are selfed (crossed with themselves), the second generation (F 2 )
will segregate into a 3:1 ratio with ¾ of the individuals exhibiting the
dominant gene and ¼ exhibiting the recessive gene.
Load the dataset Watermelon ZYMV Resistance.dta. This is a
dataset of two variables. The first variable (f2zymv) is the scoring of
the F 2 generation for resistance to Zucchini Yellow Mosaic Virus. The
second variable is the scoring of the F 1 generation backcrossed to the
recessive parent. Enter the command
csgof f2zymv, expperc( 25 75 )
he expperc (expected percentages) must add to 100% and the order
they are entered is important because this command sorts the values
in descending order before doing the calculations. Reversing the order
of 25 and 75 will result in erroneous results. The results are
+--------------------------------------+
| f2zymv expperc expfreq obsfreq |
|--------------------------------------|
| 0 25 54 50 |
| 1 75 162 166 |
+--------------------------------------+
chisq(1) is .4, p = .5297
The results indicate that the data do indeed meet the expected 3:1 ratio.
Enter the csgof command for the backcross data with expected ratio
of 1:1. To do this, enter the following and see the results:
csgof bc1zymv, expperc( 50 50 )
+---------------------------------------+
| bc1zymv expperc expfreq obsfreq |
|---------------------------------------|
| 0 50 56 51 |
| 1 50 56 61 |
+---------------------------------------+
chisq(1) is .89, p = .3447