###
5.6 Calculation of Chi-square test for deviation from Mendelian ratios

- Put your observed numbers and expected ratios (shall sum up to one) and
click the **calculation** button. In all cells with initial
values you can put data (green fields).

The number of degrees of freedom for the Chi-square is equal to the
number of cells with expected values minus one.

Example:

Test of segregation ratios from known mating can be done by Chi-square
test. If you have a test mating between two heterozygotes Aa x Aa the offspring
would have an expected segregation ratio of 1:2:1 as shown in the table below, where
the ratios are converted to a 0.25 : 0.5 : 0.25.
Genotype AA Aa aa Total
-----------------------------------------------------------------
Number, obs ** 30 51 39 ** = 120 = N
Frequency, ** .25 .5 .25 ** = 1,00
Number, 30 60 30 = 120
Deviations 0 -9 9
Chi-Square 0 1,35 2,70 = 4,05
----------

To test the applet put the bold face values from the table in the applet
and press the **Calculate** button.
The number of degrees of freedom is df = 3-1 = 2, as the material is
only providing the parameter N being used to calculate the expected numbers.
The Chi-square value is less than the test value 5,99, which means that
there is not statistically significant deviations from a 1:2:1 segregation
ratio on the 5% level.

Questions:

Calculate a Chi-square for the following observation set from test
mating of known carriers.
Total numbers of observations 30
Number of affected 16

Is the segregation ratio statistically significant different from a 1:3 segregation
ratio ?

Back to theory,
Back to theory (in Danish)
or back to the other applets