10.2 Inheritance
Chisquared tests
A chisquare test is a statistical test that can be used to determine whether observed frequencies are significantly different from expected frequencies.
They help us decide if the results we see are statistically significant. Statistical significance in this case implies that the differences are not due to chance alone, but instead may be caused by other factors at work.
It is often used in testing if a null hypothesis is supported or falsified.
If the null hypothesis H_{0} is falsified with strong statistical significance this make an alternative hypothesis a candidate to be accepted.
This is the formula for a chisquared test
A chisquared table is used to determine if the numbers we see are due to random factors. This is useful in determining if the results from a dihybrid genetic cross are due to independent assortment or not. The statistical table is used to judge at what level of confidence we would reject the null hypothesis.
Using this data do a chisquared claculation and show how significant the results are.
They crossed PPLL and ppll and then self crossed the resulting PpLl
Phenotype and genotype 
Observed 
Expected from 9:3:3:1 ratio 
Purple, long (PpLl) 
284 
216 

































Purple, round (Ppll) 
21 
72 
Red, long (ppLl) 
21 
72 
Red, round (ppll) 
55 
24 
Source http://en.wikipedia.org/wiki/Genetic_linkage
(284216)^{2 }+ (2172)^{2} + (2172)^{2 }+ (5524)^{2} = 133.7
216 72 72 24
We have 4 categories so 3 degrees of freedom and as the calculation gives a figure much higher than the 11.34 needed for 99 per cent confidence. So the Hypothesis that the genes are independently assorted is falsified. Leaving the best explanation that they are on the same chromosome so therefore linked.