chi-squared

chi-squared - BICD100 Genetics W08" Chisholm The...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
The chi-squared test for goodness of fit. This is the “basic” chi-squared test. To test how well observed data fit expected data for some number of classes (3:1, 1:1, 9:3:3:1, etc). The classes are assumed to be independent: e.g. being round yellow does not affect the probability of another pea being round green. The null hypothesis gives us the expected numbers (based on other hypotheses of independent segregation, dominance, etc, but we are not testing these explicitly--we are just testing the ratio.) Degrees of freedom: As the total is defined, if there are n classes only n-1 can vary independently. So the degrees of freedom is always 1 less than number of classes. The chi-squared test for independence This is slightly different from chi-squared test of goodness of fit. Here we test the null hypothesis that two probabilities are independent. For example if A and B are unlinked then the probability of being A should be independent of the probability of being B or b.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 06/07/2008 for the course BICD 100 taught by Professor Nehring during the Winter '08 term at UCSD.

Page1 / 2

chi-squared - BICD100 Genetics W08" Chisholm The...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online