Chi-squared test
The chi-squared (x) test is a statistical test that
measures the size of the difference between the results you actually get (observe) and those you expected to get.
- It helps you determine whether differences in the expected and observed results are significant or not, by comparing the sizes of the differences and the numbers of observations.
- The chi-squared test is conventionally used to test the null hypothesis.
The null hypothesis is
that there is no significant difference between what we expect and what we observe - in other words any differences we do see are due to chance.
Calculated chi squared values are used to
find the probability of the difference being due to chance alone.
Large chi-squared values mean
there is a statistically significant difference between the observed and expected results and the probability that these differences are due to chance is low.
There must be a reason, other than chance, for the unexpected results.
The number of categories being compared in an investigation affects the size of the chi-squared value calculated.
The degrees of freedom
the number of comparisons being made and is calculated as n-1, where n is the number of categories or possible outcomes (phenotypes in the case of phenotypic ratios) present in the analysis.
For example, if you were looking at yellow and green peas there would be two categories and therefore one degree of freedom.
If the calculated x^2 value is less than the critical value found in a table at 5% significance (p=0.05)
we do not have sufficiently strong evidence to reject our null hypothesis. Therefore, we accept the null hypothesis - there is no significant difference between what we observed and what we expected.
However if the calculated X^2 value is greater than the critical value
we reject the null hypothesis - some other factor, outside our original expectation, is likely to be causing a significant difference between expectation and observation.
the critical value
The minimum x^2 value that gives a 5% probability
The critical value increases as the degrees of freedom increase.
If X^2 is less than the critical value
there is no significant difference
If X^2 is greater than or equal to the critical value
there is a significant difference
Corn and the chi-squared (x^2) test
Epistasis:
epistasis example p1
epistasis example p2
Dominant and recessive epistasis:
Labrador colours:
Evolution
the change in inherited characteristics of a group of organisms over time, occurs due to changes in the frequency of different alleles within a population.
Population genetics:
gene pool.
allele frequency.
Calculating allele frequency:
Imagine a population of 100 diploid organisms that can all breed successfully.
You are going to look at a gene that has two possible alleles, A and a.
The frequency of allele A in the population is represented by the letter p.
The frequency of allele a in the population is represented by q.
If every individual in your population of 100 is a heterozygote (Aa), then the frequency of each allele is 100/200 or 0.5 (50%) so p + q = 1
In a diploid breeding population with two potential alleles, the frequency of the dominant allele plus the frequency of the recessive allele will always equal 1.
This simple formula is very important when using the Hardy-Weinberg principle.