9/14 Mechanisms of Evolutionary Change

Null Hypothesis vs Alternative Hypothesis (What are they used for?)

these are often used in statistical tests when determining whether or not HW conditions are met based on observed and expected genotype frequencies

• Natural populations almost never perfectly meet HW conditions but many genes can approximate them.

Null Hypothesis (H₀): there is no effect; there is no difference between the expected and observed values

Alternative Hypothesis (H_A): there is a difference between the expected and observed values

Frequency Histogram

Shows data points categorized into equal sized ‘bins’

frequency can be relative or absolute

What is a “Goodness of Fit” statistical test used for? What is one example of this type of test?

used to determine if an observed result is consistent with an expected result

One type is the Chi-squared goodness of fit test

What is the Chi-Squared Goodness of Fit Test? What is it used for?

used to detect the goodness of fit for data that fit into one of the predetermined categories (experimental categories set up before data collection, for example, genotypes); essentially determines if your observed sample data matches an expected distribution

Chi-Square Statistic (how does it determine when a result is significant?)

O is the count of observed and E is the count of expected

k is the number of categories

The calculated chi-square statistic has to be greater than or equal to the critical value in order to reject the null hypothesis.

Chi-Square Distribution (what is it? what part of the curve indicates significant results?)

a probability distribution function, similar to normal distribution

A chi-square statistic that falls to the right of p = 0.05 boundary indicates significant results and means the null hypothesis is rejected.

What is the critical value? What is it on the chi-square distribution curve? What determines critical value?

A specific value that acts as the threshold on the x-axis of the chi-square distribution curve

It is determined by the significance level, which is usually 0.05, and the degree of freedom, which is usually k minus 1.

What degree of freedom is used for Hardy-Weinberg problems?

1 degree of freedom

What does the significance level mean?

denoted by alpha α

It is the maximum risk you are willing to take of committing a false positive.

For example, a significance level of 5% means there is at most a 5% chance that your results claim a pattern that is actually due to chance.