7A - The Chi-squared test Flashcards
What can the chi-squared test be used for?
To check the results of a genetic cross.
What is the chi-squared test?
A statistical test that is used to see if the results of an experiment support a theory.
In the chi-squared test, what is the theory first used for?
To predict a result - the expected result.
What is the expected result in a chi-squared test?
The predicted result from the theory.
What is the observed result in a chi-squared test?
The actual result.
What is the actual result called in the chi-squared test?
The observed result.
What is the predicted result called in the chi-squared test?
The expected result.
In the chi-squared test, what hypothesis is made to see if the results support the theory?
Null hypothesis.
What is the null hypothesis always?
That there is no significant difference between the observed and expected results.
What can the chi-squared test be used in genetics to test theories about?
Inheritance of characteristics.
How do you carry out a chi-squared test?
First, you need to predict the results (expected results) and come up with a null hypothesis.
Then carry out the test using the formula:
Chi-squared=The sum of((O-E)2/E)
From this, to find out if there is a significant difference between yout observed and expected results you need to compare the X2 value to a critical value which corresponds to 5% (0.05) level of probability that the difference is due to chance.
If you value of chi-squared is larger than or equal to the critical value then there is a significant difference between the O and E results (something other than chance) - and the null hypothesis can be rejected.
If you value of chi-squared is smaller than to the critical value then there is no significant difference between the O and E results - and the null hypothesis can be accepted (we’ve failed to reject the null hypothesis).
When is a null hypothesis rejected?
If you value of chi-squared is larger than or equal to the critical value then there is a significant difference between the O and E results (something other than chance) - and the null hypothesis can be rejected.
When is a null hypothesis accepted?
If you value of chi-squared is smaller than to the critical value then there is no significant difference between the O and E results - and the null hypothesis can be accepted (we’ve failed to reject the null hypothesis).
What % probability do we use in the chi-squared test?
0.05 or 5%.
How do you find the correct critical value from a table?
First find the degrees of freedom for the experiment - this is the number of classes (number of phenotypes) minus 1.
Then look across the row to the column corresponding to 0.05 or 5% for the critical value.
