Topic 7—A: genetics- 6. The chi-squared test Flashcards
What is the chi squared test?
- its a statistical test that’s used to see if the results of an experiment support a theory
What is the expected result?
Theory is used to predict a result
What is the observed result?
Experiment is carried out and the actual result is recorded
To see if the results support the theory what do you have to make?
A hypothesis called a null hypothesis
What is a null hypothesis?
- it’s always that there is no significant difference between the observed and expected results
- Your experimental result will usually be a bit different from what you expect but you need to know if the difference is due to chance or because your theory is wrong
Why is the x squared test then carried out?
- to compare the goodness of fit of the observed and expected results
- the outcome either supports or rejects the null hypothesis
When can you use the x squared test
- in genetics to test theories about the inheritance of characteristics
Formula of chi squared (x2)
X^2= sum of (O-E)^2\ E
O= observed result
E= expected result
How do you work put expected result?
Total number of offspring/ ratio total x predicted ratio
What results are used to work out x^2?
Observed result
- O-E is calculated for each phenotype (expected result is substrates from the observed result)
- resulting numbers are squared
- these figures are divided by the expected results
- the numbers are added together to get x^2
How do you determine whether there is a significant difference between the observed and expected results from an experiment?
- You need to compare the x^2 value to a critical value
- the critical value is the value of x^2 that corresponds to a 0.05 (5%) level of probability that the difference between the observed and expected results is due to chance
How is the degree of freedom worked out?
Number of phenotypes - 1
If your x^2 value is larger than (or equal to) the critical value what does this mean?
There is a significant difference between the observed and expected results i.e. something other than chance is causing the difference
- null hypothesis can be rejected
If your x^ value is smaller than the critical value what does this mean?
- there is no significant difference between the observed and expected results
- Null hypothesis can’t be rejected