Lecture 7 - Chi square Flashcards
1
Q
When should you use a chi square test?
A
- it is a non-parametric test that measures the difference between the observed and expected frequencies of the outcomes of a set of variables
- when you have a categorical design
- when you have nominal data
2
Q
What is expected frequency?
A
frequency we would predict if belonging to each category were random
3
Q
What is observed frequency?
A
frequency that occur in the data set
4
Q
When should you use a chi squared goodness of fit test?
A
- if your research question is something like this ‘is the frequency of preference for a module in your observed data significantly different from the frequencies you would expect randomly (without preferences)?’
- if you have 1 variable and use a frequency table
- answers the question of how the observed value of a given phenomena is significantly different from the expected value
5
Q
When should you use chi squared test of association?
A
- when you have 2 variables with different categories
- if your research question is something like this ‘do students who took a level biology and students who took maths a level differ in their module preference?’
- should use a contingency table look at e.g.
- answers the question of whether or not there is a significant association between the 2 variables
6
Q
How to know if the chi squared is significant?
A
- your p value will be significant if it less than or equal to 0.05
7
Q
How to report a chi squared?
A
x² (df, N= XX) = XX.XX, p =.XXX/OR/p<.001
8
Q
What are the assumptions for chi squared?
A
- the level of measurement of all variables is nominal (sometimes ordinal)
- each participant must contribute to 1 and only 1 cell (mutually exclusive)
- the values of the cell should be frequencies or counts, not percentage
- the value of the cell expected should be 5 or more in at least 80% of the cells and no cell should have an expected of less than 1
