What is a contingency table used for?
To display frequencies for combinations of two variables categorised into groups
Define the chi-squared distribution.
A special case of the gamma distribution used in inferential statistics
It tests for various associations, including independence and goodness of fit.
What does degrees of freedom refer to?
The number of independent pieces of information used to calculate a statistic
It affects the shape of the chi-squared distribution.
What is the formula for the degrees of freedom for a contingency table?
v=(rows-1)x(columns-1)
What are expected frequencies?
Theoretical frequencies expected if two variables are independent
They are compared to observed frequencies in contingency tables.
The formula for calculating expected frequency in a contingency table is based on what?
What is the test statistic in the context of contingency tables?
True or false: The null hypothesis in contingency tables assumes that the two variables are dependent.
FALSE
The null hypothesis assumes that the variables are independent.
What should be done if the value of any expected frequency is less than 5?
Combine groups until all expected values are reasonably large
A group should be combine with the most similar other group(s) in the context of the question
What does the contribution of each cell in a contingency table represent?
The value that it contributes to the total of the test statistic
When are you expected to use the contributions for each cell?
When commenting on the nature of any association, the contirbutions must be referenced
The largest contributions need to be commented on
What is the purpose of combining classes in contingency tables?
To increase expected values when they are too small
This allows for valid statistical analysis.
What is the critical region in hypothesis testing?
The area in the tail(s) of the distribution where the null hypothesis can be rejected
It is determined by the significance level.
What is the grand total in a contingency table?
The total number of observations across all categories
It is used to calculate expected frequencies.
What type of variables are typically analysed using contingency tables?
Qualitative random variables
Catagorical Data
In the context of an investigation, what does a χ2 test help to determine?
Independence of categorical variables
Specifically, it assesses whether the distribution of one categorical variable differs from another.
What are the degrees of freedom on a 21x13 contingency table with no combining?
v=(21-1)x(13-1)=240
What is the null hypothesis for ALL contingency table hypothesis tests?
H0: There is no association between…
What is the alternative hypothesis for ALL contingency table hypothesis tests?
H1: There is an association between…
When is it appropriate to perform a Chi-Squared contingency table test?
When testing catagorical data for an association
What assumptions are made when carrying out the Chi-squared test?