Analysing categorical variables Flashcards
What is the name given for categorical data that can be split into 2 or more categories?
Binary // Dichotomous
What is the name of the data called if there is no obvious order for categories?
Nominal
What is the name of the data called if there is an obvious order for categories?
Ordinal
What is cross - tabulation?
This is when categorical data is compared between groups using the basis of multiple variables.
What is another name for cross - tabulation?
Contingency table
What is a pivot table?
This is an excel tool which allows you to summarise data early and thus, create a report.
DOESN’T CHANGE THE DATA.
What is a two - way contingency table?
This is a grouping variable // exposure categories which are placed in rows and outcome categories are placed in columns.
What does the chi - squared test compare?
The chi - squared test compares the observed value to the expected value.
When can the chi - squared test be used?
- Data is frequencies // counts
- Study groups are INDEPENDENT
- Value of cell expected should be > 5 > 80% cells and NOT zero.
What happens to the chi squared value when there is a BIGGER difference between O and E?
Bigger the chi - squared value.
What does the p - value depend on?
Degrees of freedom.
What is the degrees of freedom?
The number of values in the final calculation of a statistic which are free to vary.
What is the degrees of freedom for continuous variables?
Sample Size - 1
What is the degrees of freedom for categorical variables?
(r-1) X (c-1)
Why can’t a null hypothesis be rejected?
The null hypothesis CAN’T be rejected because the variables are independent.
