How to Select the Regression Type

Regression models the relationship between a dependent variable and one or more independent variables. There are many different types of Regression models. Displayr allows its users to select between seven types of Regression models. Additionally, any of these models can be run in a stepwise mode.

The type of regression depends on the type and number of outcomes the model is aiming to predict.

Requirements

An Outcome variable. When using stacked data, the Outcome variable should be a single question in a Multi type structure.
Predictors. Variables will be considered as predictors of the outcome variable. When using stacked data, the Predictor(s) need to be a single question in a Grid type structure.

Method

The type of Regression type required will depend on the outcome variable used in your Regression model. To find the Outcome variable select the output and go to Data > Linear Regression > Outcome.
OPTIONAL: To view all potential outcomes of the dependent variable go to the Data Sources tree, select the Outcome variable, and go to the object inspector > Data > Properties > Data Values > Values. Alternatively, you can drag and drop the variable onto the Page to create a table containing all outcomes.

Go to Data > Regression Type and select the appropriate model depending on the number of categories of the Outcome variable.

Outcome variable	Example	Regression Type
Two categories	1. Yes / Selected 2. No / Not selected	Binary Logit
Three to 11 ordered categories	1. Hate 2. Dislike 3. Acceptable 4. Like 5. Love	Ordered logit
Three to 11 unordered categories	1. Africa 2. Australia 3. Asia 4. America 5. Europe	Multinomial Logit Regression
12 or more ordered categories	How would you rate your happiness on a scale of 0 to 100	Linear regression
Net Promoter Score (NPS)	-100: Detractor 0: Passive/Neutral 100: Promoter	Linear regression
Purchase or usage quantities	Number of cans of Coke consumed per week	NBD (or, if you get a weird message, quasi-Poisson Regression)
Count data with the assumption that the dependent variable has a Poisson distribution	The number of births per hour during a given day	Poisson Regression
Count data with overdispersed distribution	Overdispersion occurs when the observed variance is higher than the variance of a theoretical model	Quasi-Poisson Regression