Content Type:

Glossary

Share Print

Probit model Definition

A version of regression analysis, same as logit model except it uses a cumulative normal curve rather than a logistic one.

A probit model is a type of regression used in marketing research to predict the probability of a binary outcome – such as purchase vs. no purchase – based on one or more independent variables. It assumes a normal cumulative distribution for the error term.

What are key aspects of a probit model in marketing research?

• Used for modeling binary (yes/no) decisions.
• Based on the normal distribution curve.
• Estimates likelihood of an outcome based on predictors.
• Often compared to or used alongside logit models.
• Useful when decision data are not linearly related to predictors.

Why are probit models important in market research?

They allow researchers to understand and quantify the drivers behind binary consumer decisions – such as purchase intent, product adoption or brand choice – and to predict future behavior based on specific attributes or market stimuli.

Who relies on probit models in marketing research?

• Data scientists and statisticians.
• Market modelers.
• Econometricians.
• Marketing analysts.
• Product teams testing concept or trial likelihood.

How do market researchers use a probit model?

Market researchers use probit models to analyze how variables such as price, advertising exposure, demographics or feature changes affect binary decisions like whether a consumer will try a product or not. For example, in a new product test, researchers might use a probit model to estimate the probability that a respondent will purchase the item based on their stated preferences, income level and exposure to marketing materials. The model helps quantify how sensitive consumers are to specific variables and provides a predictive framework for scenario planning and campaign optimization.