Which regression and correlation analyses are included in Minitab?

Minitab offers several regression analyses to investigate and model the relationship between a response variable and one or more predictor variables.

In This Topic

Basic measures of association
Regression analyses for continuous response variables
Regression analyses for discrete response variables

Basic measures of association

Correlation: Use to calculate Pearson's correlation or Spearman rank-order correlation (also called Spearman's rho). In Minitab, choose Stat > Basic Statistics > Correlation.
Covariance: Use to calculate the covariance, a measure of the relationship between two variables. The covariance is not standardized, unlike the correlation coefficient. In Minitab, choose Stat > Basic Statistics > Covariance.

Regression analyses for continuous response variables

Use the following analyses when you have a continuous response variable.

Regression: Model the relationship between categorical or continuous predictors and one response, and use the model to predict response values for new observations. Easily include interaction and polynomial terms, transform the response, or use stepwise regression if needed. In Minitab, choose Stat > Regression > Regression > Fit Regression Model.
Best subsets: Compare all possible models using a specified set of predictors, and display the best fitting models that contain one predictor, two predictors, and so on. In Minitab, choose Stat > Regression > Regression > Best Subsets.
Fitted line plot: Plot the relationship between one predictor and one response. In Minitab, choose Stat > Regression > Fitted Line Plot.
Nonlinear regression: Model the relationship between predictors and a response when quadratic or cubic terms are not adequate. Use when you can specify a nonlinear relationship, such as nonlinear growth or decay, to describe the relationship. In Minitab, choose Stat > Regression > Nonlinear Regression.
Stability study: Plan a stability study and create a custom worksheet for data collection. In Minitab, choose Stat > Regression > Stability Study > Create Stability Study Worksheet.; Estimate the shelf life of a drug product with a linear model. In Minitab, choose Stat > Regression > Stability Study.
Orthogonal regression: Model the relationship between one response and one predictor when the measurements of both the response and the predictor include random error. In Minitab, choose Stat > Regression > Orthogonal Regression.
Partial least squares: Determine whether a set of predictors are related to the responses. Use when you have predictors that are highly collinear or when you have more predictors than observations. In Minitab, choose Stat > Regression > Partial Least Squares.

Regression analyses for discrete response variables

Use the following analyses when you have a discrete response variable.

Binary logistic regression: Model the relationship between predictors and a response that has two outcomes, such as pass or fail. In Minitab, choose Stat > Regression > Binary Logistic Regression > Fit Binary Logistic Model.
Binary fitted line plot: Plot fitted binary logistic regression fit lines with confidence intervals. In Minitab, choose Stat > Regression > Binary Fitted Line Plot.
Ordinal logistic regression: Model the relationship between predictors and a response that has three or more outcomes that have an order, such as low, medium, and high. In Minitab, choose Stat > Regression > Ordinal Logistic Regression.
Nominal logistic regression: Model the relationship between predictors and a response that has three or more outcomes that do not have an order, such as scratch, dent, and tear. In Minitab, choose Stat > Regression > Nominal Logistic Regression.
Poisson regression: Model the relationship between predictors and a response that counts events, such as the number of soldering defects on a circuit board. You can also use stepwise regression to help determine a model. In Minitab, choose Stat > Regression > Poisson Regression > Fit Poisson Model.