Store statistics for Ordinal Logistic Regression

Stat > Regression > Ordinal Logistic Regression > Storage

You can save statistics from your analysis to the worksheet so that you can use them in other analyses, graphs, and macros. Minitab stores the selected statistics after the last column of data. The names of the storage columns end with a number that increases as you store the same statistic multiple times.

For more details on any of these statistics, go to All statistics and graphs.

Characteristics of Estimated Equation

Coefficients: Minitab stores the estimated coefficients for the fitted model in the column COEF1.
Standard error of coefficients: Minitab stores these values in the column SECO1.
Variance/covariance matrix: Minitab stores the variance-covariance matrix in a matrix called XPWX1. To view the matrix, choose Data > Display Data. To copy the matrix to the worksheet, choose Data > Copy > Matrix to Columns.
Log-likelihood for last iteration: Minitab stores the log-likelihood value for the last iteration in a constant called LOGL1. To view the constant, choose Data > Display Data. To copy the constant to the worksheet, choose Data > Copy > Constants to Column.

Event probabilities and/or aggregated data

Number of trials

Minitab stores the number of trials for each factor–covariate pattern in the column called NTRI1.

For the remaining three storage items

Enter the number of events: Enter the number of events for the response variable. For example, if the response variable includes the levels A, B, and C, you enter 3.

Event probabilities

Minitab stores the predicted event probabilities, one column for each event in the response. These values are stores in the columns called EPRO1, EPRO2, EPRO3, and so on.

Cumulative event probabilities

Minitab stores the cumulative event probabilities, one column for each event in the response (except for the last response event). These values are stores in the columns called CUMP1, CUMP2, CUMP3, and so on.

Number of occurrences

Minitab stores the number of occurrences for each factor–covariate pattern, one column for each event in the response. These values are stores in the columns called NOCC1, NOCC2, NOCC3, and so on.