This article discusses the eight plots in the DiagnosticsPanel plot, which is produced by several SAS regression procedures. For an ill-fitting model, the diagnostic plots should indicate the lack of fit. This article shows how to interpret diagnostic plots for a model that does not fit the data. Some procedures (most notably PROC REG and PROC LOGISTIC) support dozens of graphs that help you to evaluate the fit of the model, to determine whether the data satisfy various assumptions, and to identify outliers and high-leverage points.ĭiagnostic plots are most useful when the size of the data is not too large, such as less than 5,000 observations. Most SAS regression procedures support the PLOTS= option, which you can use to generate a panel of diagnostic plots. SAS, like most statistical software, makes it easy to generate regression diagnostics plots. When you fit a regression model, it is useful to check diagnostic plots to assess the quality of the fit.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |