Assess Linear Model Assumptions

Share:

Description

Provides diagnositic graphs and score tests to evaluate linear model assumptions of normality, constant variance and linearity. Follows best practices and uses many functions from car package.

Usage

1
modelAssumptions(Model, Type = "NORMAL", ID=row.names(Model$model), one.page = TRUE)

Arguments

Model

a linear model produced by lm.

Type

Type =c('NORMAL', 'CONSTANT', 'LINEAR') for normally distributed residuals with constant variance, and linear (e.g., mean of residuals 0 for all Y')

ID

Use to identify points. Default = row.names(model$model). NULL = no identification

one.page

logical; display all graphs on one page if TRUE (Default).

Author(s)

John J. Curtin jjcurtin@wisc.edu

References

Fox, J. (1991). Regression diagnostics. SAGE Series (79) Quantitative Applictions in the Social Science.

Examples

1
2
3
4
m = lm(interlocks~assets+nation, data=car::Ornstein)
modelAssumptions(m,'NORMAL')
modelAssumptions(m,'CONSTANT')
modelAssumptions(m,'LINEAR', ID=NULL)

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.