R Graphical Manual

Browse All

Last data update: 2014.03.03

R: F-tests for nested models

modelCompare

R Documentation

F-tests for nested models

Description

Calculates F-test to compare two models to determine if ModelA significantly reduces SSE from ModelC. Also reports Partial eta2 and Delta R2 for this model comparison. ModelC should contain subset of ModelA regressors.

Usage

modelCompare(ModelC, ModelA)

Arguments

`ModelC`	a linear model, produced by `lm`. This compact model should include a subset of regressors from ModelA
`ModelA`	a linear model, produced by `lm`

. This augmented model should include all regressors from ModelC plus additional regressors.

Details

Calculates F test for model comparison F = ((sseC - sseA)/ (pA - pC)) / (sseA / (N-pA)) ndf = pA - pC ddf = N -P

Value

Returns a list with results for model comparison, sses, and other relevant fields

Author(s)

John J. Curtin jjcurtin@wisc.edu

Examples

mC = lm(interlocks~assets, data=Ornstein)
mA = lm(interlocks~assets+nation, data=Ornstein)
modelCompare(mC, mA)