Profile.resid: Residuals

Description

Computes the residuals for each observation (row) where items pairs are the corresponding columns in x.set and y.set.

Usage

Profile.resid(x.set, y.set, nomiss = 0.8)

Arguments

x.set

A data.frame or matrix, with the same dimensions as y.set, of which each row is a predictor of the corresponding row in y.set.

y.set

A data.frame or matrix, with the same dimensions as x.set, of which each row is to be predicted by the correpsonding row in x.set.

nomiss

A numeric between .00 and 1.00 specifying the proportion of x-y pairs required to be complete before NA is returned instead of the regression coefficients. The default of .80 means that if more than 20 percent of the x-y pairs are incomplete an NA will be returned.

Value

Returns a data.frame of the same size as x.set containing the residual values of y.set after being predicted by x.set.

Details

The residuals from predicting the values in each row of y.set from the values in the corresponding row of y.set are returned. If fewer than 'nomiss' of the x-y pairs of observations for a given row are valid (complete) then NA will be returned for all of that row's residuals.

Examples

Run this code

data(acq1)
data(caq)
	#Lets get the regression coeficients for predicting aquaintance 
	#California Adult Q-Set (CAQ) personality ratings from #self-report CAQ ratings 
Profile.reg(caq,acq1)
	#We can look at the residuals from those regressions
res.acq <- Profile.resid(acq1, caq)
head(res.acq)