lavaSearch2 (version 1.4)

summary2: Summary with Small Sample Correction

Description

Summary with small sample correction.

Usage

summary2(object, ...)
# S3 method for lm
summary2(object, df = TRUE, bias.correct = TRUE, ...)
# S3 method for gls
summary2(object, df = TRUE, bias.correct = TRUE,
  cluster = NULL, ...)
# S3 method for lme
summary2(object, df = TRUE, bias.correct = TRUE, ...)
# S3 method for lvmfit
summary2(object, df = TRUE, bias.correct = TRUE, ...)
# S3 method for lm2
summary2(object, digit = max(3, getOption("digit")),
  robust = FALSE, df = TRUE, ...)
# S3 method for gls2
summary2(object, digit = max(3, getOption("digit")),
  robust = FALSE, df = TRUE, ...)
# S3 method for lme2
summary2(object, digit = max(3, getOption("digit")),
  robust = FALSE, df = TRUE, ...)
# S3 method for lvmfit2
summary2(object, cluster = NULL, robust = FALSE,
  df = TRUE, ...)

Arguments

object

a gls, lme or lvm object.

...

arguments passed to the summary method of the object.

df

[logical] should the degree of freedoms of the Wald statistic be computed using the Satterthwaite correction? Otherwise the degree of freedoms are set to Inf, i.e. a normal distribution is used instead of a Student's t distribution when computing the p-values.

bias.correct

[logical] should the standard errors of the coefficients be corrected for small sample bias? See sCorrect for more details.

cluster

[integer vector] the grouping variable relative to which the observations are iid.

digit

[integer > 0] the number of decimal places to use when displaying the summary.

robust

[logical] should the robust standard errors be used instead of the model based standard errors?

Details

summary2 is the same as summary except that it first computes the small sample correction (but does not store it). So if summary2 is to be called several times, it is more efficient to pre-compute the quantities for the small sample correction using sCorrect and then call summary2.

See Also

sCorrect for more detail about the small sample correction.

Examples

# NOT RUN {
m <- lvm(Y~X1+X2)
set.seed(10)
d <- lava::sim(m, 2e1)

## Gold standard
summary(lm(Y~X1+X2, d))$coef

## gls models
library(nlme)
e.gls <- gls(Y~X1+X2, data = d, method = "ML")
summary(e.gls)$tTable
sCorrect(e.gls, cluster = 1:NROW(d)) <- FALSE ## no small sample correction
summary2(e.gls)$tTable

sCorrect(e.gls, cluster = 1:NROW(d)) <- TRUE ## small sample correction
summary2(e.gls)$tTable

## lvm models
e.lvm <- estimate(m, data = d)
summary(e.lvm)$coef

sCorrect(e.lvm) <- FALSE ## no small sample correction
summary2(e.lvm)$coef

sCorrect(e.lvm) <- TRUE ## small sample correction
summary2(e.lvm)$coef

# }