confint.index: Confidence intervals for the multilevel index

In profrichharris/MLID: Multilevel Index of Dissimilarity

Description

Calculates the confidence intervals for the residuals of the multilevel index at each level. These can then be visualised in a caterpillar plot.

Usage

## S3 method for class 'index'
confint(object, parm, level = 0.95, ...)

Arguments

object	an object of class index: a multilevel index created using function id
parm	NA
level	the confidence level required
...	other arguments

Details

confint.index is a wrapper to lme4::ranef(mlm, condVar = TRUE) and is used to calculate the confidence intervals for the locations and regions at each of the higher levels of the model. In this way, places with an usually high (or low) share of population group Y with respect to population group X can be identified, net of the effects of other levels of the model. The width of the confidence interval is adjusted for a test of difference between two means (see Statistical Rules of Thumb by Gerald van Belle, 2011, eq 2.18). A 95 per cent confidence interval, for example, extends to 1.39 times the standard error around the mean and not 1.96.

Value

an object of class confint, a list of length equal to the number of levels in the index where each part of the list is a data frame giving the confidence interval for the location

See Also

catplot id ranef

Examples

## Not run: 
data(aggdata)
index <- id(aggdata, vars = c("Bangladeshi", "WhiteBrit"),
levels = c("MSOA","LAD","RGN"))
ci <- confint(index)
catplot(ci)

## End(Not run)

profrichharris/MLID documentation built on May 26, 2019, 8:34 a.m.