LinearizationVar_StRS: Calculate linearization variance of trend for stratified...

In LAStarcevich/TrendNPS: NPS Trend Analyses for Complex Survey Designs

Description

Calculate the linearization variance of the trend coefficient with a Taylor series approximation when two-level stratification is used and a separate-slopes trend model is applied. This is an internal function called from PWIGLS_ALL.

Usage

LinearizationVar_StRS(Site, wij, xij, eij, varYij, str1prop)

Arguments

Site	vector of Site names.
wij	vector of inclusion weights = Site-level design weight * Year-level panel weight.
xij	vector of shifted year variables (WYear) for trend estimation.
eij	vector of residuals from PWIGLS trend model.
varYij	vector of total variance estimates for yij, estimated from PWIGLS variance components estimates.
str1prop	Proportion of the population represented by the first level of the stratication variable.

Details

The linearization variance is based on a Taylor series approximation. See Skinner (1989, p. 82-83) for more information.

Value

Scalar variance estimate of the trend regression coefficient.

Author(s)

Leigh Ann Starcevich of Western EcoSystems Technology, Inc.

References

Skinner, C. J., D. Holt, and T. M. F. Smith. 1989. Analysis of Complex Surveys. New York: Wiley.

See Also

TrendNPS_Cont, LinearizationVar

Examples

## Not run: 
#  ---- Read example data set.
TrendVar = LinearizationVar_StRS(Site,wij,xij,eij,varYij,str1prop)

## End(Not run)

LAStarcevich/TrendNPS documentation built on May 21, 2019, 9:19 a.m.