prev: Estimated overall prevalence from sample selection model

Description

prev can be used to calculate the overall estimated prevalence from a sample selection model, with corresponding interval obtained using the delta method or posterior simulation.

Usage

prev(x, sw = NULL, naive = FALSE, ind = NULL, delta = FALSE,  
         n.sim = 100, prob.lev = 0.05, hd.plot = FALSE, 
         main = "Histogram and Kernel Density of Simulated Prevalences", 
         xlab="Simulated Prevalences", ...)

Arguments

A fitted SemiParBIVProbit object as produced by SemiParBIVProbit().

Survey weights.

naive

If FALSE then the prevalence is calculated using the (naive/classic imputation) probit model. This option has been introduced to compare adjusted (for non-random sample selection) and unadjusted estimates.

ind

Binary logical variable. It can be used to calculate the prevalence for a subset of the data.

delta

If TRUE then the delta method is used for confidence interval calculations, otherwise Bayesian posterior simulation is employed.

n.sim

Number of simulated coefficient vectors from the posterior distribution of the estimated model parameters. This is used when delta = FALSE. It may be increased if more precision is required.

prob.lev

Overall probability of the left and right tails of the prevalence distribution used for interval calculations.

hd.plot

If TRUE then a plot of the histogram and kernel density estimate of the simulated prevalences is produced. This can only be produced when delta = FALSE.

main

Title for the plot.

xlab

Title for the x axis.

...

Other graphics parameters to pass on to plotting commands. These are used only when hd.plot = TRUE.

Value

resIt returns three values: lower confidence interval limit, estimated prevalence and upper confidence interval limit.
prob.levProbability level used.
sim.prevIf delta = FALSE then it returns a vector containing simulated values of the prevalence. This is used to calculate an interval.

Details

prev estimates the overall prevalence of a disease (e.g., HIV) when there are missing values that are not at random. An interval for the estimated prevalence can be obtained using the delta method or posterior simulation. The two methods produce close intervals in most cases (this may be attributed to the shape of the probit link).

References

McGovern M.E., Barnighausen T., Marra G. and Radice R. (2015), On the Assumption of Joint Normality in Selection Models: A Copula Approach Applied to Estimating HIV Prevalence. Epidemiology, 26(2), 229-237.

Examples

Run this code

## see examples for SemiParBIVProbit

Run the code above in your browser using DataLab