RDS: bootstrap.incidence – R documentation

Pricing

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

Get Started for Free

Documentation

RDS

bootstrap.incidence

Calculates incidence and bootstrap confidence intervals for immunoassay data collected with RDS

Description

Calculates incidence and bootstrap confidence intervals for immunoassay data collected with RDS

Usage

bootstrap.incidence(
  rds.data,
  recent.variable,
  hiv.variable,
  N = NULL,
  weight.type = c("Gile's SS", "RDS-I", "RDS-I (DS)", "RDS-II", "Arithmetic Mean",
    "HCG"),
  mean.duration = 200,
  frr = 0.01,
  post.infection.cutoff = 730,
  number.of.bootstrap.samples = 1000,
  se.mean.duration = 0,
  se.frr = 0,
  confidence.level = 0.95,
  verbose = TRUE,
  ...
)

Arguments

`rds.data`	an rds.data.frame
`recent.variable`	The name of the variable indicating recent infection
`hiv.variable`	The name of the variable indicating of hiv infection
`N`	Population size
`weight.type`	A string giving the type of estimator to use. The options are `"Gile's SS"`, `"RDS-I"`, `"RDS-II"`, `"RDS-I/DS"`, and `"Arithemic Mean"`. It defaults to `"Gile's SS"`.
`mean.duration`	Estimated mean duration of recent infection (MDRI) (days)
`frr`	Estimated false-recent rate (FRR)
`post.infection.cutoff`	Post-infection time cut-off T, separating "true-recent" from "false-recent" results (days)
`number.of.bootstrap.samples`	The number of bootstrap samples used to construct the interval.
`se.mean.duration`	The standard error of the mean.duration estimate
`se.frr`	The standard error of the false recency estimate
`confidence.level`	The level of confidence for the interval
`verbose`	verbosity control
`...`	additional arguments to compute.weights

Details

The recent.variable and hiv should be the names of logical variables. Otherwise they are converted to logical using as.numeric(x) > 0.5.

This function estimates incidence using RDS sampling wieghts. Confidence intervals are constucted using HCG bootstraps. See http://www.incidence-estimation.org/ for additional information on (non-RDS) incidence estimation.

Examples

data(faux)
faux$hiv <- faux$X == "blue"
faux$recent <- NA
faux$recent[faux$hiv] <- runif(sum(faux$hiv)) < .2
faux$recent[runif(nrow(faux)) > .5] <- NA
faux$hiv[is.na(faux$recent)][c(1,6,10,21)] <- NA
attr(faux,"time") <- "wave"
bootstrap.incidence(faux,"recent","hiv",weight.type="RDS-II", number.of.bootstrap.samples=100)

RDS

Respondent-Driven Sampling

v0.9-3

LGPL-2.1

Authors

Mark S. Handcock [aut, cre], Krista J. Gile [aut], Ian E. Fellows [aut], W. Whipple Neely [aut]

Initial release

2021-03-11