surv_prevalence_by: Estimate prevalence by subgroup

In survinger: Design-Adjusted Inference for Pathogen Lineage Surveillance

Estimate prevalence by subgroup

Description

Applies surv_lineage_prevalence() within subgroups defined by a grouping variable. Analogous to survey::svyby() for stratified survey analysis.

Usage

surv_prevalence_by(
  design,
  lineage,
  by,
  time = "epiweek",
  method = "hajek",
  conf_level = 0.95
)

Arguments

design	A surv_design object.
lineage	Character. Target lineage.
by	Character. Column name to group by (e.g., "region" or "source_type").
time	Character. Time aggregation. Default "epiweek".
method	Character. Estimation method. Default "hajek".
conf_level	Numeric. Default 0.95.

Value

A tibble with columns: group, time, lineage, prevalence, se, ci_lower, ci_upper, n_obs, effective_n.

See Also

surv_lineage_prevalence(), surv_filter()

Examples

sim <- surv_simulate(n_regions = 4, n_weeks = 10, seed = 1)
d <- surv_design(sim$sequences, ~ region,
                 sim$population[c("region", "seq_rate")],
                 sim$population, source_type = "source_type")
surv_prevalence_by(d, "BA.2.86", by = "region")

survinger documentation built on April 27, 2026, 9:10 a.m.