Bayesian serological sampling functions for one or more sub-population and known test performance

one or sub population - known test performance - posterior distribution of prevalence. source here

sample_posterior_r_mcmc_hyperR(samps, posi, ni, se, sp, gam0)

Arguments

samps	number of MCMC samples desired
posi	number of positive tests population
ni	number of total tests in population
se	known sensitivity of test
sp	known specificity of test
gam0	hyperprior variance parameter

Value

Prevalence posterior distribution

Functions

• sample_posterior_r_mcmc_hyperR: sub population - known test performance - posterior distribution of prevalence. source here

References

Larremore, D. B., Fosdick, B. K., Bubar, K. M., Zhang, S., Kissler, S. M., Metcalf, C. J. E., ... & Grad, Y. (2020). Estimating SARS-CoV-2 seroprevalence and epidemiological parameters with uncertainty from serological surveys. medRxiv. doi: https://doi.org/10.1101/2020.04.15.20067066

Examples

if (FALSE) {

library(tidyverse)
library(skimr)

sensitivity = 0.93
specificity = 0.975
positive_pop <- c(321, 123, 100, 10)
negative_pop <- c(1234, 500, 375, 30)

# __ ONE-POP ---------------------------------------------------------------

# reproduce this
# https://github.com/LarremoreLab/covid_serological_sampling/
# codebase/prevalence_onepopulation_workbook.ipynb


# input for reproducible examples

result_one <- sample_posterior_r_mcmc_hyperR(samps = 10000,
                                             posi = positive_pop[1],
                                             ni = negative_pop[1],
                                             # se = sensitivity,
                                             # sp = specificity,
                                             se = 0.977,
                                             sp = 0.986,
                                             gam0 = 150
)

# reproducible example 00
result_one %>%
  as_tibble()

result_one %>%
  skim()

result_one %>%
  as_tibble() %>%
  ggplot(aes(x = r1)) +
  geom_histogram(aes(y=..density..),binwidth = 0.005)


# __ SUB-POPS --------------------------------------------------------------


# reproduce this
# https://github.com/LarremoreLab/covid_serological_sampling/
# codebase/prevalence_subpopulations_workbook.ipynb

result_sub <- sample_posterior_r_mcmc_hyperR(samps = 10000,
                                         posi = positive_pop,
                                         ni = positive_pop+negative_pop,
                                         se = sensitivity,
                                         sp = specificity,
                                         # se = 0.977,
                                         # sp = 0.986,
                                         gam0 = 150
                                         )

# reproducible example
result_sub %>%
  as_tibble()

result_sub %>%
  skim()

result_sub %>%
  as_tibble() %>%
  rownames_to_column() %>%
  select(-gam) %>%
  pivot_longer(cols = -rowname,names_to = "estimates",values_to = "values") %>%
  ggplot(aes(x = values, color = estimates)) +
  geom_density()
}