simulate_ss: Simulate Silver-Standard Data
In oslerinhealth-releases/baker: Bayesian Analysis Kit for Etiology Research

Description Usage Arguments Value See Also

simulate SS measurements:

1	simulate_ss(set_parameter, latent_samples)

set_parameter

True model parameters in a npLCM specification. It is a list comprised of the following elements:

cause_list a vector of disease classes names among cases (since the causes could be multi-pathogen, so its length could be longer than the total number of unique pathogens)
etiology a vector of proportions that sum to one
pathogen_BrS a vector of pathogen names measured in bronze-standard data. This current function only simulates one slice defined by specimentestpathogen
pathogen_SS a vector of pathogen names measured in silver-standard data.
meas_nm a list of specimentest names e.g., list(MBS = c("NPPCR"),MSS="BCX") for nasalpharyngeal specimen tested by polymerase chain reaction and blood tested by culture (Cx)
Lambda subclass weights ν_1, ν_2, …, ν_K among controls; a vector of K probabilities that sum to 1.
Eta a matrix of dimension length(cause_list) by K; each row are subclass weights η_1, η_2, …, η_K for each disease class, so needs to sum to one. In Wu et al 2016, the subclass weights are the same across disease classes across rows. But when simulating data, one can specify rows with distinct probabilities - it is a matter whether we can recover these parameters (possible when we randomly observe some cases' true disease classes)
PsiBS/PsiSS False positive rates Ψ for Bronze-Standard data and for Silver-Standard data. Dimension is J by K. PsiSS is supposed to be 0 vector (by perfect specificity in silver-standard measures).
ThetaBS/ThetaSS true positive rates Θ for Bronze-Standard data and for Silver-Standard data. Dimension is J by K (can contain NA if the total number of pathogens is more than the measured pathogens in SS).
Nu the number of controls
Nd the number of cases