groceryheist/ml_measurement_error_public
1
0
Fork 0
Code Activity

update real data examples code and rerun project.

Browse Source
This commit is contained in:
Nathan TeBlunthuis
2023-01-11 10:59:50 -08:00
parent c066f900d3
commit c45ea9dfeb
7 changed files with 306 additions and 170 deletions
Download Patch File Download Diff File Expand all files Collapse all files

98
simulations/measerr_methods.R
View File

@@ -15,7 +15,12 @@ library(bbmle)
### ideal formulas for example 2
# test.fit.2 <- measerr_mle(df, y ~ x + z, gaussian(), w_pred ~ x + z + y + y:x, binomial(link='logit'), x ~ z)
likelihood.logistic <- function(model.params, outcome, model.matrix){
ll <- vector(mode='numeric', length=length(outcome))
ll[outcome == 1] <- plogis(model.params %*% t(model.matrix[outcome==1,]), log=TRUE)
ll[outcome == 0] <- plogis(model.params %*% t(model.matrix[outcome==0,]), log=TRUE, lower.tail=FALSE)
return(ll)
}
## outcome_formula <- y ~ x + z; proxy_formula <- w_pred ~ y + x + z + x:z + x:y + z:y
measerr_mle_dv <- function(df, outcome_formula, outcome_family=binomial(link='logit'), proxy_formula, proxy_family=binomial(link='logit'),method='optim'){
@@ -126,6 +131,31 @@ measerr_mle <- function(df, outcome_formula, outcome_family=gaussian(), proxy_fo
proxy.model.matrix <- model.matrix(proxy_formula, df)
y.obs <- with(df.obs,eval(parse(text=response.var)))
df.proxy.obs <- model.frame(proxy_formula,df)
proxy.obs <- with(df.proxy.obs, eval(parse(text=proxy.variable)))
n.proxy.model.covars <- dim(proxy.model.matrix)[2]
df.truth.obs <- model.frame(truth_formula, df)
truth.obs <- with(df.truth.obs, eval(parse(text=truth.variable)))
truth.model.matrix <- model.matrix(truth_formula,df.truth.obs)
n.truth.model.covars <- dim(truth.model.matrix)[2]
df.unobs <- df[is.na(eval(parse(text=truth.variable)))]
df.unobs.x1 <- copy(df.unobs)
df.unobs.x1[,truth.variable] <- 1
df.unobs.x0 <- copy(df.unobs)
df.unobs.x0[,truth.variable] <- 0
outcome.unobs <- with(df.unobs, eval(parse(text=response.var)))
outcome.model.matrix.x0 <- model.matrix(outcome_formula, df.unobs.x0)
outcome.model.matrix.x1 <- model.matrix(outcome_formula, df.unobs.x1)
proxy.model.matrix.x0 <- model.matrix(proxy_formula, df.unobs.x0)
proxy.model.matrix.x1 <- model.matrix(proxy_formula, df.unobs.x1)
proxy.unobs <- df.unobs[[proxy.variable]]
truth.model.matrix.unobs <- model.matrix(truth_formula, df.unobs.x0)
measerr_mle_nll <- function(params){
param.idx <- 1
n.outcome.model.covars <- dim(outcome.model.matrix)[2]
@@ -138,82 +168,48 @@ measerr_mle <- function(df, outcome_formula, outcome_family=gaussian(), proxy_fo
param.idx <- param.idx + 1
# outcome_formula likelihood using linear regression
ll.y.obs <- dnorm(y.obs, outcome.params %*% t(outcome.model.matrix),sd=sigma.y, log=TRUE)
}
df.obs <- model.frame(proxy_formula,df)
n.proxy.model.covars <- dim(proxy.model.matrix)[2]
} else if( (outcome_family$family == "binomial") & (outcome_family$link == "logit") )
ll.y.obs <- likelihood.logistic(outcome.params, y.obs, outcome.model.matrix)
proxy.params <- params[param.idx:(n.proxy.model.covars+param.idx-1)]
param.idx <- param.idx + n.proxy.model.covars
proxy.obs <- with(df.obs, eval(parse(text=proxy.variable)))
if( (proxy_family$family=="binomial") & (proxy_family$link=='logit')){
ll.w.obs <- vector(mode='numeric',length=dim(proxy.model.matrix)[1])
if( (proxy_family$family=="binomial") & (proxy_family$link=='logit'))
ll.w.obs <- likelihood.logistic(proxy.params, proxy.obs, proxy.model.matrix)
# proxy_formula likelihood using logistic regression
ll.w.obs[proxy.obs==1] <- plogis(proxy.params %*% t(proxy.model.matrix[proxy.obs==1,]),log=TRUE)
ll.w.obs[proxy.obs==0] <- plogis(proxy.params %*% t(proxy.model.matrix[proxy.obs==0,]),log=TRUE, lower.tail=FALSE)
}
df.obs <- model.frame(truth_formula, df)
truth.obs <- with(df.obs, eval(parse(text=truth.variable)))
truth.model.matrix <- model.matrix(truth_formula,df)
n.truth.model.covars <- dim(truth.model.matrix)[2]
truth.params <- params[param.idx:(n.truth.model.covars + param.idx - 1)]
if( (truth_family$family=="binomial") & (truth_family$link=='logit')){
ll.x.obs <- vector(mode='numeric',length=dim(truth.model.matrix)[1])
# truth_formula likelihood using logistic regression
ll.x.obs[truth.obs==1] <- plogis(truth.params %*% t(truth.model.matrix[truth.obs==1,]),log=TRUE)
ll.x.obs[truth.obs==0] <- plogis(truth.params %*% t(truth.model.matrix[truth.obs==0,]),log=TRUE, lower.tail=FALSE)
}
if( (truth_family$family=="binomial") & (truth_family$link=='logit'))
ll.x.obs <- likelihood.logistic(truth.params, truth.obs, truth.model.matrix)
# add the three likelihoods
# add the three likelihoods
ll.obs <- sum(ll.y.obs + ll.w.obs + ll.x.obs)
## likelihood for the predicted data
## integrate out the "truth" variable.
if(truth_family$family=='binomial'){
df.unobs <- df[is.na(eval(parse(text=truth.variable)))]
df.unobs.x1 <- copy(df.unobs)
df.unobs.x1[,'x'] <- 1
df.unobs.x0 <- copy(df.unobs)
df.unobs.x0[,'x'] <- 0
outcome.unobs <- with(df.unobs, eval(parse(text=response.var)))
outcome.model.matrix.x0 <- model.matrix(outcome_formula, df.unobs.x0)
outcome.model.matrix.x1 <- model.matrix(outcome_formula, df.unobs.x1)
if(outcome_family$family=="gaussian"){
# likelihood of outcome
ll.y.x0 <- dnorm(outcome.unobs, outcome.params %*% t(outcome.model.matrix.x0), sd=sigma.y, log=TRUE)
ll.y.x1 <- dnorm(outcome.unobs, outcome.params %*% t(outcome.model.matrix.x1), sd=sigma.y, log=TRUE)
} else if( (outcome_family$family == "binomial") & (outcome_family$link == "logit") ){
ll.y.x1 <- likelihood.logistic(outcome.params, outcome.unobs, outcome.model.matrix.x1)
ll.y.x0 <- likelihood.logistic(outcome.params, outcome.unobs, outcome.model.matrix.x0)
}
if( (proxy_family$family=='binomial') & (proxy_family$link=='logit')){
proxy.model.matrix.x0 <- model.matrix(proxy_formula, df.unobs.x0)
proxy.model.matrix.x1 <- model.matrix(proxy_formula, df.unobs.x1)
proxy.unobs <- df.unobs[[proxy.variable]]
ll.w.x0 <- vector(mode='numeric', length=dim(df.unobs)[1])
ll.w.x1 <- vector(mode='numeric', length=dim(df.unobs)[1])
ll.w.x0 <- likelihood.logistic(proxy.params, proxy.unobs, proxy.model.matrix.x0)
ll.w.x1 <- likelihood.logistic(proxy.params, proxy.unobs, proxy.model.matrix.x1)
# likelihood of proxy
ll.w.x0[proxy.unobs==1] <- plogis(proxy.params %*% t(proxy.model.matrix.x0[proxy.unobs==1,]), log=TRUE)
ll.w.x1[proxy.unobs==1] <- plogis(proxy.params %*% t(proxy.model.matrix.x1[proxy.unobs==1,]), log=TRUE)
ll.w.x0[proxy.unobs==0] <- plogis(proxy.params %*% t(proxy.model.matrix.x0[proxy.unobs==0,]), log=TRUE,lower.tail=FALSE)
ll.w.x1[proxy.unobs==0] <- plogis(proxy.params %*% t(proxy.model.matrix.x1[proxy.unobs==0,]), log=TRUE,lower.tail=FALSE)
}
if(truth_family$link=='logit'){
truth.model.matrix <- model.matrix(truth_formula, df.unobs.x0)
# likelihood of truth
ll.x.x1 <- plogis(truth.params %*% t(truth.model.matrix), log=TRUE)
ll.x.x0 <- plogis(truth.params %*% t(truth.model.matrix), log=TRUE, lower.tail=FALSE)
ll.x.x1 <- plogis(truth.params %*% t(truth.model.matrix.unobs), log=TRUE)
ll.x.x0 <- plogis(truth.params %*% t(truth.model.matrix.unobs), log=TRUE, lower.tail=FALSE)
}
}

2
simulations/run_job.sbatch
View File

@@ -2,7 +2,7 @@
#SBATCH --job-name="simulate measurement error models"
## Allocation Definition
#SBATCH --account=comdata
#SBATCH --partition=compute-bigmem,compute-hugemem
#SBATCH --partition=compute-bigmem
## Resources
#SBATCH --nodes=1
## Walltime (4 hours)