X-Git-Url: https://code.communitydata.science/ml_measurement_error_public.git/blobdiff_plain/979dc14b6861ae31f00d56392fd5b8cf69f17333..b8d2048cc5338fbd872b55029c3e5d01c739a397:/simulations/irr_simulation_base.R diff --git a/simulations/irr_simulation_base.R b/simulations/irr_simulation_base.R index ebb215b..f16c96b 100644 --- a/simulations/irr_simulation_base.R +++ b/simulations/irr_simulation_base.R @@ -3,10 +3,10 @@ library(matrixStats) # for numerically stable logsumexps options(amelia.parallel="no", amelia.ncpus=1) library(Amelia) +source("measerr_methods.R") +source("pl_methods.R") -source("measerr_methods.R") ## for my more generic function. - -run_simulation <- function(df, result, outcome_formula = y ~ x + z, proxy_formula = w_pred ~ x, truth_formula = x ~ z){ +run_simulation <- function(df, result, outcome_formula = y ~ x + z, proxy_formula = w_pred ~ x, coder_formulas=list(x.obs.1~x, x.obs.0~x), truth_formula = x ~ z){ accuracy <- df[,mean(w_pred==x)] result <- append(result, list(accuracy=accuracy)) @@ -24,6 +24,8 @@ run_simulation <- function(df, result, outcome_formula = y ~ x + z, proxy_formul + + loa0.feasible <- lm(y ~ x.obs.0 + z, data = df[!(is.na(x.obs.1))]) loa0.ci.Bxy <- confint(loa0.feasible)['x.obs.0',] @@ -35,7 +37,7 @@ run_simulation <- function(df, result, outcome_formula = y ~ x + z, proxy_formul Bxy.ci.lower.loa0.feasible = loa0.ci.Bxy[1], Bzy.ci.upper.loa0.feasible = loa0.ci.Bzy[2], Bzy.ci.lower.loa0.feasible = loa0.ci.Bzy[1])) - + print("fitting loa0 model") df.loa0.mle <- copy(df) df.loa0.mle[,x:=x.obs.0] @@ -52,8 +54,11 @@ run_simulation <- function(df, result, outcome_formula = y ~ x + z, proxy_formul Bzy.ci.upper.loa0.mle = ci.upper['z'], Bzy.ci.lower.loa0.mle = ci.upper['z'])) + + loco.feasible <- lm(y ~ x.obs.1 + z, data = df[(!is.na(x.obs.1)) & (x.obs.1 == x.obs.0)]) + loco.feasible.ci.Bxy <- confint(loco.feasible)['x.obs.1',] loco.feasible.ci.Bzy <- confint(loco.feasible)['z',] @@ -65,41 +70,152 @@ run_simulation <- function(df, result, outcome_formula = y ~ x + z, proxy_formul Bzy.ci.lower.loco.feasible = loco.feasible.ci.Bzy[1])) + (model.naive <- lm(y~w_pred+z, data=df)) + + naive.ci.Bxy <- confint(model.naive)['w_pred',] + naive.ci.Bzy <- confint(model.naive)['z',] + + result <- append(result, list(Bxy.est.naive=coef(model.naive)['w_pred'], + Bzy.est.naive=coef(model.naive)['z'], + Bxy.ci.upper.naive = naive.ci.Bxy[2], + Bxy.ci.lower.naive = naive.ci.Bxy[1], + Bzy.ci.upper.naive = naive.ci.Bzy[2], + Bzy.ci.lower.naive = naive.ci.Bzy[1])) + + print("fitting loco model") + df.loco.mle <- copy(df) df.loco.mle[,x.obs:=NA] df.loco.mle[(x.obs.0)==(x.obs.1),x.obs:=x.obs.0] df.loco.mle[,x.true:=x] df.loco.mle[,x:=x.obs] print(df.loco.mle[!is.na(x.obs.1),mean(x.true==x,na.rm=TRUE)]) + loco.accuracy <- df.loco.mle[(!is.na(x.obs.1)) & (x.obs.1 == x.obs.0),mean(x.obs.1 == x.true)] loco.mle <- measerr_mle(df.loco.mle, outcome_formula=outcome_formula, proxy_formula=proxy_formula, truth_formula=truth_formula) fisher.info <- solve(loco.mle$hessian) coef <- loco.mle$par ci.upper <- coef + sqrt(diag(fisher.info)) * 1.96 ci.lower <- coef - sqrt(diag(fisher.info)) * 1.96 - result <- append(result, list(Bxy.est.loco.mle=coef['x'], + result <- append(result, list(loco.accuracy=loco.accuracy, + Bxy.est.loco.mle=coef['x'], Bzy.est.loco.mle=coef['z'], Bxy.ci.upper.loco.mle = ci.upper['x'], Bxy.ci.lower.loco.mle = ci.lower['x'], Bzy.ci.upper.loco.mle = ci.upper['z'], - Bzy.ci.lower.loco.mle = ci.upper['z'])) + Bzy.ci.lower.loco.mle = ci.lower['z'])) + + df.double.proxy.mle <- copy(df) + df.double.proxy.mle[,x.obs:=NA] + print("fitting double proxy model") + + double.proxy.mle <- measerr_irr_mle(df.double.proxy.mle, outcome_formula=outcome_formula, proxy_formula=proxy_formula, coder_formulas=coder_formulas[1], truth_formula=truth_formula) + fisher.info <- solve(double.proxy.mle$hessian) + coef <- double.proxy.mle$par + ci.upper <- coef + sqrt(diag(fisher.info)) * 1.96 + ci.lower <- coef - sqrt(diag(fisher.info)) * 1.96 + + result <- append(result, list( + Bxy.est.double.proxy=coef['x'], + Bzy.est.double.proxy=coef['z'], + Bxy.ci.upper.double.proxy = ci.upper['x'], + Bxy.ci.lower.double.proxy = ci.lower['x'], + Bzy.ci.upper.double.proxy = ci.upper['z'], + Bzy.ci.lower.double.proxy = ci.lower['z'])) + + df.triple.proxy.mle <- copy(df) + df.triple.proxy.mle[,x.obs:=NA] + + print("fitting triple proxy model") + triple.proxy.mle <- measerr_irr_mle(df.triple.proxy.mle, outcome_formula=outcome_formula, proxy_formula=proxy_formula, coder_formulas=coder_formulas, truth_formula=truth_formula) + fisher.info <- solve(triple.proxy.mle$hessian) + coef <- triple.proxy.mle$par + ci.upper <- coef + sqrt(diag(fisher.info)) * 1.96 + ci.lower <- coef - sqrt(diag(fisher.info)) * 1.96 + + result <- append(result, list( + Bxy.est.triple.proxy=coef['x'], + Bzy.est.triple.proxy=coef['z'], + Bxy.ci.upper.triple.proxy = ci.upper['x'], + Bxy.ci.lower.triple.proxy = ci.lower['x'], + Bzy.ci.upper.triple.proxy = ci.upper['z'], + Bzy.ci.lower.triple.proxy = ci.lower['z'])) + tryCatch({ + amelia.out.k <- amelia(df.loco.mle, m=200, p2s=0, idvars=c('x.true','w','x.obs.1','x.obs.0','x')) + mod.amelia.k <- zelig(y~x.obs+z, model='ls', data=amelia.out.k$imputations, cite=FALSE) + (coefse <- combine_coef_se(mod.amelia.k, messages=FALSE)) + + est.x.mi <- coefse['x.obs','Estimate'] + est.x.se <- coefse['x.obs','Std.Error'] + result <- append(result, + list(Bxy.est.amelia.full = est.x.mi, + Bxy.ci.upper.amelia.full = est.x.mi + 1.96 * est.x.se, + Bxy.ci.lower.amelia.full = est.x.mi - 1.96 * est.x.se + )) + + est.z.mi <- coefse['z','Estimate'] + est.z.se <- coefse['z','Std.Error'] + + result <- append(result, + list(Bzy.est.amelia.full = est.z.mi, + Bzy.ci.upper.amelia.full = est.z.mi + 1.96 * est.z.se, + Bzy.ci.lower.amelia.full = est.z.mi - 1.96 * est.z.se + )) + + }, + error = function(e){ + message("An error occurred:\n",e) + result$error <-paste0(result$error,'\n', e) + } + ) + + tryCatch({ + + mod.zhang.lik <- zhang.mle.iv(df.loco.mle) + coef <- coef(mod.zhang.lik) + ci <- confint(mod.zhang.lik,method='quad') + result <- append(result, + list(Bxy.est.zhang = coef['Bxy'], + Bxy.ci.upper.zhang = ci['Bxy','97.5 %'], + Bxy.ci.lower.zhang = ci['Bxy','2.5 %'], + Bzy.est.zhang = coef['Bzy'], + Bzy.ci.upper.zhang = ci['Bzy','97.5 %'], + Bzy.ci.lower.zhang = ci['Bzy','2.5 %'])) + }, + + error = function(e){ + message("An error occurred:\n",e) + result$error <- paste0(result$error,'\n', e) + }) + + df <- df.loco.mle + N <- nrow(df) + m <- nrow(df[!is.na(x.obs)]) + p <- v <- train <- rep(0,N) + M <- m + p[(M+1):(N)] <- 1 + v[1:(M)] <- 1 + df <- df[order(x.obs)] + y <- df[,y] + x <- df[,x.obs] + z <- df[,z] + w <- df[,w_pred] + # gmm gets pretty close + (gmm.res <- predicted_covariates(y, x, z, w, v, train, p, max_iter=100, verbose=TRUE)) + + result <- append(result, + list(Bxy.est.gmm = gmm.res$beta[1,1], + Bxy.ci.upper.gmm = gmm.res$confint[1,2], + Bxy.ci.lower.gmm = gmm.res$confint[1,1], + gmm.ER_pval = gmm.res$ER_pval + )) + + result <- append(result, + list(Bzy.est.gmm = gmm.res$beta[2,1], + Bzy.ci.upper.gmm = gmm.res$confint[2,2], + Bzy.ci.lower.gmm = gmm.res$confint[2,1])) - ## print(rater_formula) - ## print(proxy_formula) - ## mle.irr <- measerr_irr_mle( df, outcome_formula = outcome_formula, rater_formula = rater_formula, proxy_formula=proxy_formula, truth_formula=truth_formula) - ## fisher.info <- solve(mle.irr$hessian) - ## coef <- mle.irr$par - ## ci.upper <- coef + sqrt(diag(fisher.info)) * 1.96 - ## ci.lower <- coef - sqrt(diag(fisher.info)) * 1.96 - - ## result <- append(result, - ## list(Bxy.est.mle = coef['x'], - ## Bxy.ci.upper.mle = ci.upper['x'], - ## Bxy.ci.lower.mle = ci.lower['x'], - ## Bzy.est.mle = coef['z'], - ## Bzy.ci.upper.mle = ci.upper['z'], - ## Bzy.ci.lower.mle = ci.lower['z'])) return(result)