X-Git-Url: https://code.communitydata.science/ml_measurement_error_public.git/blobdiff_plain/47e9367ed5c61b721bdc17cddd76bced4f8ed621..refs/heads/main:/simulations/02_indep_differential.R

diff --git a/simulations/02_indep_differential.R b/simulations/02_indep_differential.R
index d4c4397..9c33be7 100644
--- a/simulations/02_indep_differential.R
+++ b/simulations/02_indep_differential.R
@@ -31,11 +31,11 @@ source("simulation_base.R")
 
 ## one way to do it is by adding correlation to x.obs and y that isn't in w.
 ## in other words, the model is missing an important feature of x.obs that's related to y.
-simulate_data <- function(N, m, B0, Bxy, Bzx, Bzy, seed, y_explained_variance=0.025, prediction_accuracy=0.73, y_bias=-0.8,accuracy_imbalance_difference=0.3){
+simulate_data <- function(N, m, B0, Bxy, Bzx, Bzy, seed, y_explained_variance=0.025, prediction_accuracy=0.73, y_bias=-0.8,z_bias=0,Px=0.5,accuracy_imbalance_difference=0.3){
     set.seed(seed)
     # make w and y dependent
-    z <- rbinom(N, 1, plogis(qlogis(0.5)))
-    x <- rbinom(N, 1, plogis(Bzx * z + qlogis(0.5)))
+    z <- rnorm(N,sd=0.5)
+    x <- rbinom(N, 1, plogis(Bzx * z + qlogis(Px)))
 
     y.var.epsilon <- (var(Bzy * z) + var(Bxy *x) + 2*cov(Bzy*z,Bxy*x)) * ((1-y_explained_variance)/y_explained_variance)
     y.epsilon <- rnorm(N, sd = sqrt(y.var.epsilon))
@@ -104,8 +104,10 @@ simulate_data <- function(N, m, B0, Bxy, Bzx, Bzy, seed, y_explained_variance=0.
     ## print(mean(df[z==1]$x == df[z==1]$w_pred))
     ## print(mean(df$w_pred == df$x))
 
-    odds.x1 <- qlogis(prediction_accuracy) + y_bias*qlogis(pnorm(scale(df[x==1]$y)))
-    odds.x0 <- qlogis(prediction_accuracy,lower.tail=F) + y_bias*qlogis(pnorm(scale(df[x==0]$y)))
+
+    resids <- resid(lm(y~x + z))
+    odds.x1 <- qlogis(prediction_accuracy) + y_bias*qlogis(pnorm(resids[x==1])) + z_bias * qlogis(pnorm(z[x==1],sd(z)))
+    odds.x0 <- qlogis(prediction_accuracy,lower.tail=F) + y_bias*qlogis(pnorm(resids[x==0])) + z_bias * qlogis(pnorm(z[x==0],sd(z)))
 
     ## acc.x0 <- p.correct[df[,x==0]]
     ## acc.x1 <- p.correct[df[,x==1]]
@@ -115,8 +117,7 @@ simulate_data <- function(N, m, B0, Bxy, Bzx, Bzy, seed, y_explained_variance=0.
 
     df[,w_pred := as.integer(w > 0.5)]
 
-    print(mean(df[z==0]$x == df[z==0]$w_pred))
-    print(mean(df[z==1]$x == df[z==1]$w_pred))
+
     print(mean(df$w_pred == df$x))
     print(mean(df[y>=0]$w_pred == df[y>=0]$x))
     print(mean(df[y<=0]$w_pred == df[y<=0]$x))
@@ -124,24 +125,27 @@ simulate_data <- function(N, m, B0, Bxy, Bzx, Bzy, seed, y_explained_variance=0.
 }
 
 parser <- arg_parser("Simulate data and fit corrected models")
-parser <- add_argument(parser, "--N", default=1000, help="number of observations of w")
-aparser <- add_argument(parser, "--m", default=500, help="m the number of ground truth observations")
+parser <- add_argument(parser, "--N", default=5000, help="number of observations of w")
+parser <- add_argument(parser, "--m", default=500, help="m the number of ground truth observations")
 parser <- add_argument(parser, "--seed", default=51, help='seed for the rng')
 parser <- add_argument(parser, "--outfile", help='output file', default='example_2.feather')
 parser <- add_argument(parser, "--y_explained_variance", help='what proportion of the variance of y can be explained?', default=0.1)
-parser <- add_argument(parser, "--prediction_accuracy", help='how accurate is the predictive model?', default=0.8)
+parser <- add_argument(parser, "--prediction_accuracy", help='how accurate is the predictive model?', default=0.75)
 parser <- add_argument(parser, "--accuracy_imbalance_difference", help='how much more accurate is the predictive model for one class than the other?', default=0.3)
 parser <- add_argument(parser, "--Bzx", help='Effect of z on x', default=0.3)
 parser <- add_argument(parser, "--Bzy", help='Effect of z on y', default=-0.3)
 parser <- add_argument(parser, "--Bxy", help='Effect of z on y', default=0.3)
 parser <- add_argument(parser, "--outcome_formula", help='formula for the outcome variable', default="y~x+z")
 parser <- add_argument(parser, "--proxy_formula", help='formula for the proxy variable', default="w_pred~y*z*x")
-parser <- add_argument(parser, "--y_bias", help='coefficient of y on the probability a classification is correct', default=-0.75)
+parser <- add_argument(parser, "--y_bias", help='coefficient of y on the probability a classification is correct', default=-0.5)
+parser <- add_argument(parser, "--z_bias", help='coefficient of z on the probability a classification is correct', default=0)
 parser <- add_argument(parser, "--truth_formula", help='formula for the true variable', default="x~z")
-
+parser <- add_argument(parser, "--Px", help='base rate of x', default=0.5)
+parser <- add_argument(parser, "--confint_method", help='method for approximating confidence intervals', default='quad')
 args <- parse_args(parser)
 
 B0 <- 0
+Px <- args$Px
 Bxy <- args$Bxy
 Bzy <- args$Bzy
 Bzx <- args$Bzx
@@ -155,9 +159,9 @@ if(args$m < args$N){
     ## pc.df <- pc(suffStat=list(C=cor(df.pc),n=nrow(df.pc)),indepTest=gaussCItest,labels=names(df.pc),alpha=0.05)
     ## plot(pc.df)
 
-    result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy, Bzx=args$Bzx, 'Bzy'=Bzy, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'accuracy_imbalance_difference'=args$accuracy_imbalance_difference, 'y_bias'=args$y_bias,'outcome_formula'=args$outcome_formula, 'proxy_formula'=args$proxy_formula,truth_formula=args$truth_formula, error='')
+    result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy, 'Bzx'=args$Bzx, 'Bzy'=Bzy, 'Px'=Px, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'accuracy_imbalance_difference'=args$accuracy_imbalance_difference, 'y_bias'=args$y_bias,'outcome_formula'=args$outcome_formula, 'proxy_formula'=args$proxy_formula,truth_formula=args$truth_formula, confint_method=args$confint_method, error='')
 
-    outline <- run_simulation(df, result, outcome_formula=as.formula(args$outcome_formula), proxy_formula=as.formula(args$proxy_formula), truth_formula=as.formula(args$truth_formula))
+    outline <- run_simulation(df, result, outcome_formula=as.formula(args$outcome_formula), proxy_formula=as.formula(args$proxy_formula), truth_formula=as.formula(args$truth_formula),confint_method=args$confint_method)
     
    
  outfile_lock <- lock(paste0(args$outfile, '_lock'),exclusive=TRUE)