X-Git-Url: https://code.communitydata.science/ml_measurement_error_public.git/blobdiff_plain/b52b4f7daaba8a877b041ddb24c8f36b466ddc5b..c45ea9dfebca86dfddc1e9237aa74866c5166519:/simulations/03_depvar.R

diff --git a/simulations/03_depvar.R b/simulations/03_depvar.R
index 79a516f..f0064f2 100644
--- a/simulations/03_depvar.R
+++ b/simulations/03_depvar.R
@@ -31,13 +31,13 @@ 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, Bzy, seed, prediction_accuracy=0.73, log.likelihood.gain = 0.1){
+simulate_data <- function(N, m, B0, Bxy, Bzy, Bzx, seed, prediction_accuracy=0.73, log.likelihood.gain = 0.1){
     set.seed(seed)
     set.seed(seed)
 
     # make w and y dependent
-    z <- rbinom(N, 1, 0.5)
-    x <- rbinom(N, 1, 0.5)
+    z <- rnorm(N, sd=0.5)
+    x <- rbinom(N, 1, plogis(Bzx*z))
 
     ystar <- Bzy * z + Bxy * x + B0
     y <- rbinom(N,1,plogis(ystar))
@@ -75,21 +75,23 @@ parser <- add_argument(parser, "--prediction_accuracy", help='how accurate is th
 ## parser <- add_argument(parser, "--x_bias_y0", help='how is the classifier biased when y = 0 ?', default=0.75)
 parser <- add_argument(parser, "--Bxy", help='coefficient of x on y', default=0.01)
 parser <- add_argument(parser, "--Bzy", help='coeffficient of z on y', default=-0.01)
+parser <- add_argument(parser, "--Bzx", help='coeffficient of z on x', default=-0.5)
+parser <- add_argument(parser, "--B0", help='Base rate of y', default=0.5)
 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")
 
 args <- parse_args(parser)
 
-B0 <- 0
+B0 <- args$B0
 Bxy <- args$Bxy
 Bzy <- args$Bzy
-
+Bzx <- args$Bzx
 
 if(args$m < args$N){
-    df <- simulate_data(args$N, args$m, B0, Bxy, Bzy, args$seed, args$prediction_accuracy)
+    df <- simulate_data(args$N, args$m, B0, Bxy, Bzy, Bzx, args$seed, args$prediction_accuracy)
 
 #    result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy,'Bzy'=Bzy, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'x_bias_y0'=args$x_bias_y0,'x_bias_y1'=args$x_bias_y1,'outcome_formula' = args$outcome_formula, 'proxy_formula' = args$proxy_formula)
-    result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy,'Bzy'=Bzy, 'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'outcome_formula' = args$outcome_formula, 'proxy_formula' = args$proxy_formula)
+    result <- list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy,'Bzy'=Bzy, 'Bzx'=Bzx,'seed'=args$seed, 'y_explained_variance'=args$y_explained_variance, 'prediction_accuracy'=args$prediction_accuracy, 'outcome_formula' = args$outcome_formula, 'proxy_formula' = args$proxy_formula)
 
     outline <- run_simulation_depvar(df, result, outcome_formula = as.formula(args$outcome_formula), proxy_formula = as.formula(args$proxy_formula))