update real data examples code and rerun project.

[ml_measurement_error_public.git] / simulations / 03_depvar.R

diff --git a/simulations/03_depvar.R b/simulations/03_depvar.R
index 69b4485947e9b2c2a89b0484dc38e2b467d72376..f0064f2940d93257b6ecfa481db7fa2b4f3c47ff 100644 (file)
--- a/simulations/03_depvar.R
+++ b/simulations/03_depvar.R
@@ -31,18 +31,17 @@ 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){
+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))
 
-    # glm(y ~ x + z, family="binomial")
-
     df <- data.table(x=x,y=y,ystar=ystar,z=z)
 
     if(m < N){
@@ -66,31 +65,33 @@ simulate_data <- function(N, m, B0, Bxy, Bzy, seed, prediction_accuracy=0.73){
 }
 
 parser <- arg_parser("Simulate data and fit corrected models")
-parser <- add_argument(parser, "--N", default=1000, help="number of observations of w")
+parser <- add_argument(parser, "--N", default=10000, 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=17, 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=0.005)
+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=0.72)
 ## parser <- add_argument(parser, "--x_bias_y1", help='how is the classifier biased when y = 1?', default=-0.75)
 ## 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=0.3)
-parser <- add_argument(parser, "--Bzy", help='coeffficient of z on y', default=-0.3)
+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))