88 lines
2.7 KiB
R
88 lines
2.7 KiB
R
### EXAMPLE 2: demonstrates how measurement error can lead to a type sign error in a covariate
|
|
### Even when you have a good predictor, if it's biased against a covariate you can get the wrong sign.
|
|
### Even when you include the proxy variable in the regression.
|
|
### But with some ground truth and multiple imputation, you can fix it.
|
|
|
|
library(argparser)
|
|
library(mecor)
|
|
library(ggplot2)
|
|
library(data.table)
|
|
library(filelock)
|
|
library(arrow)
|
|
library(Amelia)
|
|
library(Zelig)
|
|
library(predictionError)
|
|
options(amelia.parallel="no",
|
|
amelia.ncpus=1)
|
|
|
|
## SETUP:
|
|
### we want to estimate x -> y; x is MAR
|
|
### we have x -> k; k -> w; x -> w is used to predict x via the model w.
|
|
### A realistic scenario is that we have an NLP model predicting something like "racial harassment" in social media comments
|
|
### The labels x are binary, but the model provides a continuous predictor
|
|
|
|
### simulation:
|
|
#### how much power do we get from the model in the first place? (sweeping N and m)
|
|
####
|
|
source("simulation_base.R")
|
|
|
|
simulate_latent_cocause <- function(N, m, B0, Bxy, Bgy, Bkx, Bgx, seed){
|
|
set.seed(seed)
|
|
|
|
## the true value of x
|
|
|
|
g <- rbinom(N, 1, 0.5)
|
|
k <- rnorm(N, 0, 1)
|
|
xprime <- Bkx*k + Bgx * g + rnorm(N,0,1)
|
|
xvec <- scale(xprime)
|
|
|
|
y <- Bxy * xvec + Bgy * g + rnorm(N, 0, 1) + B0
|
|
|
|
df <- data.table(x=xvec,k=k,y=y,g=g)
|
|
names(df) <- c('x','k','y','g')
|
|
if( m < N){
|
|
df <- df[sample(nrow(df), m), x.obs := x]
|
|
} else {
|
|
df <- df[, x.obs := x]
|
|
}
|
|
|
|
w.model <- lm(x ~ k,df)
|
|
w <- predict(w.model,data.frame(k=k))
|
|
w <- logistic(w + rnorm(N,0,sd(w)*0.1))
|
|
## y = B0 + B1x + e
|
|
|
|
df[,':='(w=w, w_pred = as.integer(w>0.5))]
|
|
return(df)
|
|
}
|
|
|
|
|
|
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, "--m", default=200, help="m the number of ground truth observations")
|
|
parser <- add_argument(parser, "--seed", default=4321, help='seed for the rng')
|
|
parser <- add_argument(parser, "--outfile", help='output file', default='example_2.feather')
|
|
args <- parse_args(parser)
|
|
|
|
Ns <- c(1000, 10000, 1e6)
|
|
ms <- c(100, 250, 500, 1000)
|
|
B0 <- 0
|
|
Bxy <- 0.2
|
|
Bgy <- -0.2
|
|
Bkx <- 2
|
|
Bgx <- 3
|
|
|
|
outline <- run_simulation(simulate_latent_cocause(args$N, args$m, B0, Bxy, Bgy, Bkx, Bgx, args$seed)
|
|
,list('N'=args$N,'m'=args$m,'B0'=B0,'Bxy'=Bxy,'Bgy'=Bgy, 'Bkx'=Bkx, 'Bgx'=Bgx, 'seed'=args$seed))
|
|
|
|
outfile_lock <- lock(paste0(args$outfile, '_lock'),exclusive=TRUE)
|
|
if(file.exists(args$outfile)){
|
|
logdata <- read_feather(args$outfile)
|
|
logdata <- rbind(logdata,as.data.table(outline))
|
|
} else {
|
|
logdata <- as.data.table(outline)
|
|
}
|
|
|
|
print(outline)
|
|
write_feather(logdata, args$outfile)
|
|
unlock(outfile_lock)
|