plotting missing

missing.png

missing.R

# Load libs 
library(ggplot2)


# Simulate correlated data
R = matrix(cbind(1,.80, .80,1), nrow=2)
U = t(chol(R))
n_vars = dim(U)[1]
n_obs = 10000

# Set seed for reproducibility
set.seed(31415)
random_normal = matrix(rnorm(n_vars*n_obs, 0, 1), nrow=n_vars, ncol=n_obs)
X = U %*% random_normal

# Convert to df and confirm
data = as.data.frame(t(X))
names(data) = c("response","predictor")
cor(data)

# Induce missing in response 
data$response[tail(order(data$response), 100)] <- NA

# Missing 
data$missing <- is.na(data$response)

# Rescale missing to match range of y
data$missing <- ifelse(data$missing, max(data$response, na.rm=T), NA)

ggplot(data, aes(x = predictor, y = response)) +
	geom_point(alpha=.03) + 
	geom_smooth() + 
	geom_hline(aes(yintercept = max(data$response, na.rm=T)), size=.05, color="#333333", linetype="dotted", alpha=.7) + 
	geom_point(aes(x=data$predictor, y= data$missing), alpha=.03, color="red") +
	geom_text(data=NULL, label = "Missing", y = max(data$response, na.rm=T) + .1, x = -4.8, size=3) + 
    theme_minimal() 

ggsave(file="missing.png")