How can I modify my code to include loop? - r

Question

I am trying to create a function that examines how variables with different distributions influence OLS results. I have created two DVs (y1 and y2) but would like to expand this to include five or so. I am trying to change my code to include a loop so I do not have to copy and paste this multiple times, but I am not having much luck. Any suggestions would be greatly appreciated.
library(psych)
library(arm)
library(plyr)
library(fBasics)
regsim <- function(iter, n) {
ek1 <- rnorm(n, 0, 1)
ek2 <- rnorm(n, 0, 5)
x <- rnorm(n, 0, .5)
y1 <- .3*x + ek1
y2 <- .3*x + ek2
#y1
lm1 <- lm(y1 ~ x)
bhat1 <- coef (lm1)[2]
sehat1 <- se.coef (lm1) [2]
skewy1 <- skew(y1)
stdevy1 <- stdev(y1)
#y2
lm2 <- lm(y2 ~ x)
bhat2 <- coef (lm2)[2]
sehat2 <- se.coef (lm2) [2]
skewy2 <- skew(y2)
stdevy2 <- stdev(y2)
results <- c(bhat1, sehat1, stdevy1, skewy1,
bhat2, sehat2, stdevy2, skewy2)
names(results) <- c('b1', 'se1', 'sdy1', 'skewy1',
'b2', 'se2', 'sdy2', 'skewy2')
return(results)
}
iter <-1000
n <-500
results <- NULL
sims <-ldply(1:iter, regsim, n)
sims$n <- n
results <- rbind(results, sims)

Answer 1

Another option...
regsim <- function(n=100,num.y=5,sd=c(1:5)){
if(length(sd) != num.y){stop('length of sd must match number of dependent vars')
} else {
ldply(1:num.y,function(x){
e <- rnorm(n,0,sd=sd[x])
x <- rnorm(n,0,5)
y <- 0.3*x + e
out <- lm(y~x)
b1 <- coef(out)[2]
int <- coef(out)[1]
data.frame(b1=b1,int=int)
})
}
}
regsim(num.y=10,sd=c(1:10))
b1 int
1 0.30817303 0.0781049
2 0.38681600 -0.3359067
3 0.24560773 -0.0277561
4 0.08032659 0.1877233
5 0.39873955 -0.6027522
6 0.21729930 0.7384340
7 0.33761456 -0.1053028
8 0.26502006 -0.1851552
9 0.15452261 -1.6334873
10 -0.10496863 -0.3225169
This will allow you to specify the number of dependent variables and the SD for each error term. You can then use replicate to repeat the function for the desired number of replications.
replicate(10,regsim(),simplify = F)
[[1]]
b1 int
1 0.3047779 -0.01984306
2 0.3133198 -0.20458410
3 0.2833979 -0.25307502
4 0.3066878 -0.03235019
5 0.1374949 0.10958616
[[2]]
b1 int
1 0.2902103 -0.12683502
2 0.3499006 0.06691437
3 0.1949797 -0.14371830
4 0.2358269 0.53117467
5 0.2869511 0.16281380
[[3]]
b1 int
1 0.2952211 0.05905549
2 0.2367774 0.02862166
3 0.0896778 -0.08467935
4 0.2352622 -0.20835837
5 0.3149963 0.07042032
[[4]]
b1 int
1 0.2946468 -0.08266406
2 0.3322577 0.17558135
3 0.2200087 -0.25778150
4 0.1822915 0.34962679
5 0.2442479 0.34433656
[[5]]
b1 int
1 0.2882853 0.12677506
2 0.3455534 -0.27885958
3 0.2981193 0.04598347
4 0.3380173 0.05243198
5 0.2148643 -0.09631672
[[6]]
b1 int
1 0.2962269 0.03743759
2 0.2979327 -0.12830803
3 0.3352781 -0.03935422
4 0.2584965 -0.05924351
5 0.2856802 0.03430055
[[7]]
b1 int
1 0.2968077 -0.10300109
2 0.2954560 0.25979902
3 0.3276077 -0.07001758
4 0.1825841 0.13508932
5 0.4302788 -0.13951914
[[8]]
b1 int
1 0.2992147 0.02084806
2 0.2765976 0.07277813
3 0.2469616 0.44580403
4 0.2601966 -0.09849855
5 0.2679183 0.50501652
[[9]]
b1 int
1 0.2963905 0.03308366
2 0.3356783 -0.06080088
3 0.3199835 0.22533444
4 0.3546083 -0.26909478
5 0.3536241 -0.19795094
[[10]]
b1 int
1 0.3100336 -0.05228032
2 0.4076447 -0.18715063
3 0.3436858 -0.37518649
4 0.4569368 -0.09114672
5 0.3255668 -0.18738138

Answer 2

How about this:
n <- 1000
x <- rnorm(n, 0, .5)
fun_reg <- function(n, ek_mu, ek_sd, x){
s <- list() # list to collect results for output
ek <- rnorm(n, ek_mu, ek_sd)
y <- .3*x + ek
m <- lm(y ~ x)
s$bhat <- coef(m)[2]
s$sehat <- arm::se.coef(m)[2]
s$skewy <- psych::skew(y)
s$stdevy <- fBasics::stdev(y)
return(s)
}
purrr::map_dfr(c(1, 5, 10, 20, 50), ~fun_reg(n, 0, ., x))
Edit:
This now has 500 observations each and the regression is repeated with 1000 draws for each value of the standard deviation. A variable ek_sd has been added to the final output, to reflect with which standard deviation the values were arrived at. Note that x is not redrawn for each iteration, but I'm not entirely sure, that that is what you want. If you want x to be redrawn at each iteration, move it inside the function.
n <- 500
x <- rnorm(n, 0, .5)
fun_reg <- function(n, ek_mu, ek_sd, x){
s <- list()
ek <- rnorm(n, ek_mu, ek_sd)
y <- .3*x + ek
m <- lm(y ~ x)
s$ek_sd <- ek_sd
s$bhat <- coef(m)[2]
s$sehat <- arm::se.coef(m)[2]
s$skewy <- psych::skew(y)
s$stdevy <- fBasics::stdev(y)
return(s)
}
intr <- unlist(lapply(c(1, 5, 10, 20, 50), rep, 1000))
purrr::map_dfr(intr, ~fun_reg(n, 0, ., x))

Answer 3

This reduces the package reliance to just psych::skew and an optional ggplot2 call:
library(psych)
regsim <- function(n, eks) {
x <- rnorm(n, 0, .5)
ek <- sapply(eks, function(x) rnorm(n, 0, x))
y <- 0.3 * x + ek
lms <- lm(y ~ x)
data.frame(b_hat = lms[['coefficients']][2,],
int = lms[['coefficients']][1, ],
skew_y = psych::skew(y),
se_hat = unlist(lapply(summary(lms), function(lst) lst[[4]][2,2]), use.names = FALSE),
sd_y = apply(y, 2, sd),
sd_eks = eks
)
}
iter <-1000
n <-500
eks_sd = c(1,5)
# do the simulations and make them into a nice data.frame
sims <- replicate(iter, regsim(n, eks_sd), simplify = FALSE)
results <- do.call(rbind, sims)
#next parts are optional
results$iter_id <- rep(seq_len(iter), each = length(eks_sd))
tibble::as_tibble(results)
# Random graph because everyone loves graphs
library(ggplot2)
ggplot(results, aes(x = iter_id, y = int)) + geom_point() + facet_grid(vars(sd_eks))
The main thing is that lm can take multiple y arguments. That's why we we create a matrix of ek using sapply.