I am trying to run the power.t.test function to calculate sample size for a
data frame of variances (i.e, 228 rows x 4 cols). Many of the fields are
missing values, which crashes the function. I have tried na. options in the
function, but the function doesn't recognize them. I have also tried an
if-else loop to skip over fields with missing values. How can I deal with
these missing values?
Here's the code:
var.df<-read.table("Transect_variance.csv",sep=",",header=TRUE, fill=TRUE)
n.df<-data.frame(cbind(var.df[,1:2],rep(-1,228),rep(-1,228),rep(-1,228),rep(-1,228)))
names(n.df)<-c("Strata","Transect","n35","n45","n36","n46")
#var.df[1:2,]
# Strata Transect ID Var35 Var45
Var36 Var46
# Herb 3-1 Herb 3-1 2.024264 NA
7.182 NA
# Herb 4-1 Herb 4-1 2.232552 2.26
2.360 2.393387
for i in 1:6 {
for j in 1:228 {
if ( var.df[i,j]=="") {n.df[i,j]=="" } else {
power.t.test(delta = 2.5, sd = var.df[i,j], sig.level =
0.1, power = 0.9,
type = "two.sample", alternative = "two.sided")
}
}
}
______________________________________________
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
