aggregate with function rosnerTest

Question

I get an error

"Error in if (any(outlier)) { : missing value where TRUE/FALSE needed" when I try to use the rosnerTest, from the package EnvStats.

out1 <- aggregate(x = df$Price, by = list(df$Item), FUN = rosnerTest)

I'm trying to use the aggregate function in place of using for loop to do the rosner test because my data has over 14 million records with about 3 million unique items.

what package is `rosnerTest` found in? – Zelazny7 Feb 12 '16 at 20:42 — Zelazny7, Feb 12 '16 at 20:42

score 0 · Answer 1 · answered Feb 12 '16 at 20:49

0

Try tapply instead:

out1 <- tapply(df$Price, df$Item, rosnerTest)

answered Feb 12 '16 at 20:49

Zelazny7

39,946
18
70
84

I tried tapply also and I still get the same error. – RLearner Feb 12 '16 at 21:22

score 0 · Answer 2 · answered Apr 09 '21 at 15:32

It's a while ago, but maybe it still helps someone:

I got the same error because I had no outliers in some rows (e.g. all values were the same). In a for loop, you can use the try() function to ignore these errors and the loop will continue with the next row.

aggregate with function rosnerTest

2 Answers2