2

I'd like to find out if there's a statistically significant difference in the conversion rate between two categories.

My data looks like this

    operating_system converted
1             Mac     FALSE
2             Mac     FALSE
3         Windows     FALSE
4         Windows      TRUE
5         Windows     FALSE
6             Mac      TRUE
7             Mac     FALSE
8         Windows     FALSE
9             Mac     FALSE
10            Mac     FALSE

I ran this code.

chisq.test(df)

And I received this error.

Error in chisq.test(df) : all entries of 'x' must be nonnegative and finite

Cauder
  • 2,157
  • 4
  • 30
  • 69

1 Answers1

2

chisq.test uses a contingency table :

df <- data.frame(operating_system = c("Mac", "Mac", "Windows", "Windows", "Windows", "Mac", "Mac", "Windows", "Mac", "Mac"),
             converted = c(F, F, F, T, F, T, F, F, F, F), stringsAsFactors = TRUE)

chisq.test(table(df))
Clemsang
  • 5,053
  • 3
  • 23
  • 41