confIntOmegaSq function producing NAs

[IndrajeetPatil]

Hi,

I am using userfriendlyscience::confIntOmegaSq for some analysis and noticed that it is producing NAs in some contexts and am not sure why. I am providing a reprex below.

Any help would be much appreciated.

# libraries needed
library(userfriendlyscience)

# defining the dataframe
df <- as.data.frame(structure(c(4, 4, 4, 4, 2, 5, 2, 2, 2, 3, 5, 5, 3, 5, 5, 5, 4, 
                  4, 5, 3, 2, 2, 4, 2, 5, 2, 4, 4, 5, 4, 2, 2, 3, 3, 4, 3, 3, 4, 
                  3, 4, 3, 5, 4, 3, 2, 2, 3, 4, 4, 4, 4, 4, 3, 4, 4, 4, 4, 4, 4, 
                  3, 3, 2, 2, 2, 2, 2, 4, 5, 2, 4, 2, 2, 3, 2, 4, 5, 2, 4, 4, 4, 
                  3, 3, 3, 3, 3, 3, 4, 2, 3, 3, 5, 4, 4, 4, 2, 36, 53, 34, 33, 
                  28, 36, 25, 23, 29, 38, 28, 32, 41, 44, 42, 30, 65, 21, 27, 43, 
                  23, 48, 22, 20, 29, 18, 65, 37, 25, 25, 59, 25, 27, 38, 39, 31, 
                  43, 29, 66, 27, 47, 46, 36, 59, 60, 28, 61, 55, 29, 29, 29, 22, 
                  60, 29, 39, 27, 25, 19, 50, 27, 28, 57, 36, 26, 21, 55, 49, 33, 
                  32, 40, 52, 31, 41, 57, 19, 44, 55, 24, 35, 33, 35, 51, 67, 36, 
                  27, 47, 46, 19, 50, 50, 60, 66, 47, 21, 30), .Dim = c(95L, 2L
                  ), .Dimnames = list(NULL, c("x", "y"))))

# getting confidence interval for omega squared
userfriendlyscience::confIntOmegaSq(
       var1 = df$x,
       var2  = df$y,
       conf.level = 0.95
)
#> Omega squared: 95% CI = [NA; .16], point estimate = .04

Created on 2018-03-08 by the reprex package (v0.2.0).