I am new to R programming and I am stuck for some time on a certain problem. I have a dataframe where I have 7 columns. The first column are bins. I define columns 2-4 as one subset (one sample) and columns 5-7 as another sample. I want to perform statistical tests on these samples for each bin (so for each row). Here is a photo for better understanding:
I did this with the t-test and it worked. But for the Bartlett test I stumble upon some difficulties due to the syntax. So I tried this but I get an error that all observations are in the same group: Note: I save the p-value of the b.test in a new column.
#perform Bartlett test Data$P_Value_Bartlett <- NA
for (i in 1:nrow(Data)) {
Data$P_Value_Bartlett[i] <- bartlett.test(unlist(Data[i, 2:7]),rep(LETTERS[1:2], each=3))$p.value
} # transforms row i into a vector, rep defines 2 groups, then bartlett test has a numeric vector and grouping variable to run the test
So e.g. I want to perform a test: I take data of row 1 (9,75) and compare the col 2-4 with col 5-7 and see if there is for example a difference in variance. I want to perform this test in each row, always comparing the same set of cols with each other.
I also have the problem, that the test is not working if I have NA values:
I added the input: na.action=na.omit But it is not working.
Anyone an idea whether this is the correct way or if it should be done in another way?
