Argh, that was my stupidity. Assuming I understand how your columns are named my code should have read:
mkttest(mydata$`I 35-39`)
where mydata is the nane of your data.frame or tibble.
You do not have to create a vector, just read in the column of data from the data.frame It is a vector. Here is a quick example
dat1 <- data.frame(aa = 1:50, bb = 50:1)
library(modifiedmk)
mkttest(dat1$aa)
The only issue is that it looks like your variable/column names has spaces which R does not like. Therefore you need the I 35-39 format so that R recognizes that as a column name.
If I am not making sense can you supply some sample data? A handy way to supply sample data is to use the dput() function. See ?dput. If you have a very large data set then something like head(dput(myfile), 100) will likely supply enough data for us to work with.