Hello,
How do you deal with a dependent variable that has some values equal to zero when using boxcox transformations in proc transreg?
proc transreg data = sample1;
model boxcox(DV)=identity(IV);
run;
ERROR: 11 invalid values were encountered while attempting to transform variable DV.
Thank you
You could prevent λ in the Box-Cox transformation from being exactly equal to zero, then you shouldn't have any problems with zero values of Y.
Thanks for your answer. I tried this and didn't work:
proc transreg data = sample1;
model boxcox(DV / lambda ^= 0) = identity(IV);
run;
proc transreg data = sample1;
model boxcox(DV / lambda = -3 to -0.25 by 0.25,-0.1, 0.1, 0.25 to 3 by 0.25) = identity(IV);
run;
Thanks for your response. I tried using the code with that specific lambda but it showed the same error.
Don't miss out on SAS Innovate - Register now for the FREE Livestream!
Can't make it to Vegas? No problem! Watch our general sessions LIVE or on-demand starting April 17th. Hear from SAS execs, best-selling author Adam Grant, Hot Ones host Sean Evans, top tech journalist Kara Swisher, AI expert Cassie Kozyrkov, and the mind-blowing dance crew iLuminate! Plus, get access to over 20 breakout sessions.
Learn the difference between classical and Bayesian statistical approaches and see a few PROC examples to perform Bayesian analysis in this video.
Find more tutorials on the SAS Users YouTube channel.