0

I'm trying to run a regression in R and I want to control the fipsmerg variable by factors but R gives me a memory error.

input:

myprobit <-  glm(a_imt~a_imt_1+totpop+reltrad_1+reltrad_2+reltrad_3+reltrad_4+as.factor(fipsmerg),data = data, family=binomial(link="probit"))
lmr <- lm(a_imt~a_imt_1+totpop+reltrad_1+reltrad_2+reltrad_3+reltrad_4+as.factor(fipsmerg),data = data)

output:

cannot allocate vector of size 16.7 Gb

(my database has around 900 thousand observations) One person suggested I use something in R that is equivalent to Stata's absorb, but I don't know what it would be. Does anyone have any suggestions?

Improve this question
3
Related questions
0
Binomial logistic regression with categorical predictors and interaction (binomial family argument and p-value differences)
2
Memory issue when using factor for fixed effect regression
0
Are "cached" values causing logistic regression to fail?
Load 3 more related questions Show fewer related questions

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.