2
$\begingroup$

I'm studying behavior types versus individual characteristics (age, gender, marital status, education, physical handicap) and classified them into binary data except for age. Example :

  • Gender (0:Female; 1:male)
  • Marital status (0:no; 1:yes)
  • Education (college-graduated: 1;otherwise: 0)

I describe data on this form :

              Behavior 1         Behavior 2      Behavior 3
              Mean    SD         Mean    SD      Mean    SD
Age           37.05  15.8        36.2   15.05    30.07   13  
Gender        0.49   0.501       0.4    0.49     0.67    0.5
Education     0.03   0.185       0.04   0.20     0       0

We these data we could say for example that behavior 3 is more likely to occur when the age is relatively decreased and gender effect (male) comparing to other behaviors, but still speculation. But it allows me to have an idea about what variables to include in GLM. After that I'm trying to model behavior by converting behavior 3 appearance into (0, 1) for each individual

id   Behavior3 Age Gender
1       0      19  M
....
499     1      45  F

model1=glm(Behavior3 ~ Age + Gender, family=binomial)
summary(model1)
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.