2
$\begingroup$

I have a dataset with the following structure:

Choice   Bank Bank_x  Customer Customer_x
  0      UBS     .       1          .
  1      CS      .       1          .
  1      KZ      .       1          .
  0      VA      .       1          .
--------------------------------------
  0      UBS     .       2          .
  0      CS      .       2          .
  1      KZ      .       2          .
  0      VA      .       2          .

Where choice is whether a customer would open an account in a given bank tomorrow (0 = no, 1 = yes). In the data there are a number of bank and customer specific variables.

My first thought was to use a Hierarchical logit model with bank choices nested within customers, so as to get parameters for each customer. However I am suddenly in doubt about whether this is the right choice, and I would like to hear any thougths from you guys before I settle on an approach.

Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

That sounds reasonable to me. I guess the customer can say yes to more than one bank even though he probably wouldn't open an account in two banks on the same day.

Improve this answer
$\endgroup$

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.