This paper develops a demand model for bank loans with a two-step decision process. In the first step, the agent chooses the financial institution from which she would like to borrow. In the second step, conditioned in the first decision, the agent chooses the desired amount of the loan. The model belongs to the Generalized Linear Latent Mixed Model (GLLAMM) class whose flexible structure is convenient to combine a discrete distribution (first step) with a continuous one (second step). The model is empirically estimated using a sample of data from the credit bureau system SCR from the Brazilian Central Bank. The results suggest that variables like the loan maturity and its risk classification are more relevant in the choice of the financial institution whereas variables like the total number of loans the borrower has in the SCR, value of the loans still to mature, existence of guarantees are more relevant in the amount to be borrowed. Other variables like the interest rate, years of relationship, and firm size show to be important in both steps.
Download Info
To download:
If you experience problems downloading a file, check if you have the
proper application to
view it first. Information about this may be contained
in the File-Format links below. In case of further problems read
the IDEAS help
page. Note that these files are not on the IDEAS
site. Please be patient as the files may be large.
Publisher Info
Paper provided by Central Bank of Brazil, Research Department in its series Working Papers Series with number
156.