Modelos para a Utilização das Operações de Redesconto pelos Bancos com Carteira Comercial no Brasil

Many models were used to identify the factors affecting the demand for overnight funds by commercial banks. Theses models overcome overdispersion problems caused by excess of zeros found in the dataset. Generalized Linear Latent and Mixed Models (GLLAMM) constitute a class of models which allows the identification of both the direct and indirect effects of rediscount rate through the inclusion of random effects in the intercept (incorporating specific effects for each bank) and other coefficients (identifying individual behavior of each bank regarding the same stimuli). The results suggest the use of overnight funds is mainly influenced by the opening amount in bank reserves, by the net value of operations in the SELIC clearinghouse, by the rediscount rate, by the volatility of in bank reserves and by the reserve requirements on demand deposits.