A panel data approach to economic forecasting: the bias-corrected average forecast

In this paper, we propose a novel approach to econometric forecasting of stationary and ergodic time series within a panel-data framework. Our key element is to employ the (feasible) bias-corrected average forecast. Using panel-data sequential asymptotics we show that it is potentially superior to other techniques in several contexts. In particular, it is asymptotically equivalent to the conditional expectation, i.e., has an optimal limiting mean-squared error. We also develop a zeromean test for the average bias and discuss the forecast-combination puzzle in small and large samples. Monte-Carlo simulations are conducted to evaluate the performance of the feasible bias-corrected average forecast in finite samples. An empirical exercise based upon data from a well known survey is also presented. Overall, theoretical and empirical results show promise for the feasible bias-corrected average forecast.

A panel data approach to economic forecasting: the bias-corrected average forecast

In this paper, we propose a novel approach to econometric forecasting of stationary and ergodic time series within a panel-data framework. Our key element is to employ the bias-corrected average forecast. Using panel-data sequential asymptotics we show that it is potentially superior to other techniques in several contexts. In particular it delivers a zero-limiting mean-squared error if the number of forecasts and the number of post-sample time periods is sufficiently large. We also develop a zero-mean test for the average bias. Monte-Carlo simulations are conducted to evaluate the performance of this new technique in finite samples. An empirical exercise, based upon data from well known surveys is also presented. Overall, these results show promise for the bias-corrected average forecast.

A panel data approach to economic forecasting: the bias-corrected average forecast

In this paper, we propose a novel approach to econometric forecasting of stationary and ergodic time series within a panel-data framework. Our key element is to employ the (feasible) bias-corrected average forecast. Using panel-data sequential asymptotics we show that it is potentially superior to other techniques in several contexts. In particular, it is asymptotically equivalent to the conditional expectation, i.e., has an optimal limiting mean-squared error. We also develop a zeromean test for the average bias and discuss the forecast-combination puzzle in small and large samples. Monte-Carlo simulations are conducted to evaluate the performance of the feasible bias-corrected average forecast in finite samples. An empirical exercise, based upon data from a well known survey is also presented. Overall, these results show promise for the feasible bias-corrected average forecast.

Assessing competition in banking industry: a multiproduct approach

This paper aims to investigate the competition aspects of banking multiproduct operation. Based on an extension of Panzar and Rosse (1987)’s test to the case of a multiproduct banking firm, we take advantage of a new dataset constructed to Brazilian banking conglomerates to infer the impact of conglomeration on market power. We find that banks offering classic (i.e., loans and credit cards) and other bank products (i.e., brokerage services, insurance and capitalization bonds) have substantially higher market power than the ones which offer only classic products. Results suggest a positive bias on the traditional estimates of competition in which the multioutput actions are not taken into account.

Assessing competition in the banking industry: a multi-product approach

This paper investigates the competitive aspects of multi-product banking operations. Extending Panzar and Rosse (1987)’s model to the case of a multi-product banking firm, we show that the higher the economies of scope in multi-product banking are, the lower Panzar-Rosse’s measure of competition in the banking sector is. To test this empirical implication and determine the impact of multi-production/conglomeration on market power, we use a new dataset on Brazilian banking conglomerates. Consistent with our theoretical prediction, we find that banks offering classic banking products (i.e., loans and credit cards) and other banking products (i.e., brokerage services, insurance and capitalization bonds) have substantially higher market power than banks that offer only classic products. These results suggest a positive bias in the traditional estimates of competition in which multi-output actions are not considered.