Search Results
Report
Consistent covariance matrix estimation in probit models with autocorrelated errors
Some recent time-series applications use probit models to measure the forecasting power of a set of variables. Correct inferences about the significance of the variables requires a consistent estimator of the covariance matrix of the estimated model coefficients. A potential source of inconsistency in maximum likelihood standard errors is serial correlation in the underlying disturbances, which may arise, for example, from overlapping forecasts. We discuss several practical methods for constructing probit autocorrelation-consistent standard errors, drawing on the generalized method of moments ...
Journal Article
Formulas or supervision? Remarks on the future of regulatory capital
This paper was presented at the conference "Financial services at the crossroads: capital regulation in the twenty-first century" as part of session 6, "The role of capital regulation in bank supervision." The conference, held at the Federal Reserve Bank of New York on February 26-27, 1998, was designed to encourage a consensus between the public and private sectors on an agenda for capital regulation in the new century.
Report
Monetary tightening cycles and the predictability of economic activity
Eleven of fourteen monetary tightening cycles since 1955 were followed by increases in unemployment; three were not. The term spread at the end of these cycles discriminates almost perfectly between subsequent outcomes, but levels of nominal or real interest rates, as well as other interest rate spreads, generally do not.
Report
Rethinking the role of NAIRU in monetary policy: implications of model formulation and uncertainty
In this paper we rethink the NAIRU concept and examine whether it might have a useful role in monetary policy. We argue that it can, but success depends critically on defining NAIRU as a short-run concept and distinguishing it from a long-run concept like the natural rate of unemployment. We examine what effect uncertainty has on the use of NAIRU in policy. Uncertainty about the level of NAIRU does not imply that monetary policy should react less to the NAIRU gap. However, uncertainty about the effect of the NAIRU gap on inflation does require adjustments to the policy reaction function. ...
Journal Article
A prolegomenon to future capital requirements
Bank supervisors have made significant strides since 1980 in the area of capital requirements, and they are currently pursuing further refinements. This article looks beyond such developments at longer term supervisory goals. Abstracting to some extent from the current regulatory framework, the author attempts to delineate a set of fundamental principles for future work on capital requirements. He distinguishes minimum capital--an objective standard imposed by regulators across firms--from optimum capital--a subjective standard adopted by individual firms to cover their own risks-- and shows ...
Report
Extracting business cycle fluctuations: what do time series filters really do?
Various methods are available to extract the "business cycle component" of a given time series variable. These methods may be derived as solutions to frequency extraction or signal extraction problems and differ in both their handling of trends and noise and their assumptions about the ideal time-series properties of a business cycle component. The filters are frequently illustrated by application to white noise, but applications to other processes may have very different and possibly unintended effects. This paper examines several frequently used filters as they apply to a range of dynamic ...
Journal Article
Consistent margin requirements: are they feasible?
Report
Generalized canonical regression
This paper introduces a generalized approach to canonical regression, in which a set of jointly dependent variables enters the left-hand side of the equation as a linear combination, formally like the linear combination of regressors in the right-hand side of the equation. Natural applications occur when the dependent variable is the sum of components that may optimally receive unequal weights or in time series models in which the appropriate timing of the dependent variable is not known a priori. The paper derives a quasi-maximum likelihood estimator as well as its asymptotic distribution ...