Papers by Nicholas Kiefer
CREATES Research Papers, 2015
Counting processes provide a very flexible framework for modeling discrete events occurring over ... more Counting processes provide a very flexible framework for modeling discrete events occurring over time. Estimation and interpretation is easy, and links to more familiar approaches are at hand. The key is to think of data as "event histories," a record of times of switching between states in a discrete state space. In a simple case, the states could be default/non-default; in other models relevant for credit modeling the states could be credit scores or payment status (30 dpd, 60 dpd, etc.). Here we focus on the use of stochastic counting processes for mortgage default modeling, using data on high LTV mortgages. Borrowers seeking to finance more than 80% of a house's value with a mortgage usually either purchase mortgage insurance, allowing a first mortgage greater than 80% from many lenders, or use second mortgages. Are there differences in performance between loans financed by these different methods? We address this question in the counting process framework. In fact, MI is associated with lower default rates for both fixed rate and adjustable rate first mortgages.
Industrial and Labor Relations Review, Oct 1, 1982
Kiefer, N. M., Vogelsang, T. J., and Bunzel, H. (2000), “Simple Robust Testing of Regression Hypo... more Kiefer, N. M., Vogelsang, T. J., and Bunzel, H. (2000), “Simple Robust Testing of Regression Hypotheses,” Econometrica, 68, 695–714. [311,314] King, M. L. (1980), “Robust Tests for Spherical Symmetry and Their Application to Least Squares Regression,” The Annals of Statistics, 8, 1265–1271. [316] ——— (1987), “Towards a Theory of Point Optimal Testing,” Econometric Reviews, 6, 169–218. [315] Lehmann, E. L., and Romano, J. P. (2005), Testing Statistical Hypotheses, New York: Springer. [316] Müller, U. K. (2004), “A Theory of Robust Long-Run Variance Estimation,” Working paper, Princeton University. [311,314] ——— (2007), “A Theory of Robust Long-Run Variance Estimation,” Journal of Econometrics, 141, 1331–1352. [311,314,318,321] ——— (2011), “Efficient Tests Under a Weak Convergence Assumption,” Econometrica, 79, 395–435. [315] Müller, U. K., and Watson, M. W. (2008), “Testing Models of Low-Frequency Variability,” Econometrica, 76, 979–1016. [314] ——— (2013), “Measuring Uncertainty Abou...
This paper identifies the main bank specific determinants of time to failure during the financial... more This paper identifies the main bank specific determinants of time to failure during the financial crisis in Colombia using duration analysis. Using partial likelihood estimation, it shows that the process of failure of financial institutions during that period was not a merely random process; instead, it can be explained by differences in financial health and prudence existing across institutions. Among the relevant indicators that explain bank failure, the capitalization ratio appears to be the most significant one. Increases in this ratio lead to a reduction in the hazard rate of failure at any given moment in time. Of special relevance, this ratio exhibits a non-linear component. Other important variables explaining bank failure dynamics are profitability of assets and the ratio of non-performing loans to total loans. Leverage appears to affect the hazard rate also, but with lower statistical significance.
Economics Letters, 1983
A specification test based on an Edgeworth expansior is proposed and some of its useful propertie... more A specification test based on an Edgeworth expansior is proposed and some of its useful properties are noted. In particular the test has an important additivity property, in that a test for higher-order alternatives simply adds additional, asymptotically independent X2 variates to tests against lower order alternatives. July 1982.
Default is a rare event, even in segments in the midrange of a bank's portfolio. Inference ab... more Default is a rare event, even in segments in the midrange of a bank's portfolio. Inference about default rates is essential for risk management and for compliance with the requirements of Basel II. Most commercial loans are in the middle-risk categories and are to unrated companies. Expert information is crucial in inference about defaults. A Bayesian approach is proposed and illustrated using a prior distribution assessed from an industry expert. The method of All Likely Datasets, based on sufficient statistics and expert information, is used to characterize likely datasets for analysis. A check of robustness is illustrated with an epsilon-- mixture of priors.
This paper investigates the role of initial financial conditions (debt-to-asset ratio) on the dur... more This paper investigates the role of initial financial conditions (debt-to-asset ratio) on the duration of entrant firms. Previous literature has stressed productivity, size, and age effects on firm survival. Financial considerations, such as a firm's financing mix or its ability to raise capital, have largely been ignored by this literature. A unique ad-ministrative firm-level database of manufacturing firms called T2LEAP allows for the inclusion of financial balance sheet information into hazard rate models. The effect of the debt-to-asset ratio on the firm's hazard is economically and statistically significant while controlling for usual covariates and unobserved heterogeneity. Further, there is evidence of nonlinear effects in leverage's impact on hazard. Firms in the highest quintile of leverage see a negative impact of leverage on duration, while in the other quintiles the effect of leverage is positive.
Page 1. Page 2. EMPIRICAL LABOR ECONOMICS Page 3. Page 4. Empirical Labor Economics The Search Ap... more Page 1. Page 2. EMPIRICAL LABOR ECONOMICS Page 3. Page 4. Empirical Labor Economics The Search Approach THERESA J. DEVINE NICHOLAS M. KIEFER NewYork Oxford OXFORD UNIVERSITY PRESS 1991 Page 5. ...
A Bayesian approach to default rate estimation is used to predict default rates on the basis of i... more A Bayesian approach to default rate estimation is used to predict default rates on the basis of information from data and experienced industry experts. The principle advantage of the Bayesian approach is the potential for coherent incorporation of expert information crucial when data are scarce or unreliable. A secondary advantage is access to efficient computational methods such as Markov Chain Monte Carlo. The power of this approach is illustrated using annual default rate data from Moody’s (1999-2009) for two risk buckets and priors elicited from industry experts. Three structural credit models in the asymptotic single risk factor (ASRF) class underlying the Basel II framework (Generalized Linear and Generalized Linear Mixed Models), are analyzed using a Markov Chain Monte Carlo technique. The predictive distributions for defaults are obtained.
Incorporation of expert information in inference or decision settings is often important, especia... more Incorporation of expert information in inference or decision settings is often important, especially in cases where data are unavailable, costly or unreliable. One approach is to elicit prior quantiles from an expert and then to fit these to a statistical distribution and proceed according to Bayes rule. An incentive-compatible elicitation method using an external randomization is available.
The probability approach to uncertainty and modeling is applied to default probability estimation... more The probability approach to uncertainty and modeling is applied to default probability estimation. Default estimation for low-default portfolios has attracted attention as banks contemplate the requirements of Basel II.s IRB rules. Nicholas M. Kiefer proposes the formal introduction of expert information into quantitative analysis. An application treating the incorporation of expert information on the default probability is considered in detail.
Stochastically ordered random variables with given marginal distributions are combined into a joi... more Stochastically ordered random variables with given marginal distributions are combined into a joint distribution preserving the ordering and the marginals using a maximum entropy formulation. A closed-form expression is obtained. An application is in default estimation for different portfolio segments, where priors on the individual default probabilities are available and the stochastic ordering is agreeable to separate experts. The ME formulation allows an efficiency improvement over separate analyses.
This paper identifies the main bank specific determinants of time to failure during the financial... more This paper identifies the main bank specific determinants of time to failure during the financial crisis in Colombia using duration analysis. Using partial likelihood estimation, it shows that the process of failure of financial institutions during that period was not a merely random process; instead, it can be explained by differences in financial health and prudence existing across institutions. Among the relevant indicators that explain bank failure, the capitalization ratio appears to be the most significant one. Increases in this ratio lead to a reduction in the hazard rate of failure at any given moment in time. Of special relevance, this ratio exhibits a non-linear component. Other important variables explaining bank failure dynamics are profitability of assets and the ratio of non-performing loans to total loans. Leverage appears to affect the hazard rate also, but with lower statistical significance.
Uploads
Papers by Nicholas Kiefer