A new method, called Relevant Transformation of the Inputs Network Approach is proposed as a tool for model building. It is designed around flexibility (with nonlinear transformations of the predictors of interest), selective search within the range of possible models, out‐of‐sample forecasting ability and computational simplicity. In tests on simulated data, it shows both a high rate of successful retrieval of the data generating process, which increases with the sample size and a good performance relative to other alternative procedures. A telephone service demand model is built to show how the procedure applies on real data.
Under the Basel II Accord, banks and other Authorized Deposit-taking Institutions (ADIs) have to communicate their daily risk estimates to the monetary authorities at the beginning of the trading day, using a variety of Value-at-Risk (VaR) models to measure risk. Sometimes the risk estimates communicated using these models are too high, thereby leading to large capital requirements and high capital costs. At other times, the risk estimates are too low, leading to excessive violations, so that realised losses are above the estimated risk. In this paper we propose a learning strategy that complements existing methods for calculating VaR and lowers daily capital requirements, while restricting the number of endogenous violations within the Basel II Accord penalty limits. We suggest a decision rule that responds to violations in a discrete and instantaneous manner, while adapting more slowly in periods of no violations. We apply the proposed strategy to Standard & Poor's 500 Index and show there can be substantial savings in daily capital charges, while restricting the number of violations to within the Basel II penalty limits. Key words and phrases:Daily capital charges, endogenous violations, frequency of violations, optimizing strategy, risk forecasts, value-at-risk.JEL Classifications: G32, G11, G17, C53. 3 IntroductionThe Value-at-Risk (VaR) concept has become a standard tool in the exploding area of risk measurement and management. In brief, VaR is defined as an estimate of the probability and size of the potential loss to be expected over a given period. This concept has become especially important following the 1995 amendment to the Basel Accord, whereby banks and other Authorized Deposit-taking Institutions (ADIs) were permitted to use internal models to calculate their VaR thresholds (see Jorion (2000) for a detailed discussion of VaR). Consequently, the last few years have witnessed a growing literature comparing modelling approaches and implementation procedures to answer the question of how to measure VaR, with many research studies arguing in favour or against various VaR models.The amendment to the Basel Accord was designed to reward institutions with superior risk management systems. A back-testing procedure, whereby the realized returns are compared with the VaR forecasts, was introduced to assess the quality of the internal models. In cases where internal models lead to a greater number of violations than could reasonably be expected, given the confidence level, the ADI is required to hold a higher level of capital (see Table 1 in the Appendix for the penalties imposed under the Basel II Accord). If an ADI's VaR forecasts are violated more than 10 times in any financial year, the ADI may be required to adopt the 'Standardized' approach. The imposition of such a penalty is severe as it affects the profitability of the ADI directly through higher capital charges, has a damaging effect on the ADI's reputation, and may lead to the imposition of a more stringent external model to forecast the AD...
This paper analyzes the effect of educational mismatch on wages, using a rich panel dataset of workers in the major euro area countries from 2006 to 2009, drawn from the European Union Statistics on Income and Living Conditions (Eurostat). We use a consistent estimator to address the two econometric problems faced by the empirical literature: the omitted variable bias and measurement error. In principle, our fixed effect estimates confirm that overeducated workers suffer a wage penalty of similar magnitude to the return on each year of schooling attained. Interestingly, when we split the sample by age, we find that the wages of people aged under 35 basically depend on the level of education attained, while those of workers aged over 35 depend on job educational requirements. These results are interpreted taking into account the impact of the depreciation of skills on human capital. The main policy implication of the paper is that overeducation constitutes a waste of resources. Therefore public authorities should seek to reduce the negative impact of overeducation on the labor market. JEL classification: I21 J24 J31
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.