Model uncertainty and aggregated default probabilities: new evidence from Austria

Understanding the determinants of aggregated corporate default probabilities (PDs) has attracted substantial research interest over the past decades. This study addresses two major difficulties in understanding the determinants of aggregate PDs: model uncertainty and multicollinearity among the regressors. We present Bayesian model averaging (BMA) as a powerful tool that overcomes model uncertainty. Furthermore, we supplement BMA with ridge regression to mitigate multicollinearity. We apply our approach to an Austrian data set. Our findings suggest that factor prices like short-term interest rates (STIs) and energy prices constitute major drivers of default rates, while firms’ profits reduce the expected number of failures. Finally, we show that the results of our model are fairly robust with respect to the choice of the BMA parameters.     

Kalman filtering as an alternative to Ordinary Least Squares — Some theoretical considerations and empirical results

The purpose of this paper is to highlight the superiority of the Kalman filter over Ordinary Least Squares for estimating the unknown coefficients of the classical linear regression model. Both methods are analyzed with respect to their optimality properties and their usefulness in dealing with multicollinearity. Theoretical results are applied to two economic models.     

Gini-PLS Regressions

Journal of Quantitative Economics - Data contamination and excessive correlations between regressors (multicollinearity) constitute a standard and major problem in econometrics. Two techniques...     

An Index Number Method for Estimating Scale Economies and Technical Processes Using Time-series of Cross-section Data: Sources of Total Factor Productivity Growth for Japanese Manufacturing, 1964–1988

Sample multicollinearity often makes it difficult to estimate returns to scale. We present an index number method to overcome potential multicollinearity problems when the production function is homogeneous of degree k . We apply our method to estimate empirically the effects of returns to scale and technical progress on growth in total factor productivity (TFP) using establishment data for Japanese manufacturing industries. We find that, while significant scale economies exist in many manufacturing industries, the TFP growth in the last twenty-five years is attributable primarily to technical progress. This finding also validates the current practice of assuming constant-returns-to-scale production functions in macroeconometric modelling.
JEL Classification Numbers: C43, D24, 030.     

Use of the principal component method in the maximum likelihood estimation procedure of the logit model

The maximum likelihood estimates of a qualitative response market are solved by an iterative procedure. When severe multicollinearity exists among the explanatory variables, this procedure may fail to converge. In this note, using a bank-failure model, we demonstrate how the principle component method can make the iterative procedure converge when it fails to do so in the untransformed model.     

Economic freedom and growth. Which policies matter the most?

Empirical studies provide evidence that economic freedom, as measured by the Economic Freedom of the World Index, is related to economic growth. None the less, identifying which aspects of economic freedom are more conducive to growth has proven difficult, due to multicollinearity among the index areas. A possible explanation is that certain countries score high in all areas, whereas others tend do bad in all of them, simply because the former are more freedom-friendly than the latter. However, it is also true that each country presents a combination of freedoms, and restrictions to freedom, at the level of the individual indicators that make up each area. If some regularity exists with respect to these combinations, empirical detection of the most popular policy combinations would alleviate the collinearity problem, when assessing growth effects. Our article explores this possibility by means of cluster analysis, which we conduct at the individual indicator level. We show that multicollinearity can indeed be reduced in this way and identify policy packages that seem to be more conducive to economic growth than others. Results further indicate that certain policy packages may have only a short-term effect on growth, whereas others seem to have an enduring one.     

上市公司财务危机预警实证研究

从20世纪60年代起,国内外的学者对上市公司财务危机预警问题就进行了大量研究,从方法上看,主要有线性判别分析、多元线性回归分析和Logistic三种,大量的实践证明,运用Logistic模型判定上市公司财务危机预警的准确性相对较高。     

外商直接投资行业间技水溢出效应实证分析

文章选取1999~2003年的行业层面板数据，考察了FDI对中国工业部门内资企业生产率的影响。在考虑了多重共线性问题并控制住不可观测的时间效应和行业效应之后，研究结果显示，FDI产生了显著的行业内溢出和前向联系溢出，但后向联系溢出为负。此外，对技术差距最优区间的分析表明，当内资企业生产率为相应外资企业生产率的30％～70％时，前向联系溢出能实现最大化。     

我国保险业区域发展失衡的实证研究:基于保险密度的视角

本文建立了识别我国省际保险业发展影响因素的多元线性模型和识别我国省际保险业发展失衡成因的多元离差模型并运用格兰杰因果检验和逐步回归法为模型选择了最优的解释变量。除相关关系外,保证变量间还存在因果关系,并降低了解释变量间的共线性。实证结果表明,经济发展是推动我国省际保险业发展的根本动力,省际保险业发展失衡的主要原因是经济发展水平的差异,而不是社会文化环境和法律环境的差异。     

GIS-Based Hedonic Pricing of Landscape

Hedonic prices of landscape are estimated in the urban fringe of Dijon (France). Viewshed and its content as perceived at ground level are analyzed from satellite images supplemented by a digital elevation model. Landscape attributes are then fed into econometric models (based on 2,667 house sales) that allows for endogeneity, multicollinearity, and spatial correlations. Results show that when in the line of sight, trees and farmland in the immediate vicinity of houses command positive prices and roads negative prices; if out of sight, their prices are markedly lower or insignificant: the view itself matters. The layout of features in fragmented landscapes commands positive hedonic prices. Landscapes and features in sight but more than 100–300~m away all have insignificant prices.     

On Liu estimators for the logit regression model

This paper introduces a shrinkage estimator for the logit model which is a generalization of the estimator proposed by Liu (1993) for the linear regression. This new estimation method is suggested since the mean squared error (MSE) of the commonly used maximum likelihood (ML) method becomes inflated when the explanatory variables of the regression model are highly correlated. Using MSE, the optimal value of the shrinkage parameter is derived and some methods of estimating it are proposed. It is shown by means of Monte Carlo simulations that the estimated MSE and mean absolute error (MAE) are lower for the proposed Liu estimator than those of the ML in the presence of multicollinearity. Finally the benefit of the Lie estimator is shown in an empirical application where different economic factors are used to explain the probability that municipalities have net increase of inhabitants.     

中国基础设施投资的最优规模与最优次序——基于1996-2008年各省市地区面板数据分析

本文克服各项基础设施同时回归导致的多重共线性问题,基于基础设施的边际产出与最优规模分析框架,采用中国1996-2008年各省市地区面板数据实证研究发现:中国电力、燃气和水的生产与供应业、交通运输、仓储和邮电通信业、水利、环境和公共设施管理业等各项基础设施和政府总投资的边际产出分别为5.765、2.520、1.420和1.276;最优规模分别为4.66%、3.29%、5.02%和20.95%;各项基础设施的实际投资均低于最优规模。因此,为使政府投资收益最大化可按边际产出大小顺序优先次序投资;而根据各项基础设施投资的缺口和紧迫程度,则应按实际投资与最优规模差距由大到小顺序进行投资。     

基于技术进步的浙江省能源消费回弹效应研究

基于技术进步对经济增长的贡献和环境负荷分解模型,对浙江省1990年以来技术进步对GDP增长的贡献、能源消费回弹效应及能源回弹量进行实证分析。其中,对技术进步的测定采用城镇单位在岗职工工资总额和农村居民纯收入作为劳动因素,以期更合理地体现劳动对经济增长的贡献,同时对多元回归模型的多重共线性进行滞后差分变换,以期得到更为精确的实证数据。     

中国区域自主创新能力影响因素计量分析

提高自主创新能力,建立创新型国家已经成为我国的基本战略。针对国内外学者对于区域自主创新能力影响因素的归纳和总结,建立区域创新能力影响因素的概念模型,并且结合我国2007年科技年鉴数据对这些因素进行计量分析,综合考虑了数据量纲问题、异方差问题和多重共线性的影响,通过模型的检验,最终确立了影响我国区域自主创新能力因素的计量经济学模型,通过对模型结果的分析为提升我国区域自主创新能力提供一定的政策借鉴。     

REPLY TO SIEGEL ET AL.: ALCOHOL ADVERTISING IN MAGAZINES AND DISPROPORTIONATE EXPOSURE

Nelson investigated advertising placements for a diverse sample of 28 magazines and concluded that targeting of underage youth by alcohol advertisers was not occurring. Siegel et al. claim that my results suffer from collinearity, but fail to present a comprehensive measure of multicollinearity. For my model, variance inflation factors are within acceptable limits and estimation using redefined variables does not alter my prior results or conclusion. Further, Siegel et al.'s empirical results are fragile and do not support a targeting outcome. I also discuss the limitations of estimates of magazine readerships and the shortcomings of the public health literature on advertising and youth alcohol behaviors. Neither the empirical results in Siegel et al. nor their literature citations support a public policy based on a simple rule of disproportionate exposure. ( JEL L82, L66, M37)     

Implicit returns on conventional demand deposits: An empirical comparison

This paper compares the relative performance of alternative series of implicit returns on conventional demand deposits by estimating for each series a set of equations derived from a generalized CES utility model for a liquid asset portfolio. This approach offers the unique advantage of explaining money holdings with a substantially larger number of degrees of freedom than originally available, while avoiding multicollinearity even in the presence of several interest rate variables in the model. An implicit return series obtained by Barro and Santomero (1972) performs the best among all of the available seven series tested based on the criteria of a generalized measure of goodness-of-fit and a robustness of coefficient estimates.     

On ridge estimators for the negative binomial regression model

The negative binomial (NB) regression model is very popular in applied research when analyzing count data. The commonly used maximum likelihood (ML) estimator is very sensitive to highly intercorrelated explanatory variables. Therefore, a NB ridge regression estimator (NBRR) is proposed as a robust option of estimating the parameters of the NB model in the presence of multicollinearity. To investigate the performance of the NBRR and the traditional ML approach the mean squared error (MSE) is calculated using Monte Carlo simulations. The simulated result indicated that some of the proposed NBRR methods should always be preferred to the ML method.     

关于PM2.5的统计学分析

通过计量经济学分析研究使得PM2.5值达到最低的影响因素最优组合方案。以SAS方程拟合与正交试验设计的理论方法为工具,选择PM2.5为研究对象,先用SAS拟合方程,并检验序列相关性、多重共线性以证明所拟合方程的可用性。再用正交试验设计的直观分析法确定因素水平的最优组合方案,通过用正交试验设计的方差分析法讨论因素的显著性,以确定最优组合即让PM2.5的值达到最低。     

RIDGE ESTIMATORS FOR PROBIT REGRESSION: WITH AN APPLICATION TO LABOUR MARKET DATA

In this paper we propose ridge regression estimators for probit models since the commonly applied maximum likelihood (ML) method is sensitive to multicollinearity. An extensive Monte Carlo study is conducted where the performance of the ML method and the probit ridge regression (PRR) is investigated when the data are collinear. In the simulation study we evaluate a number of methods of estimating the ridge parameter k that have recently been developed for use in linear regression analysis. The results from the simulation study show that there is at least one group of the estimators of k that regularly has a lower mean squared error than the ML method for all different situations that have been evaluated. Finally, we show the benefit of the new method using the classical Dehejia and Wahba dataset which is based on a labour market experiment.     

A Poisson ridge regression estimator

The standard statistical method for analyzing count data is the Poisson regression model, which is usually estimated using maximum likelihood (ML) method. The ML method is very sensitive to multicollinearity. Therefore, we present a new Poisson ridge regression estimator (PRR) as a remedy to the problem of instability of the traditional ML method. To investigate the performance of the PRR and the traditional ML approaches for estimating the parameters of the Poisson regression model, we calculate the mean squared error (MSE) using Monte Carlo simulations. The result from the simulation study shows that the PRR method outperforms the traditional ML estimator in all of the different situations evaluated in this paper.