Switching regime models in the Spanish inter-bank market

Nonlinear present value models are adjusted to data from the Spanish inter-bank market between 1986 and 1992, with the ultimate objective of testing the rational expectations hypothesis of the term structure of the interest rates. The nonlinearity stems from using models with two stochastically switching regimes. The models are submitted to various specification tests and are compared with linear present value models. Very clearly differentiated regimes are identified, the analysis of the results in the light of the institutional, political and economic events that affected the Spanish economy during the period of study demonstrates the usefulness of this type of models. The expectation hypothesis is, however, rejected.     

Property value impacts of foreclosed housing acquisitions under uncertainty

Community development corporations seek to stabilize neighborhoods affected by the recent foreclosure crisis through acquisition and redevelopment of distressed properties. One rationale for this work is the alleviation or avoidance of negative foreclosure impacts. We estimate the lost value to proximate properties associated with a single foreclosure through a Markov chain representing probabilistic transitions between foreclosure stages. We apply our model to a case study of foreclosure properties in Chelsea, MA. A rank ordering by estimated property value impacts indicates significant potential gains in social value as compared to current community development practice. We extend our basic model to address the effects of clusters of foreclosed units upon the value of proximate properties. This study provides additional support for the use of decision modeling in foreclosed housing acquisition and redevelopment.     

On the Practice of Rescaling Covariates

Whether doing parametric or nonparametric regression with shrinkage, thresholding, penalized likelihood, Bayesian posterior estimators (e.g., ridge regression, lasso, principal component regression, waveshrink or Markov random field ), it is common practice to rescale covariates by dividing by their respective standard errors ρ. The stated goal of this operation is to provide unitless covariates to compare like with like, especially when penalized likelihood or prior distributions are used. We contend that this vision is too simplistic. Instead, we propose to take into account a more essential component of the structure of the regression matrix by rescaling the covariates based on the diagonal elements of the covariance matrix Σ of the maximum-likelihood estimator. We illustrate the differences between the standard ρ- and proposed Σ-rescalings with various estimators and data sets.     

供应链管理下基于供货不稳定的最优库存模型

针对供货环境的不稳定性,将t时刻系统所处的状态(是否能够供货)视为连续时间的马尔可夫链。在(s,S)存储策略下,利用两状态连续时间马尔可夫链的性质建立了一个新的存贮控制模型。在给定具体数值的基础上利用遗传算法对模型进行了检验计算,并对结果进行了对比分析。     

Additive cubic spline regression with Dirichlet process mixture errors

The goal of this article is to develop a flexible Bayesian analysis of regression models for continuous and categorical outcomes. In the models we study, covariate (or regression) effects are modeled additively by cubic splines, and the error distribution (that of the latent outcomes in the case of categorical data) is modeled as a Dirichlet process mixture. We employ a relatively unexplored but attractive basis in which the spline coefficients are the unknown function ordinates at the knots. We exploit this feature to develop a proper prior distribution on the coefficients that involves the first and second differences of the ordinates, quantities about which one may have prior knowledge. We also discuss the problem of comparing models with different numbers of knots or different error distributions through marginal likelihoods and Bayes factors which are computed within the framework of Chib (1995) as extended to DPM models by Basu and Chib (2003). The techniques are illustrated with simulated and real data.     

Regional disparity,transitional dynamics and convergence in China

Most of the earlier studies on the convergence of income in China are based on provincial level data with a few papers focusing on intra-provincial units’ transitional dynamics. The objective of this study is to fill the void in the literature by using county-level data which cover 1485 counties and county-level cities in 22 provinces for the period of 1997–2007. This paper makes several contributions to the literature. The findings in this paper show high persistence in income distribution among many spatial groupings. Thus the poor county-level units may remain relatively poor over time. This study provides very little evidence of convergence to the mean income in various spatial groupings. Furthermore, the empirical analysis highlights differences in transitional dynamics between cities and counties.     

A characterization of equilibria in the Groves–Ledyard mechanism

In this paper, we characterize all interior and boundary equilibria of the Groves–Ledyard mechanism for a large class of economies and determine their stability properties. We show that the mechanism admits three types of equilibria: a symmetric, efficient, stable interior equilibrium, a large set of asymmetric, efficient, unstable, interior equilibria, and a large set of asymmetric, inefficient, stable boundary equilibria. We further show that asymmetric equilibria fail to exist for large values of the punishment parameter or if the message space is bounded sufficiently. The boundary equilibria previously had not been located nor had the instability of the asymmetric equilibria been known. Interestingly, the stability of the symmetric equilibrium rests on two dynamics that individually produce instability.     

ORDINARY LEAST SQUARES LEARNING AND NONLINEARITIES IN MACROECONOMICS

Abstract.  The paper reviews the literature on adaptive learning in macroeconomic settings where the formation of expectations is particularly relevant. Special attention will be given to simple two-period overlapping generations models with a unique fixed point perfect foresight equilibrium; in this kind of scenario, eventual long-term periodic and a-periodic cycles are exclusively the result of the process of learning. The outcome that high rates of money growth have a potentially destabilizing effect generating periodic fluctuations and chaos is emphasized. The persistence of systematic forecast errors in a scenario where agents are supposed to act rationally is relevant in this context and it will be thoroughly discussed resorting to the notions of self-fulfilling mistakes, consistent expectations equilibria and beliefs equilibria.     

How Large is Congressional Dependence in Agriculture? Bayesian Inference about ‘Scale’ and ‘Scope’ in Measuring a Spatial Externality

The political economy literature on agriculture emphasises influence over political outcomes via lobbying conduits in general, political action committee contributions in particular, and the pervasive view that political preferences with respect to agricultural issues are inherently geographic. In this context, ‘interdependence’ in Congressional vote behaviour manifests itself in two dimensions. One dimension is the intensity by which neighbouring vote propensities influence one another, and the second is the geographic extent of voter influence. We estimate these facets of dependence using data on a Congressional vote on the 2001 Farm Bill using routine Markov chain Monte‐Carlo procedures and Bayesian model averaging, in particular. In so doing, we develop a novel procedure to examine both the reliability and the consequences of different model representations for measuring both the ‘scale’ and the ‘scope’ of spatial (geographic) co‐relations in voting behaviour.     

Structural transformation and smallholder agriculture: an information‐theoretic analysis of the Nicaraguan case

In light of continued debate regarding the capacity of small‐scale agricultural producers to compete amidst globalization and/or liberalization, we examine recent trends in the distribution and use of agricultural landholdings in developing nations via refined exploration of the Nicaraguan case. With nationally‐representative, Living Standards Measurement Survey‐type data for the years 1998, 2001, and 2005, we employ Markov chain methods within an information‐theoretic framework in an attempt to advance the analysis of structural transformation in developing countries beyond the examination of trends in mean farm sizes or Gini coefficients, approaches ill‐suited to the detection of the apparent complexities of structural change. Further, while Markov chain analysis has witnessed relatively widespread application in the investigation of structural transformation in developed nations, we offer a novel methodological extension by allowing for the simultaneous exploration of structural transformation across multiple dimensions–namely, structural change in both the distribution and use of agricultural landholdings—as well as the incorporation of microlevel determinants of farm size and land use change. The results of the inquiry, above all, suggest that Nicaragua's agricultural and livestock sector is characterized by a definitive persistence of smallholders. While a moderate tendency toward bifurcation in the distribution of landholdings would appear to obscure any immediate relationship between operational landholdings and land productivity, we contend that such trends are, in fact, consistent with the often observed inverse farm size‐productivity relationship.