Maximum likelihood estimation of a generalized star(p; 1p) model

Summary A STAR model is characterized by autoregressive terms lagged both in time and space. The model we call GSTAR presents also contemporaneous spatial correlation. Under the hypothesis of stationarity we derive conditional maximum likelihood estimators of the autoregressive parameters and a consistent estimator of their covariance matrix.     

Great Expectatrics: Great Papers,Great Journals,Great Econometrics

The article discusses alternative Research Assessment Measures (RAM), with an emphasis on the Thomson Reuters ISI Web of Science database (hereafter ISI). Some analysis and comparisons are also made with data from the SciVerse Scopus database. The various RAM that are calculated annually or updated daily are defined and analyzed, including the classic 2-year impact factor (2YIF), 2YIF without journal self-citations (2YIF*), 5-year impact factor (5YIF), Immediacy (or zero-year impact factor (0YIF)), Impact Factor Inflation (IFI), Self-citation Threshold Approval Rating (STAR), Eigenfactor score, Article Influence, C3PO (Citation Performance Per Paper Online), h-index, Zinfluence, and PI-BETA (Papers Ignored – By Even The Authors). The RAM are analyzed for 10 leading econometrics journals and 4 leading statistics journals. The application to econometrics can be used as a template for other areas in economics, for other scientific disciplines, and as a benchmark for newer journals in a range of disciplines. In addition to evaluating high quality research in leading econometrics journals, the paper also compares econometrics and statistics, alternative RAM, highlights the similarities and differences of the alternative RAM, finds that several RAM capture similar performance characteristics for the leading econometrics and statistics journals, while the new PI-BETA criterion is not highly correlated with any of the other RAM, and hence conveys additional information regarding RAM, highlights major research areas in leading journals in econometrics, and discusses some likely future uses of RAM, and shows that the harmonic mean of 13 RAM provides more robust journal rankings than relying solely on 2YIF.     

基于Monte Carlo模拟的STAR模型样本矩性质研究

采用Monte Carlo模拟方法对STAR模型样本矩的统计特性进行研究。分析结果表明:STAR模型的样本均值、样本方差、样本偏度及样本峰度都渐近服从正态分布;即使STAR模型的数据生成过程中不含有常数项,其总体均值可能也不是0,这与线性ARMA模型有显著区别;即使STAR模型数据生成过程中的误差项服从正态分布,数据仍有可能是有偏分布。     

Identifying Social Interactions Through Conditional Variance Restrictions

This paper proposes a new method for identifying social interactions using conditional variance restrictions. The method provides a consistent estimate of the social multiplier when social interactions take the “linear‐in‐means” form (Manski (1993)). When social interactions are not of the linear‐in‐means form, the estimator, under certain conditions, continues to form the basis of a consistent test of the no social interactions null with correct large sample size. The methods are illustrated using data from the Tennessee class size reduction experiment Project STAR. The application suggests that differences in peer group quality were an important source of individual‐level variation in the academic achievement of Project STAR kindergarten students.     

非线性视角下蔬菜市场价格的波动特征——基于STAR模型

基于非线性视角下的蔬菜价格波动特征研究能够有效捕捉到蔬菜价格的非线性调整过程,从而有助于进一步完善蔬菜价格的波动机制。以大宗蔬菜中的大白菜、黄瓜、四季豆为例,选取2002年1月到2013年9月的全国集贸市场价格数据,对蔬菜市场价格的非线性动态调整过程进行了分析。研究表明：蔬菜价格具有非线性波动特征,存在机制之间的平滑转换过程,门限值是其转换的转折点,可以作为国家调控蔬菜市场价格异常波动的重要依据;蔬菜前期市场价格是发生非线性波动的一个潜在的重要变量,因此有必要加强对蔬菜市场价格的监控和分析;从3类蔬菜价格的函数形式、转换速率以及门限值来看,蔬菜市场内部的异质性明显。     

STAR模型的滞后阶数选择与稳健性研究

本文讨论了六种信息准则在STAR模型滞后阶数选择中的适应性及稳健性问题。Monte Carlo模拟结果显示,在多数情况下,数据生成过程中的误差项分布并不影响信息准则正确识别模型最大滞后阶数的能力;对于短STAR模型,ACC准则具有较高的正确识别率,并且对不同平滑转移系数及不同门限值具有很好的稳健性;而对于长STAR模型,SC准则及ACC准则具有更高的正确率及良好的稳健性。     

Robust Bayesian inference in STAR models with neighbourhood effects

In this paper we propose a robust Bayesian procedure of estimation, testing, validation and selection of spatio-temporal autoregressive models (STAR) with neighbourhood effects applied to the appraisal of dwelling prices. The methodology does not depend on asymptotic results and, unlike previously procedures proposed in the literature, takes into account the uncertainty associated to the estimation of the neighbourhood parameters of the model, giving more realism to the analysis. Moreover, a sequential algorithm to elaborate fast on-line forecast, is provided. The methodology is illustrated by means of a practical case of the real estate market of Zaragoza.     

Economic and social inclusion of person with disability and transgender through skills development program of BRAC: A qualitative study

This article is based on the Skills Training for Advancing Resources (STAR) project for the youth initiative of the Bangladesh Rural Advancement Committee (BRAC) in Bangladesh. The objective was to explore the consequences of social and economic inclusion of this project for the persons with disability (PWDs) and transgender (TG) youth people. The research focused on how inclusive programmatic interventions created multidimensional impacts among the “marginalized” and “excluded” PWD and TG youths at the grassroots level. This study adopted a qualitative approach where in-depth case interviews and observation were applied for data collection. PWD and TG graduates, master craft persons (MCPs), employers, and program staff members were the participants in this study. Results found that PWD and TG youths faced vulnerabilities and social stigma in their lives and livelihood trajectories due to their physical inability and low level of social dignity. The STAR project has a certain level of contribution to the livelihoods of PWD and TG people, where these helped them to gain their social, cultural, and economic capital. Findings would be an important guideline for policymakers, NGO managers, and human rights workers.     

STAR模型中退势单位根检验的小样本性质研究

 Kapetanios et al. (2003)和刘雪燕(2008)提出了ESTAR和LSTAR模型单位根检验的方法。本文将时间序列退势的OLS和GLS方法与他们提出的单位根检验方法结合,通过蒙特卡洛试验发现,在STAR模型中,对时间序列退势能不同程度的改善单位根检验的功效。若时间序列只存在非零均值,ESTAR模型中OLS退势存在优势;LSTAR模型,样本容量较小时（T<=50）,OLS退势的优势较明显,样本容量较大（T>100）时,GLS退势具有了微弱的优势。若序列存在非零的均值和趋势,且样本容量较小时,LSTAR模型中GLS退势的优势较明显,ESTAR模型中OLS退势的优势较明显;样本容量较大时,LSTAR模型中二者功效都很高,ESTAR模型中GLS退势的优势较明显。     

Bayesian inference for smooth transition autoregressive (STAR) model: A prior sensitivity analysis

The main aim of this paper is to perform sensitivity analysis to the specification of prior distributions in a Bayesian analysis setting of STAR models. To achieve this aim, the joint posterior distribution of model order, coefficient, and implicit parameters in the logistic STAR model is first being presented. The conditional posterior distributions are then shown, followed by the design of a posterior simulator using a combination of Metropolis-Hastings, Gibbs Sampler, RJMCMC, and Multiple Try Metropolis algorithms, respectively. Following this, simulation studies and a case study on the prior sensitivity for the implicit parameters are being detailed at the end.