Forecasting with univariate TAR models

The forecasting stage in the analysis of a univariate threshold-autoregressive model, with exogenous threshold variable, has been developed in this paper via the computation of the so-called predictive distributions. The procedure permits one to forecast simultaneously the response and exogenous variables. An important issue in this work is the treatment of eventual missing observations present in the two time series before obtaining forecasts.     

A Note on Trend Decomposition: The 'Classical' Approach Revisited with an Application to Surface Temperature Trends

This note reconsiders the 'classical' approach to trend estimation and presents a modern treatment of this technique that enables trend filters which incorporate end-effects to be constructed easily and efficiently. The approach is illustrated by estimating recent Northern Hemispheric temperature trends. In so doing, it shows how classical trend models may be selected in empirical applications and indicates how this choice determines the properties of the latest trend estimates.     

An Examination of the Commerce Department Leading-lndicator Approach

Bivariate time series models are built that describe the empirical relationships between industrial production and components of the Composite Index of Leading Indicators (CLI). This reveals the indicators' average lead times at all points of the business cycle, the forms of the distributed lags involved, and their ability to explain later movements in economic activity. The relationship between industrial production and the CLI is also examined and used to test the contribution of the CLI toward improving time series model forecasts of the 1980 and 1981 recessions.     

Leading Indicators for the Service Sector

Since the service sector currently accounts for a large and growing share of U.S. economic activity, we have undertaken to develop indicators that throw light on its current status and future prospects. A composite coincident index of aggregate economic activity in the service sector is constructed, and a growth-cycle chronology is identified based on growth rates in this index and in its components. Then several macroeconomic leading indicators of service are identified, and from them a composite leading index is constructed. The growth rate in this index is found to give advance warnings of major swings in the growth of the service sector.     

R2 Bounds for Predictive Models: What Univariate Properties Tell us About Multivariate Predictability

ABSTRACT

A long-standing puzzle in macroeconomic forecasting has been that a wide variety of multivariate models have struggled to out-predict univariate models consistently. We seek an explanation for this puzzle in terms of population properties. We derive bounds for the predictive R² of the true, but unknown, multivariate model from univariate ARMA parameters alone. These bounds can be quite tight, implying little forecasting gain even if we knew the true multivariate model. We illustrate using CPI inflation data. Supplementary materials for this article are available online.     

我国高校绩效管理研究现状、问题与发展趋势

绩效管理已日渐成为高校人力资源管理的研究热点,本文通过我国高校绩效管理目前研究的三个层面、两个方向和几个关键问题等,对目前研究现状进行阐述,发现存在的一些问题,并预见我国高校绩效管理研究未来的发展趋势。     

近年来我国学前融合教育研究综述

当前，学前融合教育已经成为国际学前特殊教育的发展趋势。文章探讨了近年来我国学前融合教育的研究内容，分析了我国学前融合教育目前存在的现状，以期对今后开展学前融合教育有所启发。     

Econometric Analysis of Costing System Components in Rail Rate Regulation

In response to Congressional directive, the Interstate Commerce Commission (ICC) has created a railroad costing system that includes as key components ratios designed to estimate variable costs associated with freight transportation. The estimated variability ratios are used to determine freight surcharges, jurisdictional threshold rates, and basic rail rates in administrative law and federal court proceedings. In this article we assess the quality and reliability of the estimated variability ratios and their components against standards from economic theory and statistical theory and practice. Our work includes reproduction of the naive ICC regressions, updated naive regressions for the latest data set, estimation based on more secure econometric foundations, and sensitivity analyses comparing alternative estimation procedures. Fundamental questions arise concerning the scientific and evidentiary standards that are required for econometric methodology in policy making and regulatory activities.     

国务院机构改革趋势分析

中国的政治体制改革主要集中在党政关系、党和国家领导制度和政府管理体制三个方面。在近三十年的政府机构改革中,国务院机构改革,作为改革的先导和指引,一直是人们关注的焦点。国务院机构在2030年之前,既不会按照精简——膨胀——再精简的模式循环下去,也不会按照企业型政府范式逐步成为一个＂小政府＂,而是保持较平稳的态势,同时,社会管理和公共服务方面的职能会进一步加强。     

Analysis of the Car Accident Indexes in Spain: A Multiple Time Series Approach

The main objective of this article is to specify and estimate a model for the car accident rates in Spain to improve input for the decision-making process for insurance companies and provide useful information for traffic authorities. The prediction performance of the model is also analyzed in an attempt to verify the improvement in prediction that takes place when more elaborate models are used.