住房需求和住房供给——基于多重多元回归、分位数回归方法

利用因子分析、多重多元回归和分位数回归方法研究了全国房地产行业的住房需求和住房供给,结果表明房价与住房需求和供给均呈正相关关系,并随着分位数的不同而变化,房价对住房需求的影响比对住房供给的影响大而显著等,并提出了一些建议,为有关部门制定相关政策提供依据。     

Shareholdings of Board Members and Corporate Performance: A Panel Quantile Regression Analysis

This paper investigates the impact of board member shareholdings on corporate performance in China and Taiwan, and employs unbalanced panel data over the period 2005–2009. In view of the inconsistent empirical findings in the literature and the limitations of least squares regressions, this study adopts a quantile regression method including fixed effects (FE) models. An important finding is that a significant, positive relationship exists between the shareholdings of board members and accounting measures of performance, and this relationship only exists for the more profitable firms in China, while a uniformly significant and positive relationship exists across all quantiles between the shareholdings of board members and accounting measures of performance in Taiwan. These findings, which cannot be obtained using a FE model, suggest that board members can influence firm performance through holding shares in most Taiwan firms and profitable Chinese firms.     

Export Intensity and Plant Characteristics: What Can We Learn from Quantile Regression?

Using quantile regression and a rich cross section data set for German manufacturing plants this paper documents that the impact of plant characteristics on export activities varies along the conditional size distribution of the export/sales ratio. For example, firm size is statistically significant at a conventional level for the 0.25 quantile only; branch plant status matters at the upper tail of the conditional distribution of the export/sales ratio only; the craft shop dummy is only significant for the very top quantile; and patents do not matter at the very lower end of the conditional distribution of export over sales. This has implications both for understanding what makes a successful exporter, and for the design of policy measures with a focus on supporting exporters. JEL no. F10, D21, L60     

基于分位数回归法的安徽省粮食产量影响因素分析

首先利用滤波分析对改革开放以来安徽省粮食安全的相关数据进行处理,根据粮食产量的变化特征将其划分为两个阶段,接着利用分位回归模型对各阶段影响粮食总产量的各分位数进行因素分析,更为细致和深入地研究了粮食总产量及其影响因素之间的回归关系,最后依据模型分析的结果,对安徽省增加粮食产量提出了相应的政策建议。     

Regional Disparity in the Body Mass Index Distribution of Indonesians: New Evidence Beyond The Mean

This article studies the differentials in body mass index (BMI) across the distribution of Indonesian people in urban and rural regions, using the latest wave of the Indonesia Family Life Survey. Besides the mean difference decomposition, this study implements a quantile decomposition analysis and decomposes the differentials between rural and urban populations at various quantile points of the distributions. This study offers new evidence of the substantial heterogeneity of their determinants and their impacts across the distribution, which has been overlooked in the literature. Physical activities explain the distributional differentials across the distribution for men and women, and their relative contribution sizes are larger at the higher quantiles. The significance of the structural effect of food expenditure and choices is observed at the middle and higher quantile points of the female distribution. This article shows the importance of analysing distributional differences by elucidating the heterogeneity of the effects of determinants.     

长三角外商直接投资对工业经济增长影响的实证分析

文章利用长三角地区2004年经济普查中类行业的截面数据,采用普通最小二乘法（OLS）和分位数回归法（Quantile Regress）研究了该地区外商直接投资对于工业经济增长的影响,在控制人力资本和市场竞争度之后,实证结果表明外商直接投资对于长三角地区的工业经济增长显著正相关,即FDI总的溢出效应为正,同时更富有竞争力的市场也有利于工业总产值的提高。通过长三角地区内部的比较分析得出,上海利用FDI的溢出效应为负,江苏利用FDI的溢出效应为正且不显著,浙江的FDI则具有显著正的溢出效应。     

基于分位回归模型的西部上市公司资本结构研究

利用我国西部上市公司的数据,运用分位回归模型研究资本结构的各类影响因素,与OLS回归结果相对照,可以发现公司规模、股本结构、资产担保价值、非债务税盾和收益性等因素对处于资本结构不同分位的公司的非对称性影响,从而丰富了对资本结构影响因素的理解。     

高新技术企业认定政策对企业创新的激励效应——基于河北省高新技术企业的实证研究

国家“十四五”规划将创新确定为现代化全局建设的核心地位,而高新技术企业认定是政府激励企业创新的重要政策,但该政策是否达到预期效果尚需要实证检验。因此,以河北省高新技术企业为样本,使用分位数回归和门限回归重点研究高新技术企业认定对企业创新的激励效应。研究结果表明：高新技术企业认定政策可以通过税收减免、现金奖励和政治背书等途径显著激励企业的创新积极性;对创新投入水平较低企业的创新积极性影响更显著;相较于大规模企业,该政策更能促进中小规模企业的创新。     

基于半参数分位数回归模型的服务业发展水平影响因素研究

利用2020年全国329个地级市相关统计数据,建立半参数分位数回归模型,研究地区经济发展水平、城镇化率、政府作用、收入水平对不同发展水平的服务业影响效应。研究表明：地区经济发展水平与收入水平对各层次服务业发展均具有显著正向作用,但收入水平的促进作用会随着服务业发展水平的提高而减弱;城镇化率处于65%～80%时,对服务业具有逐步增强的促进作用;政府作用在促进服务业增长方面促进作用较弱。     

西安市空气质量影响因素的分位数回归分析

空气质量无论对经济的发展还是人体的健康都尤为重要。以大气中PM2.5浓度的变化为研究对象,采用逐步回归的方法对PM2.5影响最严重和最显著的因素进行筛选,利用这些因素构建普通多元线性回归模型和线性分位数回归模型来研究PM2.5浓度,全面细致地探究气象因素和污染物排放因素对西安市PM2.5浓度的影响,分析了普通多元线性回归模型和线性分位数回归模型不同分位点自变量对因变量的影响大小以及显著性特点,得出影响因素在不同分位点上的变化趋势。     

Does Financial Intermediation Development Increase Per Capita Income in Rural China？

This paper investigates the impacts of financial intermediary （or banking） development on village-level per capita income using a Chinese dataset for selected years between 1993 and 2006. The empirical results from a random effect regression model indicate that mean per capita income in rural villages follows an inverted U-shaped path as financial intermediation develops. However, using a pooled quantile regression approach, we find that median per capita income in rural villages follows a positive linear path, rather than an inverted U-shaped path, as financial intermediation develops. The positive linear effect of financial intermediary development is observed at the lower and higher ends of the conditional per capita income distribution. This suggests that development of financial intermediation in China might not have statistically significant differential effects in low-income or high-income rural villages.     

创新投入对高技术产业集聚的影响研究——基于分位数回归的实证分析

通过构建2007-2018年省域面板数据分位数回归模型,分析创新投入对高技术产业集聚的影响。结果表明：创新投入整体上对高技术产业集聚有显著地促进作用,且对东部地区的影响大于中、西部地区。在高技术产业集聚水平从低向高变化的过程中,创新投入对高技术产业集聚的影响呈显著递增趋势,并存在明显的区域差异：对东部地区的影响呈先升后降的“倒U型”分布;对中、西部地区的影响总体呈递增趋势,且中部地区的不如西部地区显著。     

证券投资基金收益概率密度预测——基于神经网络分位数回归模型

证券投资基金收益往往具有更高的峰度与更大的偏度,建立在古典假定基础上的均值回归分析难以给出准确预测结果。考虑到证券投资基金收益中的高峰、非对称等典型特征与各因素对收益序列的非线性影响模式,建立神经网络分位数回归模型,一方面,可以通过分位数回归功能,揭示各因素对证券投资收益整个条件分布的影响规律;另一方面,可以通过神经网络结构,模拟金融系统中的非线性关系。在神经网络分位数回归模型基础上,对证券投资基金收益整个条件密度函数进行预测,提供比点预测更多的有用信息,便于进行科学决策。     

中国省际保险业发展影响因素分析——基于2006-2009年的面板数据实证分析

本文运用固定效应回归模型,对中国省域的保险业发展进行了计量分析。研究结果表明:中国31个省域的保险业发展差距显著,各省域保险业的发展主要受到地区经济发展水平、物价水平、人均收入状况、教育水平和就业状况等因素的影响,并且这些因素对保险业的发展都有着显著的作用。其中GDP,DPI,受教育水平对保险业的发展有显著的正向作用,物价水平及非国有企业职工数与国有企业职工人数比对保险业发展有负面作用。     

共同富裕背景下父母受教育程度对子代收入的影响——基于CGSS2017年调查数据

以 CGSS（中国综合社会调查）2017年的微观数据为基础,分析父母受教育程度对子代收入的影响,同时考察子代受教育程度的中介作用。研究发现：父母受教育程度对子代收入有显著正向增收效应,且父亲的影响程度低于母亲;父母受教育的不平等会进一步加大子代收入差距;在父母受教育程度对子代收入的影响中,城镇、女性和东西部地区更为显著;子代受教育程度在父母受教育程度对子代的增收效应中存在部分中介作用。     

A likelihood-Based Approximate Solution to the Incidental Parameter Problem in Dynamic Nonlinear Models with Multiple Effects

Abstract

We discuss a modified objective function strategy to obtain estimators without bias to order 1/T in nonlinear dynamic panel models with multiple effects. Estimation proceeds from a bias-corrected objective function relative to some target infeasible criterion. We consider a determinant-based approach for likelihood settings, and a trace-based approach, which is not restricted to the likelihood setup. Both approaches depend exclusively on the Hessian and the outer product of the scores of the fixed effects. They produce simple and transparent corrections even in models with multiple effects. We analyze the asymptotic properties of both types of estimators when n and T grow at the same rate, and show that they are asymptotically normal and centered at the truth. Our strategy is to develop a theory for general bias-corrected estimating equations, so that we can obtain asymptotic results for a specific bias correction method using the first-order conditions.