Important considerations in using statistical procedures to control for nuisance variables in non-experimental studies

In this paper, it is argued that the effects of statistically controlling for confounding variables in non-experimental studies have received insufficient attention. One of the reasons for this inattention is likely because many researchers do not fully appreciate what a statistical control strategy entails and how the use of such a strategy can affect the hypotheses actually tested in a study. In order to address these issues, this article (a) considers what the use of statistical control entails computationally, (b) reviews studies in which researchers have focused on the unique variance added by a predictor in testing a hypothesis, and (c) shows how this practice is not always sufficient for understanding research results.     

Influences on strategic decision effectiveness: Development and test of an integrative model

This paper draws upon three broad perspectives on the strategic decision‐making process in order to develop a more completely specified model of strategic decision effectiveness in a different context, namely Egypt. The key variables in this model consist of three strategic decision‐making process dimensions (rationality, intuition, and political behavior); seven moderating variables concerning decision‐specific, environmental, and organizational factors; and strategic decision effectiveness as an outcome variable. A two‐stage study was conducted in which the first stage provided exploratory insights and the second stage investigated hypotheses on the impact of strategic decision‐making process dimensions on strategic decision effectiveness and the moderating role of broader contextual variables. The second‐stage study produced three major findings: (1) both rational and political processes appear to have more influence on strategic decision effectiveness than does intuition; (2) strategic decision effectiveness is both process‐ and context‐specific; and (3) certain results support the ‘culture‐free’ argument, while others support the ‘culture‐specific’ argument. Copyright © 2007 John Wiley & Sons, Ltd.     

Returns to schooling in Kazakhstan

This paper examines rates of return to schooling in Kazakhstan using OLS (Ordinary Least Squares) and instrumental variable (IV) methodologies. We use spouse's education and smoking as instruments. We find that spouse's education is a valid instrument and that conventional OLS estimates that assume the exogenous nature of schooling, and hence do not control for endogeneity bias, may underestimate the true rates of return. The results indicate that the returns to schooling in Kazakhstan have increased with transition. This may reflect the relative scarcities of highly educated people in Kazakhstan with human capital that employers require and, following the market reforms, reward accordingly.     

Multi-factor Risk-return Relationships

This paper derives three multi-factor risk-return relationships each of which employs macro-economic variables in presenting the underlying factors that influence security returns. The first relationship holds if the underlying portfolio lies on the expected return-standard deviation efficient frontier, the second is valid when the underlying portfolio lies inside the efficient frontier and the third characterises security markets in which no arbitrage opportunities are present. An attempt is also made to appraise critically previous multi-factor risk-return relationships which rely on an expected return-standard deviation approach.     

An Exchange Rate Model with Market Pressures and a Contagion Effect

The model we propose includes variables accounting for the behavioral aspects of decision-making in the currency markets, namely the contagion effect between countries in the same region. It combines the classical purchasing power parity (PPP) and uncovered interest rate parity (UIP) hypotheses with the effects of risk aversion in financial markets and of currency market pressures.

The results based on the Polish data confirm that the currency market instabilities arise not only from fundamental factors such as economic activity and the country’s balance of payments, but also from the contagion effect brought about by investors’ tendency to view Poland and its neighbors, the Czech Republic and Hungary, as one group.     

手机分期消费贷款信用风险研究——基于RF-Logistic模型的实证分析

识别手机分期消费贷款违约因子是防范手机消费贷款业务信用风险的关键所在。为此,基于融合随机森林（RF）和逻辑回归（Logistics）两阶段模型,通过数据挖掘揭示风险特征重要性含义,并结合经济计量方法诠释异质性客户信用违约的基准逻辑。结果表明：入网时长、终端个数、客户月流量、终端时长是影响手机分期消费贷款客户信用风险的重要性特征变量,且边际影响分别为-0.039%、3.18%、-0.01%、-1.06%,模型泛化能力强,准确率达到74%。所以,要完善手机分期消费贷款信用风险管理应从交叉数据获取、社交网络、兴趣热点和消费习惯等方面着手。     

Product‐Marketing Innovation,Skills, and Firm Productivity Growth

The role of product and marketing innovation for productivity growth is addressed using survey and register data for the Danish economy. It is hypothesized that product and marketing innovation are complementary inputs and that innovation activities are skill‐intensive. It is established that product and marketing innovation in skill‐intensive firms results in significantly faster productivity growth. Moreover, product and marketing innovation have independent roles in productivity growth, which cannot be attributed to organizational changes. Finally, we apply an instrument variable approach for firms, innovation choices to study endogeneity. The results strongly support the idea that product–marketing innovation leads to faster productivity growth in skill‐intensive firms.     

内生变量分析视角下的煤炭开采和洗选业效益研究——以山西省为例

为揭示与山西省煤炭开采和洗选业关联的其他行业污染物对煤炭开采和洗选业效益的影响,克服EKC假说只分析收入对环境单向影响的缺陷,研究各变量的内生性;通过协整检验、脉冲响应等检验手段研究煤炭开采和洗选业效益对环境污染的内生性影响,环境污染对收益的反作用,得出其长短期均衡关系和影响力度;从排废水、排废气、排废渣的与煤相关行业和煤炭市场入手,提出了山西煤炭开采和洗选业的发展路径。     

Labour market consequences of a high school diploma

This article compares the labour market outcomes of high school dropouts to high school graduates who did not enrol into higher education, but immediately entered the labour market. Using parental educational background as an instrument on a rich administrative dataset in the Flemish Region of Belgium, we find no returns to a high school diploma on average. However, these results hide considerable heterogeneity by gender and educational track. While females and individuals in vocational education may benefit from a diploma, male graduates and students holding a general education diploma may even be worse off on the labour market than dropouts. We show that sectoral heterogeneity acts as an underlying mechanism in the returns to a high school diploma.     

Modeling complex systems

Empirical observations suggest that linear dynamics are not an adequate representation of ecological systems and that a realistic representation would require adoption of complex nonlinear dynamical systems with characteristics encountered in complex adaptive systems (CAS). Adequate modeling should include and combine elements, such as strategic interactions among economic agents, nonconvexities induced by nonlinear feedbacks, separate spatial and temporal scales and modeling of spatiotemporal dynamics, and allowance of alternative time scales. Ignoring these characteristics might obscure very important features that we observe in reality, such as bifurcations and irreversibilities or hysteresis. As a consequence, the design of policies that do not take CAS characteristics into account might lead to erroneous results and undesirable states of managed economic–ecological systems.