Multiple regression with a qualitative dependent variable

This paper describes several methods by which a single set of scores for a qualitative (usually ordinal) dependent variable can be estimated simultaneously with the coefficients of the explanatory variables of a model. The canonical correlations and multiple discriminant analysis approaches are well known in the statistics literature. However, the paper goes on to show an iterative least-squares multiple regression technique can provide a useful approximation to these more general procedures. The techniques are illustrated with labor force participation and voter turnout examples.     

Marketing perspectives on digital business models: A framework and overview of the special issue

Strong digital developments are changing markets, and firms may adopt a digital business model to deal with these developments. This special issue focuses on such digital business models. In this editorial, we discuss the relevance of digital business models, propose a conceptual framework, and discuss how digital business models affect firms, firm performance, and markets. We introduce the papers in this issue and show how they each fit within the conceptual framework. We discuss four important areas for future research.     

Business experience and start-up size: Buying more lottery tickets next time around?

This paper explores the determinants of start-up size by focusing on a cohort of 6,247 businesses that started trading in 2004, using a unique dataset on customer records at Barclays Bank. Quantile regressions show that prior business experience is significantly related with start-up size, as are a number of other variables such as age, education and bank account activity. Quantile treatment effects (QTE) estimates show similar results, with the effect of business experience on (log) start-up size being roughly constant across the quantiles. Prior personal business experience leads to an increase in expected start-up size of about 50 %. Instrumental variable QTE estimates are even higher, although there are concerns about the validity of the instrument.     

Estimating the extensive margin of trade

Understanding and quantifying the determinants of the number of sectors or firms exporting in a given country is of relevance for the assessment of trade policies. Estimation of models for the number of exporting sectors, however, poses a challenge because the dependent variable has both a lower and an upper bound, implying that the partial effects of the explanatory variables on the conditional mean of the dependent variable cannot be constant. We argue that ignoring these bounds can lead to erroneous conclusions and propose a flexible specification that accounts for the doubly-bounded nature of the dependent variable. We empirically investigate the problem and the proposed solution, finding significant differences between estimates obtained with the proposed estimator and those obtained with standard approaches.     

Financial determinants of systematic risk in real estate investment trusts

Financial theory and empirical evidence suggest that a firm's systematic, or market related, risk is related to its financial conditions. This study empirically investigates the financial determinants of systematic risk for Real Estate Investment Trusts (REITs). The study is an examination of sample of 32 REITs for the period 1976–1978. The results indicate that systematic risk varies directly with financial leverage, business risk, and advisor fee. The explanatory power of the relationship between systematic risk and financial variables exceeds that of previous studies wherein firms were pooled across industry groups. The higher explanatory power observed even with limited data suggests that better estimates of coefficients of financial determinants of systematic risk may be obtained through analysis conducted on an industry by industry basis. Furthermore, such industry-specific analysis provides useful results to practicing financial managers in their financial policy considerations. With the knowledge of how the financial decisions affect the firm's systematic risk, a manager may be able to manipulate those variables so as to reduce the systematic risk for his or her firm and thus increase the market value of the firm's securities.     

Estimating dynamic response models when the data are subject to different temporal aggregation

In estimating response models using secondary data, it can happen that the observations on the variables are subject to different temporal aggregation. Estimating a dynamic model with this type of data is not straightforward, particularly when (a) estimates with good statistical properties are desired, and (b) full use of all information in the data is needed. This paper provides an overview and discussion of the various approaches to the estimation problem when independent variables are observed less frequently than the dependent variable. The superiority of one-step estimation procedures that simultaneously estimate the parameters and the missing disaggregated data points is established.Insead     

Drug trafficking,money laundering and the business cycle: Does secular stagnation include crime?

The aim of the paper is to analyze theoretically and empirically the impact the macroeconomic cycle has on the accumulation of capital by organized crime, using estimates for the global drug market. So far, the economic literature has neglected the relationships existing between illegal markets, money laundering and the business cycle. We propose a dynamic model where the business cycle influences the criminal economy via two different channels. On the one side, illegal markets grow at variable rates, depending on the health of the legal economy. Second, a pass‐through effect can exist, since the business cycle affects the legal markets which criminal operators use to launder their revenues. Furthermore, we analyze the consequences of a ‘saturation effect’ limiting maximum accumulation of illegal capital. We find that overall illegal capital is affected by the business cycle through a capital multiplier; in addition to this, the dynamics of interest rates in financial markets can influence such multiplier.     

Hierarchical Bayesian conjoint models incorporating measurement uncertainty

The authors explore situations where consumers supplement their judgments with a measurement of uncertainty about their own preferences, either implicitly or explicitly, and develop two sets of hierarchical Bayesian conjoint models incorporating such measurements. The first set of models uses the relative location of a rating to determine the importance or weight given to the rating, in a regression setting. The second set uses interval judgment as a dependent variable in a regression setting. After specifying the models, the authors perform a theoretical comparison with a basic Bayesian regression model. They show that, under different conditions, the proposed models will yield more precise individual-level partworth estimates. Two simulated data examples and data from a conjoint study are used to illustrate the gains that could be obtained from modeling uncertainty. In the empirical application, the authors show that model fit improves when ratings for items that respondents do not like are given more weight compared to ratings for items that they do like. Electronic Supplementary Material  The online version of this article (doi:) contains supplementary material, which is available to authorized users.

A NOTE ON THE QUANTILE FORMULATION

Many investment models in discrete or continuous‐time settings boil down to maximizing an objective of the quantile function of the decision variable. This quantile optimization problem is known as the quantile formulation of the original investment problem. Under certain monotonicity assumptions, several schemes to solve such quantile optimization problems have been proposed in the literature. In this paper, we propose a change‐of‐variable and relaxation method to solve the quantile optimization problems without using the calculus of variations or making any monotonicity assumptions. The method is demonstrated through a portfolio choice problem under rank‐dependent utility theory (RDUT). We show that this problem is equivalent to a classical Merton's portfolio choice problem under expected utility theory with the same utility function but a different pricing kernel explicitly determined by the given pricing kernel and probability weighting function. With this result, the feasibility, well‐posedness, attainability, and uniqueness issues for the portfolio choice problem under RDUT are solved. It is also shown that solving functional optimization problems may reduce to solving probabilistic optimization problems. The method is applicable to general models with law‐invariant preference measures including portfolio choice models under cumulative prospect theory (CPT) or RDUT, Yaari's dual model, Lopes' SP/A model, and optimal stopping models under CPT or RDUT.     

星基增强系统接收机中的导航比特同步设计与性能仿真

星基增强系统(SBAS)中导航电文速率为500符号/秒,针对其弱信号时找导航比特边界难的特点,提出了基于最大似然算法的比特同步算法,给出了在SBAS接收机中比特同步的应用公式和实现方法,并进一步创新性地设计了包含有软判决和多次判决的比特同步综合流程;最后在多种导航比特分布的情形下,对最大似然比特同步算法进行了不同载噪比下的性能仿真,确认了此算法在接收信号很弱时仍然有效。     

The Value of Information Integration in Meeting Delivery Dates

In this article, we consider the value of shared information within a business network. To make the problem concrete, we focus on a specific operational problem: How the final supplier to the customer determines promised delivery dates. In a traditional supply chain, the final supplier has little or no information on the delivery performance of intermediate suppliers and thus, has limited information with which to set delivery dates. On the other hand, in an information-integrated business network, the final supplier's enterprise resource planning (ERP) system can interact with all the intermediate suppliers' ERP systems to determine exactly how far ahead or behind schedule the network is in meeting the needs of a specific customer. This information should improve the final supplier's ability to set realistic delivery dates. We attempt to quantify the value of this information and determine precisely why it is valuable so that management can best exploit information integration.

We use a modeling approach in this research, beginning with simple analytic models and progressing to more realistic simulation models. Our analytic model establishes an important principle: Information integration not only significantly improves the average on-time delivery performance of a business network, but also dramatically improves its worst-case performance. Because customer dissatisfaction is generally associated with worst-case performance, information integration may be highly beneficial even if its effect on average on-time delivery is small. Simulation models allow us to compare the performance of more realistic business networks. These models suggest, for example, that the value of information integration is dependent on both the structure of the network itself (whether serial or arborescent) and on the typical customer order date in the production cycle. These insights allow us to begin to identify the types of business networks in which information integration will have the highest value.     

A cross-sectional analysis of asset holdings

This article introduces cross-sectional data on asset holdings derived from a survey of Australian households. We use the data to estimate asset Engel curves which are shown to fit the data extremely well. The findings indicate that cash and bank deposits and insurance are necessities, with wealth elasticities less than unity, own home has an elasticity of one and the other four assets [1) other property, 2) shares and securities, 3) superannuation, and 4) unincorporated business] are luxuries with wealth elasticities greater than unity. The Engel curve estimates are used to explain differences in the dispersion of the portfolio across households and to compute a measure of the substitutability complementarity between the individual assets. The results indicate that 1) housing is a substitute for all other assets and 2) business related assets are all pairwise complements.     

Productive capabilities: An empirical analysis of their drivers

Recent contributions to the growth and trade literature have argued that the structure of an economy, as measured by its productive capabilities, is a key determinant for inter-country differences in development. Productive capabilities have been shown to be highly predictive of future economic growth, yet the country-level variables associated with them remain relatively unknown. In this paper, we empirically explore what variables are systematically associated with productive capabilities using a model averaging framework that can handle a very large number of potential explanatory variables without the need for arbitrary model selection. In order to estimate our dynamic panel specification, we propose a novel Bayesian averaging of classical estimates procedure based on the simple and efficient bias-corrected least squares dummy variable estimator. Our baseline and robustness analysis consider a large number of variables, sample periods and model priors. We find that there is persistence (as measured by the lagged dependent variable) and that variables, such as commodity terms of trade, energy availability, government consumption, capital per worker, arable land and capital inflows show a strong and robust association with capabilities.     

A new multivariate count data model to study multi-category physician prescription behavior

Multivariate count models represent a natural way of accommodating data from multiple product categories when the dependent variable in each category is represented by a positive integer. In this paper, we propose a new simultaneous equation multi-category count data model–the Poisson-lognormal simultaneous equation model–that allows for the Poisson parameter in one equation to be a function of the Poisson parameters in other equations. While generally applicable to any situation where simultaneity is an issue and the dependent variables are measured as counts, such a specification is particularly useful for our empirical application where physicians prescribe drugs in multiple categories. Accounting for the endogeneity of detailing in such situations requires us to explicitly allow for pharmaceutical firms’ detailing activities in one category to be influenced by their activities in other categories. Estimation of such a system of equations using traditional maximum likelihood method is cumbersome, so we propose a simple solution based on using Markov Chain Monte Carlo methods. Our simulation study demonstrates the validity of the solution algorithm and the biases that would result if such simultaneity is ignored in the estimation process.     

Measures of marketing success

A mismatch of the meaning of “success”, as perceived by researcher and the firms researched, renders research less relevant and possibly, where the firm's resources are not directed at the goals selected by the researcher, misleading. This paper is concerned with the dependent variables used for business or marketing “success”, not its drivers, in seven leading marketing and strategy journals. The findings are that researcher, not respondent, views of performance dominate the literature which raises issues of relevance. Researchers are not necessarily being normative, and should be thoughtful in their selection of marketing performance objectives, i.e. the outcomes they seek to explain. A checklist of dependent variable considerations is provided together with a tentative definition of “success” against which performance may be compared.     

Dynamic Entry and Exit Linkages in the Brazilian Manufacturing Industry: An Econometric Investigation

The paper investigates dynamic linkages between entry and exit rates in Brazilian manufacturing in the context of 231 (four-digit) industries during the 1996–2005 period. The empirical analysis focuses on the estimation of a dynamic panel data model for entry and exit rates, and controls for the business cycle and structural characteristics, such as industrial concentration and suboptimal scale. The empirical evidence is partially consistent with a multiplier effect where synergetic factors prevail by exit inducing exit. Evidence partially supports a competition effect that could be related to a selection process favoring efficiency, as exit induces entry. The business cycle control variable and the aforementioned structural variables appear to play no role in delineating entry and exit linkages. The results are similar, although not identical, to previous evidence for developed countries.     

The application of probit,logit, and tobit in marketing: A review

Recent work on the analysis of qualitative dependent variables having considerable potential in marketing research are reviewed and illustrated. In particular, three related models, probit, logit, and tobit, are discussed in a nontechnical manner. In the last few years, there has been a resurgence of interest among biologists, economists, and other social scientists in developing and generalizing these three models. Yet, despite their apparent utility in marketing research, there have been only one or two rather limited applications to date. The object of this review is to enable researchers to evaluate these models and to relate them to their existing statistical procedures. The models are defined and related to the multivariate methods commonly used in marketing research. Second, the theoretical problems associated with using regression analysis and similar procedures on qualitative data are noted and the assumptions needed to resolve such problems are presented. Third, marketing applications are reviewed and an illustration of a general form of the probit model is evaluated and compared.     

A Model of Business Ethics

It appears that in the 30 years that business ethics has been a discipline in its own right a model of business ethics has not been proffered. No one appears to have tried to explain the phenomenon known as ?business ethics’ and the ways that we as a society interact with the concept, therefore, the authors have addressed this gap in the literature by proposing a model of business ethics that the authors hope will stimulate debate. The business ethics model consists of three principal components (i.e. expectations, perceptions and evaluations) that are interconnected by five sub-components (i.e. society expects; organizational values, norms and beliefs; outcomes; society evaluates; and reconnection). The introduced model makes a contribution to the creation of a conceptual framework for business ethics. A few tentative conclusions may be drawn from the introduced model of business ethics. The model aspires to be highly dynamic. The ultimate outcome is dependent upon the evolution of time and contexts. It is also dependent upon and provides reference to the behaviours and perceptions of people. The model proposes business ethics to be a continuous and an iterative process. There is no actual end of the process, but a constant reconnection to the initiation of successive process iterations of the business ethics model. The principals and sub-components of the model construct the dynamics of this continuous process. They provide guidance on what and how to explore our common efforts to understand the phenomenon known as business ethics. The model provides opportunities for further research in the field of business ethics.