AN APPLICATION OF SEQUENTIAL REGRESSION MULTIPLE IMPUTATION ON PANEL DATA

The relatively new sequential regression multiple imputation (SRMI) method is introduced, with the process of SRMI laid out in detail. The Project for Statistics on Living Standards and Development and the follow‐up KwaZulu‐Natal Income Dynamics Study provide the real panel data on which the methods reviewed are applied. The SRMI process is used to create multiple datasets completed with values imputed for data originally missing, and using the error component model estimation procedures and Rubin's rules, inferences on the panel data are made. Conclusions are drawn as to the applicability of the SRMI process to these data and as to the results of the regression analyses completed.     

ALCOHOL REGULATION AND DOMESTIC VIOLENCE TOWARDS CHILDREN

In recent years, economists have paid much attention to the demand for alcohol and the negative externalities associated with excessive drinking. Largely ignored in the literature is the link between alcohol use and domestic violence. Given the established positive relationship between alcohol consumption and acts of violence, the purpose of this paper is to examine the role that changes in the determinants of the demand for alcohol may play in reducing the incidence of violence aimed at children. Data on violence come from the 1976 Physical Violence in American Families survey. We estimate a model in which violent outcomes are affected by the state excise tax rate on beer; illegal drug prices, and other regulatory variables such as availability measures and laws restricting the advertising of alcohol. Results show that increasing the tax on beer can be an effective policy tool in reducing violence. Laws designed to make obtaining beer more difficult also may be effective in reducing violence, while restrictions on advertising and increases in illegal drug prices have no effects.     

ILLICIT DRUG USE, ABSENTEEISM, AND EARNINGS AT SIX U.S. WORKSITES

Considerable national attention has focused recently on the adverse consequences of illicit drug use. While several studies estimate the relationship between illicit drug use and wages, the findings are inconsistent. Surprisingly, some researchers identify a positive and statistically significant relationship between wages and drug use for young adults. Motivated by this counter-intuitive finding, this paper compiles unique data on employees at six worksites in order to explore the relationships among drug use, wages, and absenteeism. Using various measures of current and lifetime drug use and accounting for alcohol-use comorbidity, the authors find predominantly insignificant relationships (both direct and indirect) between drug use and both wages and absenteeism, regardless of gender.     

Why Unit Prices of Supermarket Products Vary

A variation in unit price among different sizes of the same product has been observed in many studies of supermarkets. Quantity price premiums have also been observed. This study reviews theoretical explanations for variation in unit prices and tests the explanations using data from a southeastern supermarket chain. The empirical results indicate that packaging characteristics and storage characteristics of a product are significantly related to unit price variation and to the probability of quantity price premiums.     

THE STRUCTURE OF THE FINANCIAL SERVICES INDUSTRY

Since most studies of the financial services industry have viewed the structure of the industry as fixed, there has been little discussion of its determinants. Events of the past few years make it clear that the structure of the financial services industry is changing much more rapidly than it did between the end of World War II and the mid 1960's. This paper categorizes and discusses the major factors affecting the structure of the financial services industry. The concept of supply and demand provides a useful framework for categorizing these factors. Demand is best analyzed in terms of the demand for various characteristics or attributes of financial services. These include: 1) yield; 2) liquidity; 3) safety; 4) convenience of access to the services, 5) financial advice or information. The demand for these various characteristics or attributes depends importantly on demographic and economic factors
The supply of financial services is determined by the cost curves associated with those services which are in turn determined by the cost of the factors of production and the underlying production function. Three aspects of these cost curves have an important effect on the supply of financial services and the structure of the industry — economies of scale, economies of joint production and distribution, and the management of risk. The nature of the cost and production functions underlying the supply of financial services and the structure of the industry is affected by several exogenous factors. Foremost among them are the economy, technology, regulation, and the role of the Federal government in financial service markets
Based on the discussion of how the various exogenous factors affect the structure of the financial services industry, an attempt is made to predict how structure will change as deregulation occurs.     

Why People Do Not Always Follow the Doctor's Orders: The Role of Hope and Perceived Control

The lack of adherence to medical advice is a widely recognized health care concern with important implications for consumer well‐being. This study advances a model for better understanding adherence behaviors by incorporating the positive emotion of hope and consumer perceptions of control. Empirical testing of the model in the context of type 2 diabetes, a lifestyle‐changing chronic illness, shows that hope generates more patient adherence. Furthermore, individuals have higher hope when they believe they are capable of performing the actions their treatment requires, and/or that their health outcomes are under their physician's control. The results indicate that health care providers can play an important role in encouraging adherence behaviors by cultivating hope and customizing their interactions with patients. Interventions aimed at increasing patient self‐efficacy or promoting patients' beliefs that health outcomes are under their physician's control are two routes to building hope. Health initiatives aimed at increasing diabetes treatment adherence should consider alternatives beyond asking patients to “take control” of their diabetes.     

Do Macroforecasters Herd?

We show that typical tests of whether forecasters herd will falsely indicate herding behavior for a variety of types of behavior and forecasting environments that give rise to disagreement among forecasters. We establish that forecasters will appear to herd if differences between them reflect noise as opposed to private information, or if they arise from informational rigidities. Noise can have a behavioral interpretation and if so will depend on the behavioral model under consideration. An application of the herding tests to U.S. quarterly survey forecasts of inflation and output growth data 1981–2013 does not support herding behavior.