Weaker MSE criteria and tests for linear restrictions in regression models with non-spherical disturbances

This paper extend, in an asymptotic sense, the strong and the weaker mean square error criteria and corresponding tests to linear models with non-spherical disturbances where the error covariance matrix is unknown but a consistent estimator for it is available. The mean square error tests of Toro-Vizcorrondo and Wallace (1968) and Wallace (1972) test for the superiority of restricted over unrestricted linear estimators in a least squares context. This generalization of these tests makes them available for use with GLS, Zellner's SUR, 2SLS, 3SLS, tests of over identification, and so forth.     

Goodness of fit for seemingly unrelated regressions: Glahn's R2y.x and Hooper's r̄2

This paper presents a measure of goodness of fit for Zellner's seemingly unrelated regressions. The measure is a monotonic transform of the appropriate (asymptotic) F-statistic, is bounded on [0, 1] and is maximized by Zellner's estimation technique. Glahn's composite correlation coefficient is shown to be a special case of this measure. It is also compared to Hooper's squared trace correlation coefficient. All three measures as well as some additional asymptotic summary test statistics are calculated for the two-equation example of Zellner. The applicability of the latter test statistics seems not to be recognized in applied work.     

End-of-life care in nursing homes: the high cost of staff turnover

Nursing home staff turnover results in high cost--both economic and personal--and has a negative impact on the quality of care provided to residents at the end of life. Reducing staff turnover in nursing homes would benefit both the cost to the U.S. health care system, and, most importantly, the care residents receive in the vulnerable period leading to death. There is rising pressure on nursing homes to improve their palliative and end-of-life care practices and reduce transfers to hospital for situations and conditions that can be safely managed on site. Nursing care staff deserve an investment in the specific training necessary for them to give the highest quality care to dying residents. This training should be multifaceted and include the physiological, psychological, spiritual, interpersonal, and cultural (including ethnic) aspects of dying. Empowerment with these necessary knowledge, skills, and attitudes will not only result in better care for residents but likely also will reduce the burnout and frustration staff experience in caring for residents near death.     

Disability Risk Management and Postinjury Employment of Workers With Back Pain

We analyze the outcomes of occupational back pain among four large employers that use one or more of the following disability management practices: aggressive return to work, claims management, medical management, or time‐limited job accommodations. Outcomes measured at 6 and 12 months postonset include: duration of initial work absence and the probability of returning to stable employment. Employment outcomes are better in firms with more proactive return‐to‐work policies than in firms with more restrictive policies. We devise a statistical test for attrition bias and conclude that sample attrition does not significantly alter our results.     

Summary of Results of Survey of Seminar Attendees

Abstract

The Society of Actuaries undertook a three-phase research project on mortality improvement in the three NAFTA countries: Canada, Mexico, and the U.S. Phase 1 consisted of a literature review of papers on projecting mortality levels in the future and a study of the trend in mortality improvement during this century. Phase 2 consisted of a discussion of different facets of modeling mortality rates at a seminar attended by 79 experts (actuaries, demographers, economists, and medical researchers) representing different countries. The last session of the seminar consisted of the completion of a survey by the attendees to obtain input for Phase 3, which would analyze the impact of mortality improvement on the social security system of each country. This paper summarizes the results of the survey.

The survey results illustrate the difficulty in forecasting mortality levels, because the effects of many factors that could have significant impact on mortality rates are unknown. This suggests the need for dynamic forecasting, which allows for the possibility of random shocks. A majority of the survey respondents believe that stochastic forecasting models, despite their complexity, have significant potential to add value. Respondents also believe that both historical data and cause-specific mortality forecasts are useful as input and also in validating forecasts of the aggregate levels of mortality. The challenge is to develop more sophisticated forecasting models to produce results that are relatively easy to interpret and to communicate these results to the desired audiences, including the public and policymakers.

The survey results suggest that the aggregate effect of lifestyle changes, medical advances, diseases, catastrophe, and physical environmental changes is an increase in life span. However, there is much uncertainty about the future. Respondents expect that beyond the year 2020 the mean annual rate of reduction in mortality for males age 65 and over will average about 0.58% for Canada, 0.76% for Mexico, and 0.67% for the U.S. The results for the female age 65 and over population are 0.64%, 0.83%, and 0.70%, respectively. The age 65 and over population is expected to see larger percentage reductions in mortality than the 0–14 and 15–64 populations. The reductions in male and female mortality will be ultimately the same, and the mortality levels in the three countries will ultimately converge, although differences may persist for decades.     

The link between hunting goals and strategy and harvest outcome

Abstract

This article explores relationships among hunting goals, hunting strategies, and harvest success and attempts to assess if and how the relationships between harvest and nonharvest goals and harvest outcomes change in the presence of selected intervening hunting strategy variables. Log‐linear analysis examines the relationship among harvest outcome, hunting goals, and hunting strategies. Hunting strategies were found helpful in explaining the patterns of harvest outcome, suggesting that how a person hunts may be as important as why they hunt. Hunting strategy is seen as a viable concept for use in future investigations.     

International strategies of mid-sized firms: A comparison of Indiana and Guangdong Province

A China strategy is becoming more important for a growing number of mid-sized companies as they observe China's increasingly greater impact on the U.S. economy. Our study surveyed Indiana and Guangdong firms to assess their interest in future international engagement in the other's country. Our results confirm current engagement by mid-sized firms from both countries in some activities with the other country, but there is a strong interest in doing more. Hence, there are opportunities for many Indiana organizations to play a role in assisting Indiana firms in developing international expertise, business development, and knowledge of China. In the study, 97 firms from the Guangdong Province and 105 Indiana firms identified their current international activities as well their future intentions relative to business development in the other's country.     

A Hausman-type test to detect the presence of influential outliers in regression analysis

In regression analysis, classical estimations may be excessively influenced by a few atypical observations. We propose a Hausman-type test to balance robustness and efficiency and to check whether a robust method should be implemented. An economic application is presented.     

Social media influencers: A route to brand engagement for their followers

Social Media Influencers (SMIs) are micro‐celebrities with large followings on social media platforms who engage consumers and hold the potential to promote customer‐brand relationships across different product categories. SMIs have an existing relationship of trust with consumers, and consumers seek out the content created by SMIs for valuable information and advice. This study explores the process of brand engagement between consumers and brands in the digital content marketing environment, specifically examining the research question: Do SMIs act as a route to brand engagement for their followers? The context for this study is the beauty community on YouTube; over 60,000 user comments were analyzed through automated text analysis. This study is among the first to provide empirical evidence that SMIs do act as a route to brand engagement through the three dimensions of cognitive processing, affection and activation.     

Forecasting Social Security Actuarial Assumptions

Abstract

This paper presents a forecasting model of economic assumptions that are inputs to projections of the Social Security system. Social Security projections are made to help policy-makers understand the financial stability of the system. Because system income and expenditures are subject to changes in law, they are controllable and not readily amenable to forecasting techniques. Hence, we focus directly on the four major economic assumptions to the system: inflation rate, investment returns, wage rate, and unemployment rate. Population models, the other major input to Social Security projections, require special demographic techniques and are not addressed here.

Our approach to developing a forecasting model emphasizes exploring characteristics of the data. That is, we use graphical techniques and diagnostic statistics to display patterns that are evident in the data. These patterns include (1) serial correlation, (2) conditional heteroscedasticity, (3) contemporaneous correlations, and (4) cross-correlations among the four economic series. To represent patterns in the four series, we use multivariate autoregressive, moving average (ARMA) models with generalized autoregressive, conditionally heteroscedastic (GARCH) errors.

The outputs of the fitted models are the forecasts. Because the forecasts can be used for nonlinear functions such as discounting present values of future obligations, we present a computer-intensive method for computing forecast distributions. The computer-intensive approach also allows us to compare alternative models via out-of-sample validation and to compute exact multivariate forecast intervals, in lieu of approximate simultaneous univariate forecast intervals. We show how to use the forecasts of economic assumptions to forecast a simplified version of a fund used to protect the Social Security system from adverse deviations. We recommend the use of the multivariate model because it establishes important lead and lag relationships among the series, accounts for information in the contemporaneous correlations, and provides useful forecasts of a fund that is analogous to the one used by the Social Security system.