Compromise Allocation in Univariate Stratified Sampling

To reduce the loss of efficiency in the Neyman allocation caused by using the estimators instead of the unknown strata standard deviations of population, we suggest a compromise allocation that the Neyman allocation using an estimator of the pooled standard deviation of combined strata and the proportional allocation are used together. It is shown that the compromise allocation makes the estimator more efficient than the proportional allocation and the Neyman allocation using the estimated strata standard deviations. Simulation study is carried out for the numerical comparison and the results are reported.     

The battle over SNS privacy for US employees and job applicants: an analysis of 2012–2013 state legislation

This study examines US legislation designed to prohibit employer access to employee and job applicant personal social networking sites (SNSs) between 2012 and 2013. It asks if the legislation addressed how employers could use SNSs in the hiring process by requesting SNS passwords, if there were consequences for violators, if employer retaliation was prohibited, if third-party access was allowed, if employee SNS monitoring was prohibited, if SNS friend requests by employers was allowed and if employer requested changes in privacy settings were prohibited. In addition, the study also examined the interest groups and political party-affiliated sponsors that were active in the creation of the legislation. The results discover important inconsistencies between the states’ legislation, which question the ability to protect worker and applicant online privacy. US policy recommendations and transnational implications follow.     

Yearlong physical activity and health-related quality of life in older Japanese adults: the Nakanojo Study

We hypothesized that the health-related quality of life (HRQOL) would be poorer in physically inactive older adults. This was tested in a sample of 73 male and 108 female free-living healthy Japanese participants, age 65-85 years. We measured accelerometer step counts and their metabolic equivalents (METs) throughout each 24-hr period for 1 year. At the end of the year, HRQOL was assessed. Physical activity was grouped into quartiles. HRQOL was poorer in the lowest quartiles of participants with respect to both step count and duration of activity >3 METs; however, our sample showed no better HRQOL in those participants exceeding minimum standards of daily physical activity, corresponding to counts of around 5,500 and 4,500 steps/day and durations of around 13 and 14 min/day in men and women, respectively. Causation cannot be demonstrated from this cross-sectional study, but nevertheless we suggest that elderly individuals should be encouraged to meet such standards of habitual physical activity.     

Several biplot methods applied to gene expression data

DNA microarray experiments result in enormous amount of data, which need careful interpretation. Biplot approaches show simultaneous display of genes and samples in low-dimensional graphs and thus can be used to represent the relationships between genes and samples. There are several different types of biplots, and these methods need to be evaluated because each plot provides different result.     

The safety costs of contingent work: Evidence from Minnesota

We find that workers’ compensation costs for leased/staff agency workers are about three times higher than for regular full-time workers. This differential grows even wider when controlling for worker characteristics. Authors give a number of reasons for this result, including claimsreporting moral hazard on the part of contingent work-ers. We also present results on claim denials by work status, which seems to support the cost model. The authors gratefully acknowledge research support from the grants for research program of International Foundation of Employee Benefit Plans (IFEBP). Comments from Rich Derrig, Larry Aarhus, members of the Industrial Relations Center workshop, and an anonymous referee are greatly appreciated. The authors also appreciate Brian Zaidman for his helpful comments and assistance with the data for this study.     

The Cusum of Squares Test for Scale Changes in Infinite Order Moving Average Processes

In this paper we consider the problem of testing for a scale change in the infinite order moving average process X _j = _{i =0} a _{i j i} , where _j are i.i.d. r.v.s with E ₁ < for some > 0. In performing the test, a cusum of squares test statistic analogous to Inclan & Tiao's (1994) statistic is considered. It is well-known from the literature that outliers affect test procedures leading to false conclusions. In order to remedy this, a cusum of squares test based on trimmed observations is considered. It is demonstrated that this test is robust against outliers, is valid for infinite variance processes as well. Simulation results are given for illustration.     

A non-stationary integer-valued autoregressive model

It is frequent to encounter a time series of counts which are small in value and show a trend having relatively large fluctuation. To handle such a non-stationary integer-valued time series with a large dispersion, we introduce a new process called integer-valued autoregressive process of order p with signed binomial thinning (INARS(p)). This INARS(p) uniquely exists and is stationary under the same stationary condition as in the AR(p) process. We provide the properties of the INARS(p) as well as the asymptotic normality of the estimates of the model parameters. This new process includes previous integer-valued autoregressive processes as special cases. To preserve integer-valued nature of the INARS(p) and to avoid difficulty in deriving the distributional properties of the forecasts, we propose a bootstrap approach for deriving forecasts and confidence intervals. We apply the INARS(p) to the frequency of new patients diagnosed with acquired immunodeficiency syndrome (AIDS) in Baltimore, Maryland, U.S. during the period of 108 months from January 1993 to December 2001.