Optimal block sequences for blocked fractional factorial split-plot designs

It is known that for blocked 2^n-k$2^{n-k}$ designs a judicious sequencing of blocks may allow one to obtain early and insightful results regarding influential parameters in the experiment. Such findings may justify the early termination of the experiment thereby producing cost and time savings. This paper introduces an approach for selecting the optimal sequence of blocks for regular two-level blocked fractional factorial split-plot screening experiments. An optimality criterion is developed so as to give priority to the early estimation of low-order factorial effects. This criterion is then applied to the minimum aberration blocked fractional factorial split-plot designs tabled in McLeod and Brewster [2004. The design of blocked fractional factorial split-plot experiments. Technometrics 46, 135–146]. We provide a catalog of optimal block sequences for 16 and 32-run minimum aberration blocked fractional factorial split-plot designs run in either 4 or 8 blocks.     

The effect of employee loyalty on wages

In spite of a sizeable body of research linking employee loyalty to organizational performance, the causal link between employee loyalty and employee wages has rarely been examined. We use the UK’s 2011 Work and Employment Relations Survey (WERS) employee-firm matched data to estimate ordinary least squares (OLS), instrumental variables (IV) models and treatment effects models. Our results show that employee loyalty is negatively associated with wages.     

A New Family of BAN Estimators for Polytomous Logistic Regression Models based on ϕ- Divergence Measures

In this paper we study polytomous logistic regression model and the asymptotic properties of the minimum ϕ-divergence estimators for this model. A simulation study is conducted to analyze the behavior of these estimators as function of the power-divergence measure ϕ_(λ) Research partially done when was visiting the Bowling Green State University as the Distinguished Lukacs Professor     

Estimating the probability of winning (losing) in a gambler's ruin problem with applications

In a classical gambler's ruin problem, the distribution of the number of games lost till ruin is considered, which we call the lost game distribution (LGD). Some applications of LGD in the theory of queues, in the theory of epidemic and in certain clustering and branching models are mentioned. The maximum likelihood estimation of LGD in the framework of modified power series distribution (MPSD), introduced by the author (1974), is studied. The variance and bias of the MLE are given and the actual mean of the MLE is obtained by discussing the negative moments of the MPSD in general. The minimum variance unbiased estimator of θ^k (k≥1) is obtained employing the technique developed by the author (1977) for the class of MPSD.     

Designing fractional factorial split-plot experiments with few whole-plot factors

Summary.  When it is impractical to perform the experimental runs of a fractional factorial design in a completely random order, restrictions on the randomization can be imposed. The resulting design is said to have a split-plot, or nested, error structure. Similarly to fractional factorials, fractional factorial split-plot designs can be ranked by using the aberration criterion. Techniques that generate the required designs systematically presuppose unreplicated settings of the whole-plot factors. We use a cheese-making experiment to demonstrate the practical relevance of designs with replicated settings of these factors. We create such designs by splitting the whole plots according to one or more subplot effects. We develop a systematic method to generate the required designs and we use the method to create a table of designs that is likely to be useful in practice.     

The Effects of Licensing on the Wages of Radiologic Technologists

We analyze the effect that state licensing of radiologic technologists (RTs) has had upon RT wages with a unique dataset that allows us to control for place of work and job specialization. Using OLS and several measures of licensing, we find evidence that RTs working in states with licensing statutes earn as much as 3.3% more than RTs working in states without licensing. When we control for endogeneity using instrumental variables (IV) estimation, our estimate of the licensing premium doubles (6.9%). Our results provide further support for existing theories of the effects of occupational licensing on the wages of practitioners.

Child Poverty in Northern Ireland: The Limits of Welfare-to-Work Policies

Levels of child poverty in Northern Ireland are high; 32 per cent of children live in households whose only income derives from benefits, compared with 19 per cent of children in Britain living in families totally dependent on benefits. Unemployment, low pay, a higher cost of living, low levels of public services, including childcare and support services for people with disabilities, slightly larger families and a lack of access by poorer women to the means of limiting their family size, together with even greater levels of inequality than in Britain, all contribute to the high levels of child poverty in Northern Ireland. This paper argues that even the less ambitious child poverty targets announced by the Department of Work and Pensions at the end of 2003 will not be met unless there is a fundamental change in the government's approach. In particular, evidence from Northern Ireland suggests that its insistence on work as the primary—if not only—route out of poverty will not lead to a radical reduction in levels of child poverty.