Variance approximation under balanced sampling

A balanced sampling design has the interesting property that Horvitz–Thompson estimators of totals for a set of balancing variables are equal to the totals we want to estimate, therefore the variance of Horvitz–Thompson estimators of variables of interest are reduced in function of their correlations with the balancing variables. Since it is hard to derive an analytic expression for the joint inclusion probabilities, we derive a general approximation of variance based on a residual technique. This approximation is useful even in the particular case of unequal probability sampling with fixed sample size. Finally, a set of numerical studies with an original methodology allows to validate this approximation.     

Generalized confounded row–column designs

Generalized Confounded Row–Column (GCRC) designs for factorial experiments have been introduced and methods of constructing GCRC designs have been discussed. Fractionally replicated GCRC designs have also been constructed. The designs obtained ensure balancing with respect to estimable effects.     

A comparison of balancing scores for estimating rate ratios of count data in observational studies

In this article, we conduct a Monte Carlo study to examine four balancing scores (BS1: propensity score, BS2: prognostic score, BS3: adjusted propensity score estimated by the estimated prognostic score, and BS4: adjusted propensity score estimated by the estimated prognostic score and other covariates) for adjusting bias in estimating the marginal and the conditional rate ratios of count data in observational studies. Simulation results show that BS1–BS4 are not much different in terms of estimating the marginal and the conditional rate ratios, however, choosing the appropriate matching algorithm is more important than selecting a balancing scores.     

Propensity score model specification for estimation of average treatment effects

Treatment effect estimators that utilize the propensity score as a balancing score, e.g., matching and blocking estimators are robust to misspecifications of the propensity score model when the misspecification is a balancing score. Such misspecifications arise from using the balancing property of the propensity score in the specification procedure. Here, we study misspecifications of a parametric propensity score model written as a linear predictor in a strictly monotonic function, e.g. a generalized linear model representation. Under mild assumptions we show that for misspecifications, such as not adding enough higher order terms or choosing the wrong link function, the true propensity score is a function of the misspecified model. Hence, the latter does not bring bias to the treatment effect estimator. It is also shown that a misspecification of the propensity score does not necessarily lead to less efficient estimation of the treatment effect. The results of the paper are highlighted in simulations where different misspecifications are studied.     

Optimal inclusion probabilities for balanced sampling

When auxiliary information is available at the design stage, samples may be selected by means of balanced sampling. The variance of the Horvitz-Thompson estimator is then reduced, since it is approximately given by that of the residuals of the variable of interest on the balancing variables. In this paper, a method for computing optimal inclusion probabilities for balanced sampling on given auxiliary variables is studied. We show that the method formerly suggested by Tillé and Favre (2005) enables the computation of inclusion probabilities that lead to a decrease in variance under some conditions on the set of balancing variables. A disadvantage is that the target optimal inclusion probabilities depend on the variable of interest. If the needed quantities are unknown at the design stage, we propose to use estimates instead (e.g., arising from a previous wave of the survey). A limited simulation study suggests that, under some conditions, our method performs better than the method of Tillé and Favre (2005).     

Machine covering with combined partial information

Machine scheduling and covering problems may occur in many applications such as load balancing in network communication channel assignment, parallel processing in large-size computing, task arrangement in flexible manufacturing systems, etc. In this paper we study machine covering problems with combined partial information on m   parallel identical machines. We consider sequences where the processing time of all jobs are at most 1/k$1/k$ times of the optimal value (for an integer k). For the case where the optimal value is not known in advance, we show that LS algorithm is optimal. For the case where the optimal value is known in advance, we give lower bounds and present semi-online algorithms.     

Practical statistical considerations for investigating anti-tumor treatments in mice

Anti-tumor treatment outcomes in mouse experiments can be challenging to interpret and communicate accurately. In reporting these experiments, rigorous statistical considerations are commonly absent, although statistical applications have been proposed. We investigated the practicality and utility of different statistical strategies for the analysis of anti-tumor responses in a longitudinal mouse case study. Each analysis that we performed had different endpoints, investigated different questions, and was based on different assumptions. We found rudimentary visual and risk analysis insufficient without additional considerations, and upon further investigation we found improvements in key anti-tumor parameter estimates associated with a drug combination in our case study. We offer practical statistical considerations for investigating anti-cancer treatments in mice, applying a multi-tier statistical approach.     

Model averaging procedure for varying-coefficient partially linear models with missing responses

This paper is concerned with model averaging procedure for varying-coefficient partially linear models with missing responses. The profile least-squares estimation process and inverse probability weighted method are employed to estimate regression coefficients of the partially restricted models, in which the propensity score is estimated by the covariate balancing propensity score method. The estimators of the linear parameters are shown to be asymptotically normal. Then we develop the focused information criterion, formulate the frequentist model averaging estimators and construct the corresponding confidence intervals. Some simulation studies are conducted to examine the finite sample performance of the proposed methods. We find that the covariate balancing propensity score improves the performance of the inverse probability weighted estimator. We also demonstrate the superiority of the proposed model averaging estimators over those of existing strategies in terms of mean squared error and coverage probability. Finally, our approach is further applied to a real data example.     

Extensions of Permutation Solutions to Test for Treatment Effects in Replicated Single-Case Alternation Experiments with Multivariate Response

Single-case experiments are frequently used to do research involving a clinical intervention, since large-n trials are often impractical in clinical research. In order to investigate a possible difference in the effect of the treatments considered in the study, nonparametric instruments are valid tools; in particular, permutation solutions work well when we wish to assess differences in treatment effects. We present an extension of a permutation solution to the multivariate response case and to the case of replicated single-case experiments. A simulation study shows that the approach is both reliable under the null hypothesis and powerful under the alternative. At the end, we present the results of an application to two real experiments.     

A meta-analysis approach for step-stress experiments

The step-stress model is a special case of accelerated life testing that allows for testing of units under different levels of stress with changes occurring at various intermediate stages of the experiment. Interest then lies on inference for the mean lifetime at each stress level. All step-stress models discussed so far in the literature are based on a single experiment. For the situation when data have been collected from different experiments wherein all the test units had been exposed to the same levels of stress but with possibly different points of change of stress, we introduce a model that combines the different experiments and facilitates a meta-analysis for the estimation of the mean lifetimes. We then discuss in detail the likelihood inference for the case of simple step-stress experiments under exponentially distributed lifetimes with Type-II censoring.     

Gamma-distribution order statistics,maximal multinomial frequency and randomization designs

The paper discusses the relationship between the gamma-distribution order statistics, the maximal cell frequency in multinomial trials and the distribution arising in a commonly used balanced randomization scheme with several treatments. The latter is used in clinical trials, load balancing in computer files storage, parapsychological experiments, etc., where a randomization design starts with the uniform probability assignment of subjects to treatments. The limiting distributions of the waiting time until a treatment receives the given number of subjects are described. The relationship to classical occupancy problems, in particular, to the Banach match-box problem and to the birthday problem is discussed.     

On a problem with singularity in comparison of linear experiments

For consistency, the parameter space in the Gauss-Markov model with singular covariance matrix is usually restricted by observation vector. This restriction arises some difficulties in comparison of linear experiments. To avoid it we reduce the problem of comparison from singular to nonsingular case.     

Comparison of experiments based on generalized entropy measures

Taneja (1989) studied a unified (r,s)-entropy which includes as a particular case some of the known entropies. Based on this unified (r, s)entropys we have defined the average amount of information provided by an experiment X over the unknown parameter 8 with prior knowledge p(0). By using average amount of information in unified form, we have compared experiments based on bayesian approach. Some connections with the criteria of Blackwell and Lehmann are also made.     

Uniform coverage designs for mixture experiments

We investigate an optimization problem for mixture experiments. We consider the case when a large number of ingredients are available but mixtures can contain only a few number of ingredients. These conditions are held in experiments for self assembling molecular systems. First, we introduce a concept of uniform coverage design specialized for the situation. Next, we propose to use the stepwise technique for estimating coefficients of third-order Scheffe model which describes a response surface. After that, we propose a method of adding new mixtures for a movement to an extremum region. By this method, additional mixtures of experiments are extremum points of current estimated model and points which lead to more accurate estimation of current model prediction. This methodology is studied numerically for a model constructed from real data.     

Autoregressive distributed lag models and cointegration

Summary This paper considers cointegration analysis within an autoregressive distributed lag (ADL) framework. First, different reparameterizations and interpretations are reviewed. Then we show that the estimation of a cointegrating vector from an ADL specification is equivalent to that from an error-correction (EC) model. Therefore, asymptotic normality available in the ADL model under exogeneity carries over to the EC estimator. Next, we review cointegration tests based on EC regressions. Special attention is paid to the effect of linear time trends in case of regressions without detrending. Finally, the relevance of our asymptotic results in finite samples is investigated by means of computer experiments. In particular, it turns out that the conditional EC model is superior to the unconditional one. We thank Vladimir Kuzin for excellent research assistance and Surayyo Kabilova for skillful word processing. Moreover, we are grateful to an anonymous referee for clarifying comments.     

A comparison of random balance and two-stage group screening designs: A case study

In this paper we focus on the problem of supersaturated (fewer runs than factors) screening experiments. We consider two major types of designs which have been proposed in this situ¬ation: random balance and two-stage group screening. We discuss the relative merits and demerits of each strategy. In addition, we compare the performance of these strategies by means of a case study in which 100 factors are screened in 20,42,62, and 84 runs.     

A methodology for quantifying the effect of missing data on decision quality in classification problems

Decision making is often supported by decision models. This study suggests that the negative impact of poor data quality (DQ) on decision making is often mediated by biased model estimation. To highlight this perspective, we develop an analytical framework that links three quality levels – data, model, and decision. The general framework is first developed at a high-level, and then extended further toward understanding the effect of incomplete datasets on Linear Discriminant Analysis (LDA) classifiers. The interplay between the three quality levels is evaluated analytically – initially for a one-dimensional case, and then for multiple dimensions. The impact is then further analyzed through several simulative experiments with artificial and real-world datasets. The experiment results support the analytical development and reveal nearly-exponential decline in the decision error as the completeness level increases. To conclude, we discuss the framework and the empirical findings, elaborate on the implications of our model on the data quality management, and the use of data for decision-models estimation.     

A generalization of the alias matrix

The investigation of aliases or biases is important for the interpretation of the results from factorial experiments. For two-level fractional factorials this can be facilitated through their group structure. For more general arrays the alias matrix can be used. This tool is traditionally based on the assumption that the error structure is that associated with ordinary least squares. For situations where that is not the case, we provide in this article a generalization of the alias matrix applicable under the generalized least squares assumptions. We also show that for the special case of split plot error structure, the generalized alias matrix simplifies to the ordinary alias matrix.     

The optimal allocation of active redundancies to k-out-of-n systems with respect to hazard rate ordering

This paper deals with the allocation of active redundancies to a k-out-of-n system with independent and identically distributed (i.i.d.) components in the sense of the hazard rate order. It is shown that the system's hazard rate may be decreased by balancing the allocation of active redundancies. This generalizes the main result of Singh and Singh (1997) and improves the corresponding one of Hu and Wang (2009) as well. As an application, we build the reversed hazard rate order on order statistics from sample having proportional hazard rates, which strengthens the usual stochastic order in Theorem 2.1 of Pledger and Proschan (1971) to the reversed hazard order in the situation that all components are of (rational) proportional hazard rates.     

Functional Discriminant Coordinates

In this article we propose a new method of construction of discriminant coordinates and their kernel variant based on the regularization (ridge regression). Moreover, we compare the case of discriminant coordinates, functional discriminant coordinates and the kernel version of functional discriminant coordinates on 20 data sets from a wide variety of application domains using values of the criterion of goodness and statistical tests. Our experiments show that the kernel variant of discriminant coordinates provides significantly more accurate results on the examined data sets.