Asymptotic relative efficiency of wald tests in measurement error models

In this paper, asymptotic relative efficiency (ARE) of Wald tests for the Tweedie class of models with log-linear mean, is considered when the aux¬iliary variable is measured with error. Wald test statistics based on the naive maximum likelihood estimator and on a consistent estimator which is obtained by using Nakarnura's (1990) corrected score function approach are defined. As shown analytically, the Wald statistics based on the naive and corrected score function estimators are asymptotically equivalents in terms of ARE. On the other hand, the asymptotic relative efficiency of the naive and corrected Wald statistic with respect to the Wald statistic based on the true covariate equals to the square of the correlation between the unobserved and the observed co-variate. A small scale numerical Monte Carlo study and an example illustrate the small sample size situation.     

Efficiency or Competition? A Structural Econometric Analysis of Canada's AWS Auction and the Set‐Aside Provision

In 2008, Industry Canada auctioned 105 MHz of spectrum to a group of bidders that included incumbents and potential new entrants into the Canadian mobile phone market, raising $4.25 billion. In an effort to promote new entry, 40 MHz of spectrum was set‐aside for new entrants. In order to estimate the implicit cost of the set‐aside provision, we estimate the parameters of the bidders' profit function via a maximum match estimator based on the notion of pairwise stability in matches. We find that all telecommunications firms valued both geographic complementarities across auction licenses as well as absolute spectrum. Under a reasonable alternative scenario, our results indicate that the set‐aside led to a total profit loss of approximately 10%.     

Quasi-binomial zero-inflated regression model suitable for variables with bounded support

In recent years, a variety of regression models, including zero-inflated and hurdle versions, have been proposed to explain the case of a dependent variable with respect to exogenous covariates. Apart from the classical Poisson, negative binomial and generalised Poisson distributions, many proposals have appeared in the statistical literature, perhaps in response to the new possibilities offered by advanced software that now enables researchers to implement numerous special functions in a relatively simple way. However, we believe that a significant research gap remains, since very little attention has been paid to the quasi-binomial distribution, which was first proposed over fifty years ago. We believe this distribution might constitute a valid alternative to existing regression models, in situations in which the variable has bounded support. Therefore, in this paper we present a zero-inflated regression model based on the quasi-binomial distribution, taking into account the moments and maximum likelihood estimators, and perform a score test to compare the zero-inflated quasi-binomial distribution with the zero-inflated binomial distribution, and the zero-inflated model with the homogeneous model (the model in which covariates are not considered). This analysis is illustrated with two data sets that are well known in the statistical literature and which contain a large number of zeros.     

Adherence to Mediterranean diet and risk of prostate cancer

In Europe, countries following the traditional Mediterranean Diet (MeDi), particularly Southern European countries, have lower prostate cancer (PCa) incidence and mortality compared to other European regions. In the present study, we investigated the association between the MeDi and the relative risk of PCa and tumor aggressiveness in a Spanish population. Among individual score components, it has been found that subjects with PCa were less likely to consume olive oil as the main culinary fat, vegetables, fruits and fish than those without. However, these differences were not statistically significative. A high intake of fruit, vegetables and cooked tomato sauce Mediterranean style (sofrito) was related to less PCa aggressiveness. Results showed that there are no differences in the score of adherence to the Mediterranean dietary patterns between cases and controls, with mean values of 8.37?±?1.80 and 8.25?±?2.48, respectively. However, MeDi was associated with lower PCa agressiveness according to Gleason score. Hence, relations between Mediterranean dietary patterns and PCa are still inconclusive and merit further investigations. Further large-scale studies are required to clarify the effect of MeDi on prostate health, in order to establish the role of this diet in the prevention of PCa.     

Poverty and educational achievement in the US: A less-biased estimate using PISA 2012 data

In the current paper, we employ the most recent Programme for International Student Assessment (PISA) data to calculate a less-biased estimate of poverty on US achievement. The PISA was specifically chosen as it is an assessment removed from a specific curriculum and instead focuses on concepts that students should know in order to participate in a global economy. Using a propensity score matching approach, our findings suggest that US students in poverty have notable educational attainment deficiencies compared to a matched group of students who are not in poverty. In other words, when we select two students who have a great deal in common but for the fact that one comes from a poverty background, the student in poverty is expected to perform nearly 28 points, or about a quarter of a standard deviation lower, on the PISA assessment. In real terms, this puts math achievement for children not in poverty on-par with the Organisation for Economic Co-operation and Development (OECD) average, while children in poverty are well below the OECD average.     

College-bound friends and college application choices: Heterogeneous effects for Latino and White students

Friends are among the most influential social forces affecting adolescent behavior, yet little work has focused on the influence of friends on the decision to apply to college. Using data from the senior cohort of the Texas Higher Education Opportunity Project, we employed propensity score matching with sensitivity analyses to investigate links between having college-oriented friends and applying to college. We found that college-oriented friends increased the likelihood of applying to any college and to 4-year colleges, both for White and Latino students. However, Latino students benefited less from college-oriented friends compared to White students. Our findings suggest that college-choice models should more directly account for the influence of friends in applying to college, taking account of racial and ethnic differences, and future research should explore why Latino students benefit less.     

A Statewide Parenting Alternative Sentencing Program: Description and Preliminary Outcomes

ABSTRACT

The Washington State Legislature created the Parenting Sentencing Alternative in 2010, authorizing a substitute to total confinement for parents of minor children. The Alternative is designed to strengthen family bonds and improve parenting skills to encourage successful reintegration. An overview of the Alternative’s history, design, and implementation is presented, followed by preliminary results from an impact evaluation. A case study of a successful participant is presented, and implications for the findings are discussed.     

Approximating the risk score for disease diagnosis using MARS

In disease screening and diagnosis, often multiple markers are measured and combined to improve the accuracy of diagnosis. McIntosh and Pepe [Combining several screening tests: optimality of the risk score, Biometrics 58 (2002), pp. 657–664] showed that the risk score, defined as the probability of disease conditional on multiple markers, is the optimal function for classification based on the Neyman–Pearson lemma. They proposed a two-step procedure to approximate the risk score. However, the resulting receiver operating characteristic (ROC) curve is only defined in a subrange (L, h) of false-positive rates in (0,1) and the determination of the lower limit L needs extra prior information. In practice, most diagnostic tests are not perfect, and it is usually rare that a single marker is uniformly better than the other tests. Using simulation, I show that multivariate adaptive regression spline is a useful tool to approximate the risk score when combining multiple markers, especially when ROC curves from multiple tests cross. The resulting ROC is defined in the whole range of (0,1) and is easy to implement and has intuitive interpretation. The sample code of the application is shown in the appendix.     

On some aspects of a generalized alternative zero-inflated logarithmic series distribution

Here, we consider a generalized form of the alternative zero-inflated logarithmic series distribution of Kumar and Riyaz (J. Statist. Comp. Simul., 2015) and study some of its important aspects. The parameters of the distribution are estimated by the method of maximum likelihood and some test procedures are developed for testing the significance of the additional parameter of the model. All these estimation and testing procedures are illustrated with the help of certain real life datasets. A simulation study is also carried out for assessing the performance of the estimators.