Rank regression for accelerated failure time model with clustered and censored data

For clustered survival data, the traditional Gehan-type estimator is asymptotically equivalent to using only the between-cluster ranks, and the within-cluster ranks are ignored. The contribution of this paper is two fold: - (i) incorporating within-cluster ranks in censored data analysis, and; - (ii) applying the induced smoothing of Brown and Wang (2005, Biometrika) for computational convenience. Asymptotic properties of the resulting estimating functions are given. We also carry out numerical studies to assess the performance of the proposed approach and conclude that the proposed approach can lead to much improved estimators when strong clustering effects exist. A dataset from a litter-matched tumorigenesis experiment is used for illustration.

Estimation of Inequality Indices of the Cumulative Distribution Function

Date of Acceptance: 02/03/2015

Estimation of Inequality Indices of the Cumulative Distribution Function

Date of Acceptance: 02/03/2015

Joint hypothesis tests for multidimensional inequality indices

Acknowledgments This work has been undertaken with the support of the A*MIDEX project (n ∘ ANR-11-IDEX-0001-02) funded by the “Investissements d’Avenir” French Government program, managed by the French National Research Agency (ANR). We are grateful to Julian Williams, Editor Badi H. Baltagi and an anonymous referee for helpful comments. We are responsible for any errors.

The VLT-FLAMES survey of massive stars: atmospheric parameters and rotational velocity distributions for B-type stars in the Magellanic Clouds

Aims.We aim to provide the atmospheric parameters and rotational velocities for a large sample of O- and early B-type stars, analysed in a homogeneous and consistent manner, for use in constraining theoretical models. Methods: Atmospheric parameters, stellar masses, and rotational velocities have been estimated for approximately 250 early B-type stars in the Large (LMC) and Small (SMC) Magellanic Clouds from high-resolution VLT-FLAMES data using the non-LTE TLUSTY model atmosphere code. This data set has been supplemented with our previous analyses of some 50 O-type stars (Mokiem et al. 2006, 2007) and 100 narrow-lined early B-type stars (Hunter et al. 2006; Trundle et al. 2007) from the same survey, providing a sample of ~400 early-type objects. Results: Comparison of the rotational velocities with evolutionary tracks suggests that the end of core hydrogen burning occurs later than currently predicted and we argue for an extension of the evolutionary tracks. We also show that the large number of the luminous blue supergiants observed in the fields are unlikely to have directly evolved from main-sequence massive O-type stars as neither their low rotational velocities nor their position on the H-R diagram are predicted. We suggest that blue loops or mass-transfer binary systems may populate the blue supergiant regime. By comparing the rotational velocity distributions of the Magellanic Cloud stars to a similar Galactic sample, we find that (at 3s confidence level) massive stars (above 8 M?) in the SMC rotate faster than those in the solar neighbourhood. However there appears to be no significant difference between the rotational velocity distributions in the Galaxy and the LMC. We find that the v sin i distributions in the SMC and LMC can modelled with an intrinsic rotational velocity distribution that is a Gaussian peaking at 175 km s-1 (SMC) and 100 km s-1 (LMC) with a 1/e half width of 150 km s-1. We find that in NGC 346 in the SMC, the 10-25 M? main-sequence stars appear to rotate faster than their higher mass counterparts. It is not expected that O-type stars spin down significantly through angular momentum loss via stellar winds at SMC metallicity, hence this could be a reflection of mass dependent birth spin rates. Recently Yoon et al. (2006) have determined rates of GRBs by modelling rapidly rotating massive star progenitors. Our measured rotational velocity distribution for the 10-25 M? stars is peaked at slightly higher velocities than they assume, supporting the idea that GRBs could come from rapid rotators with initial masses as low as 14 M? at low metallicities.

Exact Multivariate Tests of Asset Pricing Models with Stable Asymmetric Distributions

In this paper, we propose exact inference procedures for asset pricing models that can be formulated in the framework of a multivariate linear regression (CAPM), allowing for stable error distributions. The normality assumption on the distribution of stock returns is usually rejected in empirical studies, due to excess kurtosis and asymmetry. To model such data, we propose a comprehensive statistical approach which allows for alternative - possibly asymmetric - heavy tailed distributions without the use of large-sample approximations. The methods suggested are based on Monte Carlo test techniques. Goodness-of-fit tests are formally incorporated to ensure that the error distributions considered are empirically sustainable, from which exact confidence sets for the unknown tail area and asymmetry parameters of the stable error distribution are derived. Tests for the efficiency of the market portfolio (zero intercepts) which explicitly allow for the presence of (unknown) nuisance parameter in the stable error distribution are derived. The methods proposed are applied to monthly returns on 12 portfolios of the New York Stock Exchange over the period 1926-1995 (5 year subperiods). We find that stable possibly skewed distributions provide statistically significant improvement in goodness-of-fit and lead to fewer rejections of the efficiency hypothesis.

Finite-Sample Simulation-Based Inference in VAR Models with Applications to Order Selection and Causality Testing

Statistical tests in vector autoregressive (VAR) models are typically based on large-sample approximations, involving the use of asymptotic distributions or bootstrap techniques. After documenting that such methods can be very misleading even with fairly large samples, especially when the number of lags or the number of equations is not small, we propose a general simulation-based technique that allows one to control completely the level of tests in parametric VAR models. In particular, we show that maximized Monte Carlo tests [Dufour (2002)] can provide provably exact tests for such models, whether they are stationary or integrated. Applications to order selection and causality testing are considered as special cases. The technique developed is applied to quarterly and monthly VAR models of the U.S. economy, comprising income, money, interest rates and prices, over the period 1965-1996.

A compound class of Weibull and power series distributions

In this paper we introduce the Weibull power series (WPS) class of distributions which is obtained by compounding Weibull and power series distributions where the compounding procedure follows same way that was previously carried out by Adamidis and Loukas (1998) This new class of distributions has as a particular case the two-parameter exponential power series (EPS) class of distributions (Chahkandi and Gawk 2009) which contains several lifetime models such as exponential geometric (Adamidis and Loukas 1998) exponential Poisson (Kus 2007) and exponential logarithmic (Tahmasbi and Rezaei 2008) distributions The hazard function of our class can be increasing decreasing and upside down bathtub shaped among others while the hazard function of an EPS distribution is only decreasing We obtain several properties of the WPS distributions such as moments order statistics estimation by maximum likelihood and inference for a large sample Furthermore the EM algorithm is also used to determine the maximum likelihood estimates of the parameters and we discuss maximum entropy characterizations under suitable constraints Special distributions are studied in some detail Applications to two real data sets are given to show the flexibility and potentiality of the new class of distributions (C) 2010 Elsevier B V All rights reserved

Improving IRT parameter estimates with small sample sizes: Evaluating the efficacy of a new data augmentation technique

The 3PL model is a flexible and widely used tool in assessment. However, it suffers from limitations due to its need for large sample sizes. This study introduces and evaluates the efficacy of a new sample size augmentation technique called Duplicate, Erase, and Replace (DupER) Augmentation through a simulation study. Data are augmented using several variations of DupER Augmentation (based on different imputation methodologies, deletion rates, and duplication rates), analyzed in BILOG-MG 3, and results are compared to those obtained from analyzing the raw data. Additional manipulated variables include test length and sample size. Estimates are compared using seven different evaluative criteria. Results are mixed and inconclusive. DupER augmented data tend to result in larger root mean squared errors (RMSEs) and lower correlations between estimates and parameters for both item and ability parameters. However, some DupER variations produce estimates that are much less biased than those obtained from the raw data alone. For one DupER variation, it was found that DupER produced better results for low-ability simulees and worse results for those with high abilities. Findings, limitations, and recommendations for future studies are discussed. Specific recommendations for future studies include the application of Duper Augmentation (1) to empirical data, (2) with additional IRT models, and (3) the analysis of the efficacy of the procedure for different item and ability parameter distributions.

Validation of the Drinking Refusal Self-Efficacy Questionnaire - Revised in an Adolescent Sample (DRSEQ-RA)

Adolescent drinking is a significant issue yet valid psychometric tools designed for this group are scarce. The Drinking Refusal Self-Efficacy Questionnaire—Revised Adolescent Version (DRSEQ-RA) is designed to assess an individual's belief in their ability to resist drinking alcohol. The original DRSEQ-R consists of three factors reflecting social pressure refusal self-efficacy, opportunistic refusal self-efficacy and emotional relief refusal self-efficacy. A large sample of 2020 adolescents aged between 12 and 19 years completed the DRSEQ and measures of alcohol consumption in small groups. Using confirmatory factor analysis, the three factor structure was confirmed. All three factors were negatively correlated with both frequency and volume of alcohol consumption. Drinkers reported lower drinking refusal self-efficacy than non-drinkers. Taken together, these results suggest that the adolescent version of the Drinking Refusal Self-Efficacy Questionnaire (DRSEQ-RA) is a reliable and valid measure of drinking refusal self-efficacy.

An application of the Driver Behaviour Questionnaire in a large Australian organisational fleeting setting : can it predict crashes and demerit point loss?

This study reports on the utilisation of the Manchester Driver Behaviour Questionnaire (DBQ) to examine the self-reported driving behaviours of a large sample of Australian fleet drivers (N = 3414). Surveys were completed by employees before they commenced a one day safety workshop intervention. Factor analysis techniques identified a three factor solution similar to previous research, which was comprised of: (a) errors, (b) highway-code violations and (c) aggressive driving violations. Two items traditionally related with highway-code violations were found to be associated with aggressive driving behaviours among the current sample. Multivariate analyses revealed that exposure to the road, errors and self-reported offences predicted crashes at work in the last 12 months, while gender, highway violations and crashes predicted offences incurred while at work. Importantly, those who received more fines at work were at an increased risk of crashing the work vehicle. However, overall, the DBQ demonstrated limited efficacy at predicting these two outcomes. This paper outlines the major findings of the study in regards to identifying and predicting aberrant driving behaviours and also highlights implications regarding the future utilisation of the DBQ within fleet settings.

Considering gambling involvement in the understanding of problem gambling: A large cross-sectional study of an Australian population

Instead of regarding a particular type of gambling activity (for example, electronic gambling machines, table games) as an isolated factor for problem gambling, recent research suggests that gambling involvement (for example, as measured by the number of different types of gambling activities played) should also be considered. Using a large sample of the Victorian adult population, this study found that the strength of association between problem gambling and the type of gambling reduced after adjusting for gambling involvement. This finding supports recent research that gambling involvement is an important factor in assessing the risk of problem gambling. The study also provides insights into the measurements of gambling involvement and provides alternative statistical modelling to analyse problem gambling.

Why do birds participate in mixed-species foraging flocks? A large-scale synthesis

Mixed-species flocks of foraging birds have been documented from terrestrial habitats all over the world and are thought to form for either improved feeding efficiency or better protection from predators. Two kinds of flock participants are recognized: those that join other species ('followers') and are therefore likely to be the recipients of the benefits of flock participation and those that are joined ('leaders'). Through comparative analyses, using a large sample of flocks from around the world, we show that (1) 'followers' tend to be smaller, more insectivorous, and feed in higher strata than matched species that participate in flocks to a lesser extent and (2) 'leaders' tend to be cooperative breeders more often than matched species that are not known to lead flocks. Furthermore, meta-analyses of published results from across the world showed that bird species in terrestrial mixed-species flocks increase foraging rates and reduce vigilance compared to when they are solitary or in conspecific groups. Moreover, the increase in foraging rates is seen only with flock followers and not flock leaders. These findings suggest a role for predation in the evolution of mixed-species flocking. Species that are vulnerable to predation follow species whose vigilance they can exploit. By doing so, they are able to reduce their own vigilance and forage at higher rates. (C) 2009 The Association for the Study of Animal Behaviour. Published by Elsevier Ltd. All rights reserved.

Statistical Simulation of Rarefied Gas Flows in Micro-Channels

Rarefied gas flows through micro-channels are simulated using particle approaches, named as the information preservation (IP) method and the direct simulation Monte Carlo (DSMC) method. In simulating the low speed flows in long micro-channels the DSMC method encounters the problem of large sample size demand and the difficulty of regulating boundary conditions at the inlet and outlet. Some important computational issues in the calculation of long micro-channel flows by using the IP method, such as the use the conservative form of the mass conservation equation to guarantee the adjustment of the inlet and outlet boundary conditions and the super-relaxation scheme to accelerate the convergence process, are addressed. Stream-wise pressure distributions and mass fluxes through micro-channels given by the IP method agree well with experimental data measured in long micro-channels by Pong et al. (with a height to length ratio of 1.2:3000), Shih et al. (l.2:4800), Arkilic et al. and Arkilic (l.3:7500), respectively. The famous Knudsen minimum of normalized mass flux is observed in IP and DSMC calculations of a short micro-channel over the entire flow regime from continuum to free molecular, whereas the slip Navier-Stokes solution fails to predict it.

Parametric and non-parametric estimates of willingness to pay for forest recreation in Northern Ireland: A discrete choice contingent valuation study with follow-ups

In this study we show that forest areas contribute significantly to the estimated benefits from om outdoor recreation in Northern Ireland. Secondly we provide empirical evidence of the gains in the statistical efficiency of both benefit and parameter estimates obtained by analysing follow-up responses with Double Bounded interval data analysis. As these gains are considerable, it is clearly worth considering this method in CVM survey design even when moderately large sample sizes are used. Finally we demonstrate that estimates of means and medians of WTP distributions for access to forest recreation show plausible magnitude, are consistent with previous UK studies, and converge across parametric and non-parametic methods of estimation.