The generalized odd log-logistic family of distributions: properties,regression models and applications

We propose a new class of continuous distributions with two extra shape parameters named the generalized odd log-logistic family of distributions. The proposed family contains as special cases the proportional reversed hazard rate and odd log-logistic classes. Its density function can be expressed as a linear combination of exponentiated densities based on the same baseline distribution. Some of its mathematical properties including ordinary moments, quantile and generating functions, two entropy measures and order statistics are obtained. We derive a power series for the quantile function. We discuss the method of maximum likelihood to estimate the model parameters. We study the behaviour of the estimators by means of Monte Carlo simulations. We introduce the log-odd log-logistic Weibull regression model with censored data based on the odd log-logistic-Weibull distribution. The importance of the new family is illustrated using three real data sets. These applications indicate that this family can provide better fits than other well-known classes of distributions. The beauty and importance of the proposed family lies in its ability to model different types of real data.     

Gini index based goodness-of-fit test for the logistic distribution

To model growth curves in survival analysis and biological studies the logistic distribution has been widely used. In this article, we propose a goodness-of-fit test for the logistic distribution based on an estimate of the Gini index. The exact distribution of the proposed test statistic and also its asymptotic distribution are presented. In order to compute the proposed test statistic, parameters of the logistic distribution are estimated by approximate maximum likelihood estimators (AMLEs), which are simple explicit estimators. Through Monte Carlo simulations, power comparisons of the proposed test with some known competing tests are carried. Finally, an illustrative example is presented and analyzed.     

The Weibull–Dagum distribution: Properties and applications

ABSTRACT

In this article, we define a new lifetime model called the Weibull–Dagum distribution. The proposed model is based on the Weibull–G class. It can also be defined by a simple transformation of the Weibull random variable. Its density function is very flexible and can be symmetrical, left-skewed, right-skewed, and reversed-J shaped. It has constant, increasing, decreasing, upside-down bathtub, bathtub, and reversed-J shaped hazard rate. Various structural properties are derived including explicit expressions for the quantile function, ordinary and incomplete moments, and probability weighted moments. We also provide explicit expressions for the Rényi and q-entropies. We derive the density function of the order statistics as a mixture of Dagum densities. We use maximum likelihood to estimate the model parameters and illustrate the potentiality of the new model by means of a simulation study and two applications to real data. In fact, the proposed model outperforms the beta-Dagum, McDonald–Dagum, and Dagum models in these applications.     

The odd power cauchy family of distributions: properties,regression models and applications

We study some mathematical properties of a new generator of continuous distributions with one extra parameter called the odd power Cauchy family including asymptotics, linear representation, moments, quantile and generating functions, entropies, order statistics and extreme values. We introduce two bivariate extensions of the new family. The maximum likelihood method is discussed to estimate the model parameters by means of a Monte Carlo simulation study. We define a new log-odd power Cauchy–Weibull regression model. The usefulness of the proposed models is proved empirically by means of three real data sets.     

Testing the validity of the exponential model for hybrid Type-I censored data

The exponential distribution has been used in life-testing and reliability studies. In this article, we first express the entropy of Type-I hybrid censoring scheme in terms of hazard function and provide an estimate of the entropy of Type-I hybrid censored data. Then, we construct a goodness-of-fit test statistic based on Kullback–Leibler information for Type-I hybrid censored data. The test statistic is used to test for exponentiality. A Monte Carlo simulation is conducted to obtain the power of the proposed test against various alternatives. Finally, a data example is presented for illustrative purpose.     

Moments of nonparametric probability density functions of entropy estimators applied to testing the inverse Gaussian distribution

The inverse Gaussian (IG) distribution is widely used to model data and then it is important to develop efficient goodness of fit tests for this distribution. In this article, we introduce some new test statistics for examining the IG goodness of fit based on correcting moments of nonparametric probability density functions of entropy estimators. These tests are consistent against all alternatives. Critical points and power of the tests are explored by simulation. We show that the proposed tests are more powerful than competitor tests. Finally, the proposed tests are illustrated by real data examples.     

Comparing different propensity score estimation methods for estimating the marginal causal effect through standardization to propensity scores

Hernan and Robins proposed a method for calculating marginal causal effect of treatment using standardization to propensity scores.

?Data adaptive methods have been suggested as alternatives to logistic regression for the estimation of propensity scores. We examined the performance of various data mining methods using simulated data. The estimators' performance was evaluated in terms of relative bias, 95% CI coverage rate, and mean squared error.

?All methods (except CART and GBM) displayed generally acceptable performance. However, under the conditions of moderate non-additivity and moderate nonlinearity, ANN and SL outperformed logistic regression with better bias reduction and more consistent 95% CI coverage.     

本地社区的角色:对知识区域发展理论的修正

到了21世纪初,知识作为城乡区域发展的关键因素的重要意义已经完全确立,然而,作为知识型发展赖以确立的具体机制和体制关系的研究却只是在近些年才开始而且还有些欠缺.本文主要基于"三重螺旋模式"(Etzkowitz & Klofsten,2005),这种模式提出,大学、企业和政府是所有知识型发展的关键因素.本文是澳大利亚昆士兰州知识型社区发展的个案研究,考察了"三重螺旋模式"在地方和区域之间相互关系中的作用.表明了作为创新基地的社区在各关键因素的相互作用中的核心作用,并提出了"四重螺旋模式"的设想.在"四重螺旋模式"中,社区在新经济构建过程中与企业、大学、政府具有同等重要的作用.结论:只有社区,企业,大学,政府四个因素有机融合,共同作用,知识型发展才会得到提高.     

Longitudinal data analysis in the presence of informative sampling: weighted distribution or joint modelling

ABSTRACT

Weighted distributions, as an example of informative sampling, work appropriately under the missing at random mechanism since they neglect missing values and only completely observed subjects are used in the study plan. However, length-biased distributions, as a special case of weighted distributions, remove the subjects with short length deliberately, which surely meet the missing not at random mechanism. Accordingly, applying length-biased distributions jeopardizes the results by producing biased estimates. Hence, an alternate method has to be used such that the results are improved by means of valid inferences. We propose methods that are based on weighted distributions and joint modelling procedure and compare them in analysing longitudinal data. After introducing three methods in use, a set of simulation studies and analysis of two real longitudinal datasets affirm our claim.     

On the estimation of extropy

Recently, Lad, Sanfilippo, and Agro [(2015), ‘Extropy: Complementary Dual of Entropy’, Statistical Science, 30, 40–58.] showed the measure of entropy has a complementary dual, which is termed extropy. The present article introduces some estimators of the extropy of a continuous random variable. Properties of the proposed estimators are stated, and comparisons are made with Qiu and Jia’s estimators [(2018a), ‘Extropy Estimators with Applications in Testing uniformity’, Journal of Nonparametric Statistics, 30, 182–196]. The results indicate that the proposed estimators have a smaller mean squared error than competing estimators. A real example is presented and analysed.