Conditional statistical inference and quantification of relevance

Summary. We argue that it can be fruitful to take a predictive view on notions such as the precision of a point estimator and the confidence of an interval estimator in frequentist inference. This predictive approach has implications for conditional inference, because it immediately allows a quantification of the concept of relevance for conditional inference. Conditioning on an ancillary statistic makes inference more relevant in this sense, provided that the ancillary is a precision index. Not all ancillary statistics satisfy this demand. We discuss the problem of choice between alternative ancillary statistics. The approach also has implications for the best choice of variance estimator, taking account of correlations with the squared error of estimation itself. The theory is illustrated by numerous examples, many of which are classical.     

Regression Kink With an Unknown Threshold

This article explores estimation and inference in a regression kink model with an unknown threshold. A regression kink model (or continuous threshold model) is a threshold regression constrained to be everywhere continuous with a kink at an unknown threshold. We present methods for estimation, to test for the presence of the threshold, for inference on the regression parameters, and for inference on the regression function. A novel finding is that inference on the regression function is nonstandard since the regression function is a nondifferentiable function of the parameters. We apply recently developed methods for inference on nondifferentiable functions. The theory is illustrated by an application to the growth and debt problem introduced by Reinhart and Rogoff, using their long-span time-series for the United States.     

Renewal theory and the sequential design of experiments with two states of nature

In the sequential design of experiments in experimentel is sequentially performing experiments to help him make an inference about the true state of nature. Using results from renewal twenty at derive approximations for the operations characteristics and average sample numbers for this problem when there are two states of nature.

A critical problem in the sequential design of experiments is finding a good procedure. We investigate a Bayesian formulation of this problem and use our approximations to approximate the Bayes risk. Minimization of this approximate Bayes risk over procedures is discussed as a method of finding a good procedure, but difficulties are encountered due to the discrete time character of the sequential process. To avoid these difficulties, we consider minimization of an approximation related to a diffusion process. This leads to a simple rule for the sequential selection of experiments.     

On the existence and uniqueness of maximizers of two likelihood functions

While applying theclassical maximum likelihood method for a certain statistical inference problem, Smith and Weissman [5] have noted that there are conditions under which the likelihood function may be unbounded above or may not possess local maximizers. Ariyawansà and Templeton [1] have derived inference procedures for this problem using the theory of structural inference [2,3,4]. Based on numerical experience, and without proof, they state that the resulting likelihood functions possess unique, global maximizers, even in instances where the classical maximum likelihood method fails in the above sense. In this paper, we prove that under quite mild conditions, these likelihood functions that result from the application of the theory of structural inference are well-behaved, and possess unique, global maximizers. This research was supported in part by the Applied Mathematical Sciences subprogram of the U.S. Department of Energy under contract W-31-109-Eng-38 while the author was visiting the Mathematics and Computer Science Division of Argonne National Laboratory, Argonne, Illinois.     

Test and prediction in factorial models with independent variance estimates

The multiple inference character of several tests in the same application is usually taken into consideration by requiring that the tests have a multiple level of significance. Also, a prediction problem in an application with several possible predictor variables requires that the multiple inference character of the problem be considered. This is not being done in the methods commonly used to choose predictor variables. Here, we discuss both the test and prediction methods in two-level factorial designs and suggest a principle for choosing variables which is based on multiple inference thinking. By an example use demonstrated that the principle proposed leads to the use of fewer prediction variables than does the Akaike method.     

Structural inference for parameters of a power function distribution

We consider the problem of statistical inference on the parameters of the three parameter power function distribution based on a full unordered sample of observations or a type II censored ordered sample of observations. The inference philosophy used is the theory of structural inference. We state inference procedures which yield inferential statements about the three unknown parameters. A numerical example is given to illustrate these procedures. It is seen that within the context of this example the inference procedures of this paper do not encounter certain difficulties associated with classical maximum likelihood based procedures. Indeed it has been our numerical experience that this behavior is typical within the context of that subclass of the three parameter power function distribution to which this example belongs.     

Likelihood methods in randomized trials with noncompliance and subsequent nonresponse

This article considers likelihood methods for estimating the causal effect of treatment assignment for a two-armed randomized trial assuming all-or-none treatment noncompliance and allowing for subsequent nonresponse. We first derive the observed data likelihood function as a closed form expression of the parameter given the observed data where both response and compliance state are treated as variables with missing values. Then we describe an iterative procedure which maximizes the observed data likelihood function directly to compute a maximum likelihood estimator (MLE) of the causal effect of treatment assignment. Closed form expressions at each iterative step are provided. Finally we compare the MLE with an alternative estimator where the probability distribution of the compliance state is estimated independent of the response and its missingness mechanism. Our work indicates that direct maximum likelihood inference is straightforward for this problem. Extensive simulation studies are provided to examine the finite sample performance of the proposed methods.     

Estimating ordered parameters by linear programming

There are many models that require the estimation of a set of ordered parameters. For example, multivariate analysis of variance often is formulated as testing for the equality of the parameters versus an ordered alternative. This problem, referred to as isotonic inference, constrained inference, or isotonic regression, has led to the development of general solutions, not often easy to apply in special models. In this expository paper, we study the special case of a separable convex quadratic programming problem for which the optimality conditions lead to a readily solved linear complementarity problem in the Lagrange multipliers, and subsequently to an equivalent linear programming problem, whose solution can be used to recover the solution of the original isotonic problem. The method can be applied to estimating ordered correlations, ordered binomial probabilities, ordered Poisson parameters, ordered exponential scale parameters, or ordered risk differences.     

大数据背景下网络调查样本的建模推断问题研究——以广义Boosted模型的倾向得分推断为例

随着大数据和网络的不断发展,网络调查越来越广泛,大部分网络调查样本属于非概率样本,难以采用传统的抽样推断理论进行推断,如何解决网络调查样本的推断问题是大数据背景下网络调查发展的迫切需求。本文首次从建模的角度提出了解决该问题的基本思路：一是入样概率的建模推断,可以考虑构建基于机器学习与变量选择的倾向得分模型来估计入样概率推断总体;二是目标变量的建模推断,可以考虑直接对目标变量建立参数、非参数或半参数超总体模型进行估计;三是入样概率与目标变量的双重建模推断,可以考虑进行倾向得分模型与超总体模型的加权估计与混合推断。最后,以基于广义Boosted模型的入样概率建模推断为例演示了具体解决方法。     

Bimodality based on the generalized skew-normal distribution

This paper focuses on the development of a new extension of the generalized skew-normal distribution introduced in Gómez et al. [Generalized skew-normal models: properties and inference. Statistics. 2006;40(6):495–505]. To produce the generalization a new parameter is introduced, the signal of which has the flexibility of yielding unimodal as well as bimodal distributions. We study its properties, derive a stochastic representation and state some expressions that facilitate moments derivation. Maximum likelihood is implemented via the EM algorithm which is based on the stochastic representation derived. We show that the Fisher information matrix is singular and discuss ways of getting round this problem. An illustration using real data reveals that the model can capture well special data features such as bimodality and asymmetry.     

Likelihood-free inference via classification

Increasingly complex generative models are being used across disciplines as they allow for realistic characterization of data, but a common difficulty with them is the prohibitively large computational cost to evaluate the likelihood function and thus to perform likelihood-based statistical inference. A likelihood-free inference framework has emerged where the parameters are identified by finding values that yield simulated data resembling the observed data. While widely applicable, a major difficulty in this framework is how to measure the discrepancy between the simulated and observed data. Transforming the original problem into a problem of classifying the data into simulated versus observed, we find that classification accuracy can be used to assess the discrepancy. The complete arsenal of classification methods becomes thereby available for inference of intractable generative models. We validate our approach using theory and simulations for both point estimation and Bayesian inference, and demonstrate its use on real data by inferring an individual-based epidemiological model for bacterial infections in child care centers.     

Statistical inference for discretely observed Markov jump processes

Summary.  Likelihood inference for discretely observed Markov jump processes with finite state space is investigated. The existence and uniqueness of the maximum likelihood estimator of the intensity matrix are investigated. This topic is closely related to the imbedding problem for Markov chains. It is demonstrated that the maximum likelihood estimator can be found either by the EM algorithm or by a Markov chain Monte Carlo procedure. When the maximum likelihood estimator does not exist, an estimator can be obtained by using a penalized likelihood function or by the Markov chain Monte Carlo procedure with a suitable prior. The methodology and its implementation are illustrated by examples and simulation studies.     

Improper priors for translation families

We consider the problem of inference when sampling from a translation family with an improper prior. Properties of the formal Bayes inference will be studied. We give conditions (on the prior and/or the family) guaranteeing the HS-coherence (see Heath and Sudderth, Ann. Statist. 6 (1978), 333–345) of the formal Bayes posterior. Since HS-coherence is equivalent to being a posterior of a finitely additive prior, all coherence results imply the existence of a finitely additive prior which has the formal Bayes inference as a posterior.     

A note on predictive inference for multivariate elliptically contoured distributions

The prediction problem is considered for the multivariate regression model with an elliptically contoured error distribution. We show that the predictive distribution under elliptical errors assumption is the same as that obtained under normally distributed error in both the Bayesian approach using an im-proper prior and the classical approach. This gives inference robustness with respect to departures from the reference case of independent sampling from the normal distribution.     

Asymptotic Inference for Jump Diffusions with State‐Dependent Intensity

We establish the local asymptotic normality property for a class of ergodic parametric jump‐diffusion processes with state‐dependent intensity and known volatility function sampled at high frequency. We prove that the inference problem about the drift and jump parameters is adaptive with respect to parameters in the volatility function that can be consistently estimated.     

Using Heteroscedasticity-Consistent Standard Errors for the Linear Regression Model with Correlated Regressors

The use of heteroscedasticity-consistent covariance matrix (HCCM) estimators is very common in practice to draw correct inference for the coefficients of a linear regression model with heteroscedastic errors. However, in addition to the problem of heteroscedasticity, linear regression models may also be plagued with some considerable degree of collinearity among the regressors when two or more regressors are considered. This situation causes many adverse effects on the least squares measures and alternatively, the ordinary ridge regression method is used as a common practice. But in the available literature, the problems of multicollinearity and heteroscedasticity have not been discussed as a combined issue especially, for the inference of the regression coefficients. The present article addresses the inference about the regression coefficients taking both the issues of multicollinearity and heteroscedasticity into account and suggests the use of HCCM estimators for the ridge regression. This article proposes t- and F-tests, based on these HCCM estimators, that perform adequately well in the numerical evaluation of the Monte Carlo simulations.     

Semiparametric Sieve-Type Generalized Least Squares Inference

This article considers the problem of statistical inference in linear regression models with dependent errors. A sieve-type generalized least squares (GLS) procedure is proposed based on an autoregressive approximation to the generating mechanism of the errors. The asymptotic properties of the sieve-type GLS estimator are established under general conditions, including mixingale-type conditions as well as conditions which allow for long-range dependence in the stochastic regressors and/or the errors. A Monte Carlo study examines the finite-sample properties of the method for testing regression hypotheses.     

Reliability estimation from field return data

In this article statistical inference for the failure time distribution of a product from “field return data”, that records the time between the product being shipped and returned for repair or replacement, is described. The problem that is addressed is that the data are not failure times because they also include the time that it took to ship and install the product and then to return it to the manufacturer for repair or replacement. The inference attempts to infer the distribution of time to failure (that is, from installation to failure) from the data when in addition there are separate data on the times from shipping to installation, and from failure to return. The method is illustrated with data from units installed in a telecommunications network. Our collaborator on writing this paper, Ed Lisay of Alcatel-Lucent, passed away suddenly in October 2008. As a tribute, we can state that Ed had an energetic and vigorous charisma in the application of his skills. He brought a sense of fun to his many interests, such as his achievement of becoming a master electrician. Ed is sadly missed by his family, friends and colleagues.     

Minimum Contrast Empirical Likelihood Inference of Discontinuity in Density*

Abstract

This article investigates the asymptotic properties of a simple empirical-likelihood-based inference method for discontinuity in density. The parameter of interest is a function of two one-sided limits of the probability density function at (possibly) two cut-off points. Our approach is based on the first-order conditions from a minimum contrast problem. We investigate both first-order and second-order properties of the proposed method. We characterize the leading coverage error of our inference method and propose a coverage-error-optimal (CE-optimal, hereafter) bandwidth selector. We show that the empirical likelihood ratio statistic is Bartlett correctable. An important special case is the manipulation testing problem in a regression discontinuity design (RDD), where the parameter of interest is the density difference at a known threshold. In RDD, the continuity of the density of the assignment variable at the threshold is considered as a “no-manipulation” behavioral assumption, which is a testable implication of an identifying condition for the local average treatment effect. When specialized to the manipulation testing problem, the CE-optimal bandwidth selector has an explicit form. We propose a data-driven CE-optimal bandwidth selector for use in practice. Results from Monte Carlo simulations are presented. Usefulness of our method is illustrated by an empirical example.     

Efficient Bayesian shape-restricted function estimation with constrained Gaussian process priors

Statistics and Computing - This article revisits the problem of Bayesian shape-restricted inference in the light of a recently developed approximate Gaussian process that admits an equivalent...