Confirmatory and Structural Categorical Latent Variables Models

The paper proposes a general framework for modeling multiple categorical latent variables (MCLV). The MCLV models extend latent class analysis or latent transition analysis to allow flexible measurement and structural components between endogenous categorical latent variables and exogenous covariates. Therefore, modeling frameworks in conventional structural equation models, for example, CFA and MIMIC models are feasible in the MCLV circumstances. Parameter estimations for the MCLV models are performed by using generalized expectation–maximization (E–M) algorithm. In addition, the adjusted Bayesian information criterion provides help for model selections. A substantive study of reading development is analyzed to illustrate the feasibility of MCLV models.     

Log–Linear Mixed Models for Categorical Data

A method for construction of mixed models for categorical responses is described and its use is exemplified for three experimental designs: the repeated–measurements design, the change–over design and a design used for measurement of inter–observer agreement. The method may be viewed as an extension of the standard log–linear model methodology.     

Disclosure‐protected Inference Using Generalised Linear Models

Vast amounts of data that could be used in the development and evaluation of policy for the benefit of society are collected by statistical agencies. It is therefore no surprise that there is very strong demand from analysts, within business, government, universities and other organisations, to access such data. When allowing access to micro‐data, a statistical agency is obliged, often legally, to ensure that it is unlikely to result in the disclosure of information about a particular person or organisation. Managing the risk of disclosure is referred to as statistical disclosure control (SDC). This paper describes an approach to SDC for output from analysis using generalised linear models, including estimates of regression parameters and their variances, diagnostic statistics and plots. The Australian Bureau of Statistics has implemented the approach in a remote analysis system, which returns analysis output from remotely submitted queries. A framework for measuring disclosure risk associated with a remote server is proposed. The disclosure risk and utility of approach are measured in two real‐life case studies and in simulation.     

Continuous Dependent Variables and Organizational Ecology: Toward a more Perfect Union

In this paper, I review all previously published organizational ecology research which utilizes continuous dependent variables. I unearth twenty-one such studies, half of which were published within the past four years. The broadening array of dependent variables in this field is a most welcome development. However, each of these papers has at least one methodological limitation, in specification of cross-unit effects and/or controls for autocorrelation. Perhaps the most serious problem is the assertion that the fixed effects research design solves the problem of autocorrelation. I demonstrate that this assertion is untrue. I conclude with advice on the proper way to model continuous dependent variables in organizational ecology research, as follows: (1) Consider omitting all organizations which do not exist for more time periods than the number of independent variables. (2) Test for autocorrelation, report the results, and correct for autocorrelation if the test indicates that it is a problem. (3) Use a fixed effects model, and justify it based on the nonrandomness of the data.     

Scaling for Residual Variance Components of Ordered Category Responses in Generalised Linear Mixed Multilevel Models

A method is proposed that enables changes in variance components to be computed from the results of fitting ordered response generalised models with multilevel and random effects. This deals with the rescaling of the response that occurs as we add new features to a developing model.     

Diagnostic Tests of Cross‐section Independence for Limited Dependent Variable Panel Data Models*

This article considers the problem of testing for cross‐section independence in limited dependent variable panel data models. It derives a Lagrangian multiplier (LM) test and shows that in terms of generalized residuals of Gourieroux et al. (1987) it reduces to the LM test of Breusch and Pagan (1980) . Because of the tendency of the LM test to over‐reject in panels with large N (cross‐section dimension), we also consider the application of the cross‐section dependence test (CD) proposed by Pesaran (2004) . In Monte Carlo experiments it emerges that for most combinations of N and T the CD test is correctly sized, whereas the validity of the LM test requires T (time series dimension) to be quite large relative to N. We illustrate the cross‐sectional independence tests with an application to a probit panel data model of roll‐call votes in the US Congress and find that the votes display a significant degree of cross‐section dependence.     

Bootstrap J-Test for Panel Data Models with Spatially Dependent Error Components,a Spatial Lag and Additional Endogenous Variables

We develop a bootstrap J-test method for testing a panel model against one non-nested alternative when the competing specifications are estimated by Feasible Generalised Spatial Two Stage Least Squares/Generalised Method of Moments (FGS2SLS/GMM). Both models incorporate spatially correlated error components, thus accounting for spatial heterogeneity via random effects, and accommodate endogenous regressors other than the spatially lagged dependent variable. The proposed scheme is applied to a testing problem involving non-nested wage equations as motivated by the Wage Curve literature and the New Economic Geography theory. Results show that our bootstrap test is a reliable and effective procedure for correcting asymptotic reference critical values and distinguishing between the two rival hypotheses.     

Comparison of Sampling Schemes for Dynamic Linear Models

Hyperparameter estimation in dynamic linear models leads to inference that is not available analytically. Recently, the most common approach is through MCMC approximations. A number of sampling schemes that have been proposed in the literature are compared. They basically differ in their blocking structure. In this paper, comparison between the most common schemes is performed in terms of different efficiency criteria, including efficiency ratio and processing time. A sample of time series was simulated to reflect different relevant features such as series length and system volatility.     

Modelling Hospital Admission and Length of Stay by Means of Generalised Count Data Models

For a large heterogeneous group of patients, we analyse probabilities of hospital admission and distributional properties of lengths of hospital stay conditional on individual determinants. Bayesian structured additive regression models for zero‐inflated and overdispersed count data are employed. In addition, the framework is extended towards hurdle specifications, providing an alternative approach to cover particularly large frequencies of zero quotes in count data. As a specific merit, the model class considered embeds linear and nonlinear effects of covariates on all distribution parameters. Linear effects indicate that the quantity and severity of prior illness are positively correlated with the risk of hospital admission, while medical prevention (in the form of general practice visits) and rehabilitation reduce the expected length of future hospital stays. Flexible nonlinear response patterns are diagnosed for age and an indicator of a patients' socioeconomic status. We find that social deprivation exhibits a positive impact on the risk of admission and a negative effect on the expected length of future hospital stays of admitted patients. Copyright © 2015 John Wiley & Sons, Ltd.     

Testing for Heteroskedasticity and Predictive Failure in Linear Regression Models*

It is argued that, when researchers wish to carry out a Chow test of the significance of prediction errors, it is necessary to assume homoskedasticity because standard results on heteroskedasticity‐robust tests are not available. The effects of heteroskedasticity on the Chow prediction error test are examined. The implementation of tests for heteroskedasticity is discussed, with the case in which the regressors include dummy variables for prediction error tests receiving special attention. Monte Carlo results are reported.     

Generalized Forecast Error Variance Decomposition for Linear and Nonlinear Multivariate Models

We propose a new generalized forecast error variance decomposition with the attractive property that the proportions of the impact accounted for by innovations in each variable sum to unity. Our decomposition is based on the generalized impulse response function, and it can easily be obtained by simulation. The new decomposition is illustrated in an empirical application to US output growth and interest rate spread data.     

一类变库存费且存货影响销售率的EOQ模型

从实际背景出发,在变库存费和存货影响销售率条件下,分别就最小化平均费用和最大化平均利润讨论了具有Ramp型需求的变质性物品的EOQ模型,给出了无短缺量拖后和部分拖后条件下最佳订购批量的求解方案,数值例子对两个不同目标下的最佳订购批量及各项相关费用进行了比较,揭示了变库存费和存货影响销售率对最优订货策略的影响。     

A Pairwise Difference Estimator for Partially Linear Spatial Autoregressive Models

Abstract

We propose a pairwise difference estimator for partially linear spatial autoregressive models with heteroscedastic or/and spatially correlated error terms. In comparison with other competing estimators, e.g. the profile QMLE (Su & Jin, 2010) and the semiparametric GMM estimator (Su, 2012), our estimator has the advantage of computational simplicity particularly when one is interested in estimating the finite dimensional parameters in the model. Large sample properties of the estimator are formally established and a consistent estimate of the asymptotic CV matrix is provided. We then use the method to robustly estimate the effect of strategic interaction in deciding local school spending.

RÉSUMÉ nous proposons un estimateur de différence par paire pour des modèles autorégressifs spatiaux partiellement linéaires, avec conditions d'erreurs à corrélation hétéroscédastique et/ou spatiale. Par rapport à d'autres estimateurs possibles, p.ex. le QMLE de profil (Su & Jin, 2010), et l'estimateur GMM semi-paramétrique (Su, 2012), notre estimateur présente l'avantage de la simplicité du calcul, notamment lorsque l'on s'intéresse à l'estimation des paramètres dimensionnels finis dans le modèle. Les propriétés de grand échantillon de l'estimateur sont établies officiellement, et une estimation homogène de la matrice CV asymptotique est fournie. Nous utilisons ensuite la méthode d'estimation consistante de l'effet de l'interaction stratégique dans les décisions sur les dépenses des écoles locales.

EXTRACTO Proponemos un estimador de diferencias por pares para modelos autorregresivos espaciales parcialmente lineales con términos de error heteroscedásticos o/y espacialmente correlacionados. En comparación con otros estimadores competidores, p. ej., QMLE (Su & Jin, 2010) y el estimador GMM semiparamétrico (Su, 2012), nuestro estimador tiene la ventaja de la simplicidad computacional, particularmente cuando uno está interesado en estimar los parámetros dimensionales finitos en el modelo. Las propiedades de muestras grandes del estimador se establecen formalmente y se proporciona una estimación constante de la matriz CV asimptótica. Seguidamente, utilizamos el método para estimar contundentemente el efecto de la interacción estratégica para decidir el gasto de escuelas locales.

摘要 : 我们对部分线性空间自回归模型提出了–种成对差异估计量, 采用异方差或/和空间相关误差项。与其他估计量, 例如包络准最大似然估计 (Su & Jin, 2010) 和半参量 GMM 估计 (Su, 2012) 相比, 我们的估计量具有计算复杂度低的优势, 尤其是用于估计模型中的有限维度参数时。我们已经建立了这种估计方法的大采样样本, 还提供对渐近线 CV 矩阵的–致估计。接着, 使用这种方法, 我们透彻分析了政策对本地学校支出的影响。     

Estimated Precision for Predictions from Generalized Linear Models in Sociological Research

In this paper I present a general method forconstructing confidence intervals for predictionsfrom the generalized linear model in sociologicalresearch. I demonstrate that the method used forconstructing confidence intervals for predictions inclassical linear models is indeed a special case ofthe method for generalized linear models. I examinefour such models – the binary logit, the binaryprobit, the ordinal logit, and the Poissonregression model – to construct confidence intervalsfor predicted values in the form of probability,odds, Z score, or event count. The estimatedconfidence interval for an event prediction, whenapplied judiciously, can give the researcher usefulinformation and an estimated measure of precisionfor the prediction so that interpretation ofestimates from the generalized linear model becomeseasier.     

Multiple Local Maxima in Restricted Likelihoods and Posterior Distributions for Mixed Linear Models

Scattered reports of multiple maxima in posterior distributions or likelihoods for mixed linear models appear throughout the literature. Less scrutinised is the restricted likelihood, which is the posterior distribution for a specific prior distribution. This paper surveys existing literature and proposes a unifying framework for understanding multiple maxima. For those problems with covariance structures that are diagonalisable in a specific sense, the restricted likelihood can be viewed as a generalised linear model with gamma errors, identity link and a prior distribution on the error variance. The generalised linear model portion of the restricted likelihood can be made to conflict with the portion of the restricted likelihood that functions like a prior distribution on the error variance, giving two local maxima in the restricted likelihood. Applying in addition an explicit conjugate prior distribution to variance parameters permits a second local maximum in the marginal posterior distribution even if the likelihood contribution has a single maximum. Moreover, reparameterisation from variance to precision can change the posterior modality; the converse also is true. Modellers should beware of these potential pitfalls when selecting prior distributions or using peak‐finding algorithms to estimate parameters.     

Three Corrected Score Tests for Generalized Linear Models with Dispersion Covariates

We develop three corrected score tests for generalized linear models with dispersion covariates, thus generalizing the results of Cordeiro , Ferrari and Paula (1993) and Cribari-Neto and Ferrari (1995) . We present, in matrix notation, general formulae for the coefficients which define the corrected statistics. The formulae only require simple operations on matrices and can be used to obtain analytically closed-form corrections for score test statistics in a variety of special generalized linear models with dispersion covariates. They also have advantages for numerical purposes since our formulae are readily computable using a language supporting numerical linear algebra. Two examples, namely, iid sampling without covariates on the mean or dispersion parameter oand one-way classification models, are given. We also present some simulations where the three corrected tests perform better than the usual score test, the likelihood ratio test and its Bartlett corrected version. Finally, we present a numerical example for a data set discussed by Simonoff and Tsai (1994) .     

浅析沪昆客专连续梁施工线性监控技术

沪昆客专跨焦柳铁路特大桥主跨为1-(80.6+128+80.6)m大跨连续梁,介绍沪昆客专100m以上大跨连续梁线性监控施工的成功经验。同时在施工过程采用了全过程有效的线性监控方法,是保证大跨度连续梁成功施工的关键。     

Asymptotics of the Non-parametric Function for B-splines-based Estimation in Partially Linear Models

We consider least squares method for partially linear models based on polynomial splines. We derive the asymptotic property for the estimator, focusing on the estimation of the non-parametric function, in particular whether and how the estimation of the linear part will affect the non-parametric part (the converse relation, that is, how the linear part will be affected by the non-parametric part is much better known, which we will also review). One important goal along the way is to clarify the role of projection in semiparametric models, which was nevertheless a classical trick for proving the asymptotic normality of the linear part. A crucial question we try to answer is whether projection plays any role in the estimation of the non-parametric function. The answer is both positive and negative depending on the direction along which to assess asymptotic normality. The style of writing of the paper is somewhat expository, and it also contains several new results not found in the current literature. Finally, we demonstrate in our numerical studies that construction of the pointwise confidence intervals for the non-parametric function motivated by our theory improves upon those constructed by pretending the linear part is known.