Observed Information Research Articles

The Azzalini Skew-t Information Matrix Evaluation and Use for Standard Error Calculations

The Azzalini skew-t distributions are popular because of their theoretical foundation and the availability of computational methods in the R package sn. One difficulty with this skew-t family is that the elements of the expected information matrix do not have closed form analytic formulas. Thus, we developed a numerical integration method of computing the expected information matrix in the R package skewtInfo. The accuracy of our expected information matrix calculation method was confirmed by comparing the result with that obtained using an observed information matrix for a very large sample size. A Monte Carlo study to evaluate the accuracy of the finite-sample standard errors obtained with our expected information matrix calculation method, for the case of three realistic skew-t parameter vectors, indicates that use of the expected information matrix results in standard errors as accurate as, and sometimes a little more accurate than, use of an observed information matrix.

The Topp Leone odd Lindley-G family of distributions : Properties and applications

We introduce a new class of continuous distributions called the Topp Leone odd Lindley-G family. Some mathematical properties of the new family such as; the raw and incomplete moments, moment generating function, stress strength model, Rényi entropy, probability weighted moments and order statistics are investigated. We discuss the maximum likelihood estimates and the observed information matrix for the model parameters. The potentiality of the new family is illustrated by means of three applications to real data sets.

Improved Wald Statistics for Item-Level Model Comparison in Diagnostic Classification Models.

Diagnostic classification models (DCMs) have been widely used in education, psychology, and many other disciplines. To select the most appropriate DCM for each item, the Wald test has been recommended. However, prior research has revealed that this test provides inflated Type I error rates. To address this problem, the authors propose to replace the asymptotic covariance matrix from the original version of the Wald statistic with a matrix obtained from improved computation methods. In this study, the Wald test based on the observed information matrix and the Wald test based on the sandwich-type matrix are proposed for item-level model comparisons and a simulation study is conducted to investigate their empirical behavior. Simulation results indicate that when the sample size is reasonably large ( ), the Type I error rates of the Wald test based on the sandwich-type matrix are accurate with adequate or excellent power under most of the simulation conditions.

The Transmuted Odd Lindley-G Family of Distributions


 
 
 
 We propose a new generator of univariate continuous distributions with two extra parameters called the transmuted odd-Lindley generator which extends the odd Lindely-G family introduced by Gomes-Silva et al. [1]. Some mathematical properties of the new generator such as, the ordinary and incomplete moments, generating function, stress strength model, Rényi entropy, probability weighted moments and order statistics are investigated. Certain characterisations of the proposed family are estimated. We discuss the maximum likelihood estimates and the observed information matrix for the model parameters. The potentiality of the new family is illustrated by means of five applications to real data sets.
 
 
 
 

The Stochastic Stationary Root Model

We propose and study the stochastic stationary root model. The model resembles the cointegrated VAR model but is novel in that: (i) the stationary relations follow a random coefficient autoregressive process, i.e., exhibhits heavy-tailed dynamics, and (ii) the system is observed with measurement error. Unlike the cointegrated VAR model, estimation and inference for the SSR model is complicated by a lack of closed-form expressions for the likelihood function and its derivatives. To overcome this, we introduce particle filter-based approximations of the log-likelihood function, sample score, and observed Information matrix. These enable us to approximate the ML estimator via stochastic approximation and to conduct inference via the approximated observed Information matrix. We conjecture the asymptotic properties of the ML estimator and conduct a simulation study to investigate the validity of the conjecture. Model diagnostics to assess model fit are considered. Finally, we present an empirical application to the 10-year government bond rates in Germany and Greece during the period from January 1999 to February 2018.

Exponentiated Power Lindley Logarithmic: Model, Properties and Applications

A new class of lifetime distributions is proposed. Closed form expressions are provided for the density, cumulative distribution, survival and hazard rate functions. Maximum likelihood estimation is discussed and formulas for the elements of the observed information matrix are provided. Simulation studies are conducted. Finally, two real data applications are given showing the flexibility and potentiality of the new distribution

Information matrix estimation procedures for cognitive diagnostic models.

Two new methods to estimate the asymptotic covariance matrix for marginal maximum likelihood estimation of cognitive diagnosis models (CDMs), the inverse of the observed information matrix and the sandwich-type estimator, are introduced. Unlike several previous covariance matrix estimators, the new methods take into account both the item and structural parameters. The relationships between the observed information matrix, the empirical cross-product information matrix, the sandwich-type covariance matrix and the two approaches proposed by de la Torre (2009, J. Educ. Behav. Stat., 34, 115) are discussed. Simulation results show that, for a correctly specified CDM and Q-matrix or with a slightly misspecified probability model, the observed information matrix and the sandwich-type covariance matrix exhibit good performance with respect to providing consistent standard errors of item parameter estimates. However, with substantial model misspecification only the sandwich-type covariance matrix exhibits robust performance.

Likelihood inference based on EM algorithm for the destructive length-biased Poisson cure rate model with Weibull lifetime

ABSTRACTIn this article, we consider the destructive length-biased Poisson cure rate model, proposed by Rodrigues et al., that presents a realistic and interesting interpretation of the biological mechanism for the recurrence of tumor in a competing causes scenario. Assuming the lifetime to follow the Weibull distribution and censoring mechanism to be non-informative, the necessary steps of the EM algorithm for the determination of the MLEs of the model parameters are developed here based on right censored data. The standard errors of the MLEs are obtained by inverting the observed information matrix. A simulation study is then carried out to examine the method of inference developed here. Finally, the proposed methodology is illustrated with a real melanoma dataset.

Numerical approximation of the observed information matrix with Oakes' identity.

An efficient and accurate numerical approximation methodology useful for obtaining the observed information matrix and subsequent asymptotic covariance matrix when fitting models with the EM algorithm is presented. The numerical approximation approach is compared to existing algorithms intended for the same purpose, and the computational benefits and accuracy of this new approach are highlighted. Instructive and real-world examples are included to demonstrate the methodology concretely, properties of the estimator are discussed in detail, and a Monte Carlo simulation study is included to investigate the behaviour of a multi-parameter item response theory model using three competing finite-difference algorithms.

An alternative two-parameter gamma generated family of distributions: properties and applications

Motivated by Torabi and Hedesh (2012), we propose a gamma extended family of distributions with two extra generator parameters. We present some special models and study general mathematical properties like asymptotes and shapes, ordinary and incomplete moments, generating and quantile functions, probability weighted moments, mean deviations, Bonferroni and Lorenz curves, asymptotic distributions of the extreme values, Shannon entropy, Renyi entropy, reliability and order statistics. The method of maximum likelihood is used to estimate the model parameters and the observed information matrix is determined. We de fine a new regression model based on the logarithm of the roposed distribution. The usefulness of the new models is proved empirically in three applications to real data.

The beta generalized Gompertz distribution

• A new continuous model called the beta generalized Gompertz distribution is introduced. • Some mathematical properties of the new model are studied. • The model parameters are estimated by maximum likelihood. • The usefulness of the new model is illustrated in an application to real data. A new five-parameter continuous model called the beta generalized Gompertz distribution is introduced and studied. This distribution contains the Gompertz, generalized Gompertz, beta Gompertz, generalized exponential, beta generalized exponential, exponential and beta exponential distributions as special sub-models. Some mathematical properties of the new model are derived. We show that the density function of the new distribution can be expressed as a linear combination of Gompertz densities. We obtain explicit expressions for the moments, moment generating function, quantile function, density function of the order statistics and their moments, mean deviations, Bonferroni and Lorenz curves and Rényi entropy. The model parameters are estimated by using the maximum likelihood method of estimation and the observed information matrix is determined. Finally, an application to real data set is given to illustrate the usefulness of the proposed model.

A new generalization of the gamma distribution with application to negatively skewed survival data

ABSTRACTWe propose a three-parameter distribution referred to as the reflected- shifted-truncated gamma (RSTG) distribution to model negatively skewed data. Various properties of the proposed distribution are derived. The estimation of the model parameters is approached by maximum likelihood methods and the observed information matrix is derived. Monte Carlo simulations are performed to compare the performances of the proposed methods of estimation for both small and large samples. Using information theoretic criteria, we compare the RSTG distribution to the exponential, generalized F, generalized gamma, Gompertz, log-logistic, lognormal, Rayleigh, and Weibull distributions in three negatively skewed real datasets.

The beta compound Rayleigh distribution : Properties and applications

In this paper, we introduce a new four parameter continuous model, called the beta compound Rayleigh (BCR) distribution that extends the compound Rayleigh distribution. Basic properties of the proposed distribution such as; mean, variance, coefficient of variation, raw and incomplete moments, skewness, kurtosis, moment and probability generating functions, reliability analysis, Lorenz, Bonferroni and Zenga curves, Rényi of entropy, order statistics and record statistics are investigated. We obtain the maximum likelihood estimates and the observed information matrix for the model parameters. Two real data sets are used to illustrate the usefulness of the new model.

Two-part models with stochastic processes for modelling longitudinal semicontinuous data: Computationally efficient inference and modelling the overall marginal mean.

Several researchers have described two-part models with patient-specific stochastic processes for analysing longitudinal semicontinuous data. In theory, such models can offer greater flexibility than the standard two-part model with patient-specific random effects. However, in practice, the high dimensional integrations involved in the marginal likelihood (i.e. integrated over the stochastic processes) significantly complicates model fitting. Thus, non-standard computationally intensive procedures based on simulating the marginal likelihood have so far only been proposed. In this paper, we describe an efficient method of implementation by demonstrating how the high dimensional integrations involved in the marginal likelihood can be computed efficiently. Specifically, by using a property of the multivariate normal distribution and the standard marginal cumulative distribution function identity, we transform the marginal likelihood so that the high dimensional integrations are contained in the cumulative distribution function of a multivariate normal distribution, which can then be efficiently evaluated. Hence, maximum likelihood estimation can be used to obtain parameter estimates and asymptotic standard errors (from the observed information matrix) of model parameters. We describe our proposed efficient implementation procedure for the standard two-part model parameterisation and when it is of interest to directly model the overall marginal mean. The methodology is applied on a psoriatic arthritis data set concerning functional disability.

Autoregressive Models with Mixture of Scale Mixtures of Gaussian Innovations

This paper presents a theoretical and empirical study of likelihood inference for the autoregressive models with finite (m-component) mixture of scale mixtures of normal (Gaussian) (SMN) innovations. This model involves autoregressive models with single and mixture component of innovations, which are frequently used in time series data analysis. An EM-type algorithm for the maximum likelihood estimation is developed and the observed information matrix is obtained. The performance of the proposed model through a simulation study is also evaluated. The model is then applied on a real time series data set.

A New Family of Topp and Leone Geometric Distribution with Reliability Applications

In this paper, a new class of lifetime distribution, which is called Topp–Leone (J-shaped) geometric distribution, is obtained by compound of the Topp–Leone and geometric distributions. Reliability and statistical properties of the new distribution such as quantiles, moment, hazard rate, reversed hazard rate, mean residual life, mean inactivity time, entropies, moment generating function, order statistics and their stochastic orderings are obtained. Estimation of the model parameters by least squares, weighted least squares, maximum likelihood and the observed information matrix are derived. Finally, a real data set is analyzed for illustrative purposes.

Inverted Beta Lindley Distribution

In this paper, a three-parameter continuous distribution, namely, Inverted Beta-Lindley (IBL) distribution is proposed and studied. The new model turns out to be quite flexible for analyzing positive data and has various shapes of density and hazard rate functions. Several statistical properties associated with this distribution are derived. Moreover, point estimation via method of moments and maximum likelihood method are studied and the observed information matrix is derived. An application of the new model to real data shows that it can give consistently a better fit than other important lifetime models.

Nonlinear regression models based on the normal mean–variance mixture of Birnbaum–Saunders distribution

This paper presents a new extension of nonlinear regression models constructed by assuming the normal mean–variance mixture of Birnbaum–Saunders distribution for the unobserved error terms. A computationally analytical EM-type algorithm is developed for computing maximum likelihood estimates. The observed information matrix is derived for obtaining the asymptotic standard errors of parameter estimates. The practical utility of the methodology is illustrated through both simulated and real data sets.

Maximum Likelihood Estimation of Structural Equation Models for Continuous Data: Standard Errors and Goodness of Fit

Classical accounts of maximum likelihood (ML) estimation of structural equation models for continuous outcomes involve normality assumptions: standard errors (SEs) are obtained using the expected information matrix and the goodness of fit of the model is tested using the likelihood ratio (LR) statistic. Satorra and Bentler (1994) introduced SEs and mean adjustments or mean and variance adjustments to the LR statistic (involving also the expected information matrix) that are robust to nonnormality. However, in recent years, SEs obtained using the observed information matrix and alternative test statistics have become available. We investigate what choice of SE and test statistic yields better results using an extensive simulation study. We found that robust SEs computed using the expected information matrix coupled with a mean- and variance-adjusted LR test statistic (i.e., MLMV) is the optimal choice, even with normally distributed data, as it yielded the best combination of accurate SEs and Type I errors.

Quantum theory from questions

We reconstruct the explicit formalism of qubit quantum theory from elementary rules on an observer's information acquisition. Our approach is purely operational: we consider an observer O interrogating a system S with binary questions and define S's state as O's `catalogue of knowledge' about S. From the rules we derive the state spaces for N elementary systems and show that (a) they coincide with the set of density matrices over an N-qubit Hilbert space; (b) states evolve unitarily under the group $\rm{PSU}(2^N)$ according to the von Neumann evolution equation; and (c) O's binary questions correspond to projective Pauli operator measurements with outcome probabilities given by the Born rule. As a by-product, this results in a propositional formulation of quantum theory. Aside from offering an informational explanation for the theory's architecture, the reconstruction also unravels new structural insights. We show that, in a derived quadratic information measure, (d) qubits satisfy inequalities which bound the information content in any set of mutually complementary questions to 1 bit; and (e) maximal sets of mutually complementary questions for one and two qubits must carry precisely 1 bit of information in pure states. The latter relations constitute conserved informational charges which define the unitary groups and, together with their conservation conditions, the sets of pure quantum states. These results highlight information as a `charge of quantum theory' and the benefits of this informational approach. This work emphasizes the sufficiency of restricting to an observer's information to reconstruct the theory and completes the quantum reconstruction initiated in arXiv:1412.8323.