共查询到13条相似文献,搜索用时 8 毫秒
1.
2.
3.
4.
5.
6.
Philip D. O'Neill 《Statistics and Computing》2003,13(1):37-44
The Reed-Frost epidemic model is a simple stochastic process with parameter q that describes the spread of an infectious disease among a closed population. Given data on the final outcome of an epidemic, it is possible to perform Bayesian inference for q using a simple Gibbs sampler algorithm. In this paper it is illustrated that by choosing latent variables appropriately, certain monotonicity properties hold which facilitate the use of a perfect simulation algorithm. The methods are applied to real data. 相似文献
7.
Gibbs sampling has had great success in the analysis of mixture models. In particular, the “latent variable” formulation of the mixture model greatly reduces computational complexity. However, one failing of this approach is the possible existence of almost-absorbing states, called trapping states, as it may require an enormous number of iterations to escape from these states. Here we examine an alternative approach to estimation in mixture models, one based on a Rao–Blackwellization argument applied to a latent-variable-based estimator. From this derivation we construct an alternative Monte Carlo sampling scheme that avoids trapping states. 相似文献
8.
J. Møller 《Journal of the Royal Statistical Society. Series B, Statistical methodology》1999,61(1):251-264
We discuss how the ideas of producing perfect simulations based on coupling from the past for finite state space models naturally extend to multivariate distributions with infinite or uncountable state spaces such as auto-gamma, auto-Poisson and autonegative binomial models, using Gibbs sampling in combination with sandwiching methods originally introduced for perfect simulation of point processes. 相似文献
9.
A Monte Carlo simulation study on partially adaptive estimators of linear regression models 总被引:1,自引:0,他引:1
This paper presents a comprehensive comparison of well-known partially adaptive estimators (PAEs) in terms of efficiency in estimating regression parameters. The aim is to identify the best estimators of regression parameters when error terms follow from normal, Laplace, Student's t, normal mixture, lognormal and gamma distribution via the Monte Carlo simulation. In the results of the simulation, efficient PAEs are determined in the case of symmetric leptokurtic and skewed leptokurtic regression error data. Additionally, these estimators are also compared in terms of regression applications. Regarding these applications, using certain standard error estimators, it is shown that PAEs can reduce the standard error of the slope parameter estimate relative to ordinary least squares. 相似文献
10.
Bayesian analysis of nonlinear and non-Gaussian state space models via multiple-try sampling methods
Mike K. P. So 《Statistics and Computing》2006,16(2):125-141
We develop in this paper three multiple-try blocking schemes for Bayesian analysis of nonlinear and non-Gaussian state space
models. To reduce the correlations between successive iterates and to avoid getting trapped in a local maximum, we construct
Markov chains by drawing state variables in blocks with multiple trial points. The first and second methods adopt autoregressive
and independent kernels to produce the trial points, while the third method uses samples along suitable directions. Using
the time series structure of the state space models, the three sampling schemes can be implemented efficiently. In our multimodal
examples, the three multiple-try samplers are able to generate the desired posterior sample, whereas existing methods fail
to do so. 相似文献
11.
Yonghui Liu Chaoxuan Mao Víctor Leiva Shuangzhe Liu Waldemiro A. Silva Neto 《Journal of applied statistics》2022,49(5):1323
In the present study, we provide a motivating example with a financial application under COVID-19 pandemic to investigate autoregressive (AR) modeling and its diagnostics based on asymmetric distributions. The objectives of this work are: (i) to formulate asymmetric AR models and their estimation and diagnostics; (ii) to assess the performance of the parameters estimators and of the local influence technique for these models; and (iii) to provide a tool to show how data following an asymmetric distribution under an AR structure should be analyzed. We take the advantages of the stochastic representation of the skew-normal distribution to estimate the parameters of the corresponding AR model efficiently with the expectation-maximization algorithm. Diagnostic analytics are conducted by using the local influence technique with four perturbation schemes. By employing Monte Carlo simulations, we evaluate the statistical behavior of the corresponding estimators and of the local influence technique. An illustration with financial data updated until 2020, analyzed using the methodology introduced in the present work, is presented as an example of effective applications, from where it is possible to explain atypical cases from the COVID-19 pandemic. 相似文献
12.
J. Møller & K. Schladitz 《Journal of the Royal Statistical Society. Series B, Statistical methodology》1999,61(4):955-969
Fill's algorithm for perfect simulation for attractive finite state space models, unbiased for user impatience, is presented in terms of stochastic recursive sequences and extended in two ways. Repulsive discrete Markov random fields with two coding sets like the auto-Poisson distribution on a lattice with 4-neighbourhood can be treated as monotone systems if a particular partial ordering and quasi-maximal and quasi-minimal states are used. Fill's algorithm then applies directly. Combining Fill's rejection sampling with sandwiching leads to a version of the algorithm which works for general discrete conditionally specified repulsive models. Extensions to other types of models are briefly discussed. 相似文献
13.
Tim B. Swartz Paramjit S. Gill Saman Muthukumarana 《Revue canadienne de statistique》2009,37(2):143-160
This article is concerned with the simulation of one‐day cricket matches. Given that only a finite number of outcomes can occur on each ball that is bowled, a discrete generator on a finite set is developed where the outcome probabilities are estimated from historical data involving one‐day international cricket matches. The probabilities depend on the batsman, the bowler, the number of wickets lost, the number of balls bowled and the innings. The proposed simulator appears to do a reasonable job at producing realistic results. The simulator allows investigators to address complex questions involving one‐day cricket matches. The Canadian Journal of Statistics © 2009 Statistical Society of Canada 相似文献