Model-averaged ℓ1 regularization using Markov chain Monte Carlo model composition

Bayesian model averaging (BMA) is an effective technique for addressing model uncertainty in variable selection problems. However, current BMA approaches have computational difficulty dealing with data in which there are many more measurements (variables) than samples. This paper presents a method for combining ?₁ regularization and Markov chain Monte Carlo model composition techniques for BMA. By treating the ?₁ regularization path as a model space, we propose a method to resolve the model uncertainty issues arising in model averaging from solution path point selection. We show that this method is computationally and empirically effective for regression and classification in high-dimensional data sets. We apply our technique in simulations, as well as to some applications that arise in genomics.     

Volatility and GMM — Monte Carlo studies and empirical estimations

In this article we examine small sample properties of a generalized method of moments (GMM) estimation using Monte Carlo simulations. We assume that the generated time series describe the stochastic variance rate of a stock index. we use a mean reverting square-root process to simulate the dynamics of this instantaneous variance rate. The time series obtained are used to estimate the parameters of the assumed variance rate process by applying GMM. Our results are described and compared to estimates from empirical data which consist of volatility as well as daily volume data of the German stock market. One of our main findings is that estimates of the mean reverting parameter that are not significantly different from zero do not necessarily imply a rejection of the hypothesis of a mean reverting behavior of the underlying stochastic process.     

Assessing Type I error and power of multistate Markov models for panel data—A simulation study

Ordinal outcomes collected at multiple follow-up visits are common in clinical trials. Sometimes, one visit is chosen for the primary analysis and the scale is dichotomized amounting to loss of information. Multistate Markov models describe how a process moves between states over time. Here, simulation studies are performed to investigate the Type I error and power characteristics of multistate Markov models for panel data with limited non-adjacent state transitions. The results suggest that the multistate Markov models preserve the Type I error and adequate power is achieved with modest sample sizes for panel data with limited non-adjacent state transitions.     

Economic and economic–statistical designs of VSI Bayesian control chart using Monte Carlo method and ABC algorithm

The usual practice in using a Bayesian control chart to monitor a process is done by taking samples from the process with fixed sampling intervals. Recent studies on traditional control charts have shown that variable sampling interval (VSI) scheme compared to classical scheme (fixed ratio sampling, FRS) helps practitioners to detect process shifts more quickly. In this paper, the effectiveness of VSI scheme on performance of Bayesian control chart has been studied, based on economic (ED) and economic–statistical designs (ESD). Monte Carlo method and artificial bee colony algorithm have been utilized to obtain optimal design parameters of Bayesian control chart (sample size, sampling intervals, warning limit and control limit) since the statistic of this approach does not have any specified distribution. Finally, VSI Bayesian control chart has been compared to FRS Bayesian and VSI X-bar approaches based on ED and ESD, separately. According to the results, it has been found that the performance of VSI Bayesian scheme is better than FRS Bayesian and VSI X-bar approaches.     

Kolmogorov–Smirnov,Fluctuation, and Z g Tests for Convergence of Markov Chain Monte Carlo Draws

We examine the sizes and powers of three tests of convergence of Markov Chain Monte Carlo draws: the Kolmogorov–Smirnov test, fluctuation test, and Geweke's test. We show that the sizes and powers are sensitive to the existence of autocorrelation in the draws. We propose a filtered test that is corrected for autocorrelation. We present a numerical illustration using the Federal funds rate.     

Csiszar’s ϕ-divergences for testing the order in a Markov chain

x ₁, ..., x _n+r can be treated as the sample values of a Markov chain of order r or less (chain in which the dependence extends over r+1 consecutive variables only), and consider the problem of testing the hypothesis H ₀ that a chain of order r− 1 will be sufficient on the basis of the tools given by the Statistical Information Theory: _ϕ-Divergences. More precisely, if p _{a 1 ....., a r}: _{a r +1} denotes the transition probability for a r ^th order Markov chain, the hypothesis to be tested is H ₀:p _{a 1 ....., a r}: _{a r +1} = p _{a 2 ....., a r}: _{a r +1}, a _i ∈{1, ..., s}, i = 1, ..., r + 1 The tests given in this paper, for the first time, will have as a particular case the likelihood ratio test and the test based on the chi-squared statistic. Received: August 3, 1998; revised version: November 25, 1999     

Multilevel and Multi-index Monte Carlo methods for the McKean–Vlasov equation

We address the approximation of functionals depending on a system of particles, described by stochastic differential equations (SDEs), in the mean-field limit when the number of particles approaches infinity. This problem is equivalent to estimating the weak solution of the limiting McKean–Vlasov SDE. To that end, our approach uses systems with finite numbers of particles and a time-stepping scheme. In this case, there are two discretization parameters: the number of time steps and the number of particles. Based on these two parameters, we consider different variants of the Monte Carlo and Multilevel Monte Carlo (MLMC) methods and show that, in the best case, the optimal work complexity of MLMC, to estimate the functional in one typical setting with an error tolerance of \(\mathrm {TOL}\), is Open image in new window when using the partitioning estimator and the Milstein time-stepping scheme. We also consider a method that uses the recent Multi-index Monte Carlo method and show an improved work complexity in the same typical setting of Open image in new window . Our numerical experiments are carried out on the so-called Kuramoto model, a system of coupled oscillators.     

Discussion on “A comparison of Monte Carlo methods for computing marginal likelihoods of item response theory models”

In this discussion, the sensitivity of the result by the choice of parameters a and b in one of approaches reviewed by the authors to calculate the marginal likelihood for 2 parameter logistic item response theory model is investigated using a small simulation study.     

Darling-Erdös-type test for change detection in parameters and variance for stationary VAR models

The aim of this article is the construction of the test statistic for the detection of changes in vector autoregressive (AR) models where both AR parameters and the variance matrix of the error term are the subjects of a change. The approximating distribution of the proposed statistic is the Gumbel distribution. The proof stands on the approximation of weakly dependent random vectors by independent ones and by application of Horváth’s extension of Darling-Erdös extremal result for random vectors, see Darling and Erdös (1956) Darling, D.A., Erdös, P. (1956). A limit theorem for the maximum of normalized sums of independent random variables. Duke Math. J. 23:143–155.[Crossref], [Web of Science ®] , [Google Scholar] and Horváth (1993) Horváth, L. (1993). The maximum likelihood method for testing changes in the parameters of normal observations. Ann. Stat. 21(2):671–680.[Crossref], [Web of Science ®] , [Google Scholar]. The test statistic is a modification of the likelihood ratio.     

Some applications of nonlinear and non-Gaussian state–space modelling by means of hidden Markov models

Nonlinear and non-Gaussian state–space models (SSMs) are fitted to different types of time series. The applications include homogeneous and seasonal time series, in particular earthquake counts, polio counts, rainfall occurrence data, glacial varve data and daily returns on a share. The considered SSMs comprise Poisson, Bernoulli, gamma and Student-t distributions at the observation level. Parameter estimations for the SSMs are carried out using a likelihood approximation that is obtained after discretization of the state space. The approximation can be made arbitrarily accurate, and the approximated likelihood is precisely that of a finite-state hidden Markov model (HMM). The proposed method enables us to apply standard HMM techniques. It is easy to implement and can be extended to all kinds of SSMs in a straightforward manner.     

Tail index and second-order parameters’ semi-parametric estimation based on the log-excesses

In this paper we are interested in the derivation of the asymptotic and finite-sample distributional properties of a ‘quasi-maximum likelihood’ estimator of a ‘scale’ second-order parameter β, directly based on the log-excesses of an available sample. Such estimation is of primordial importance for the adaptive selection of the optimal sample fraction to be used in the classical semi-parametric tail index estimation as well as for the reduced-bias estimation of the tail index, high quantiles and other parameters of extreme or even rare events. An application in the area of survival analysis is provided, on the basis of a data set on males diagnosed with cancer of the tongue.     

Estimating sensitive proportions by Warner’s randomized response technique using multiple randomized responses from distinct persons sampled

In 1965 Warner pioneered randomized response techniques to estimate the proportion of people bearing a sensitive characteristic. He restricted applying his randomized response device to gather data on sensitive issues from respondents chosen by simple random sampling with replacement (SRSWR). It has spawned numerous ramifications. We present results for the situation where the distinct persons chosen in an SRSWR are identified but each one independently gives a randomized response by Warner’s device, repeated as many times as he/she is selected. Two new estimators are proposed for the sensitive proportion and compared against relevant competitors.     

Estimating the change in soccer’s home advantage during the Covid-19 pandemic using bivariate Poisson regression

AStA Advances in Statistical Analysis - In wake of the Covid-19 pandemic, 2019–2020 soccer seasons across the world were postponed and eventually made up during the summer months of 2020....     

Modelling and research on manufacturer’s capacity of remanufacturing and recycling in closed-loop supply chain

This paper introduces and analyses the present situation of the electronic waste recycling at home and abroad. Involving manufacturers in the recycling process of supply chain as the dominant party and establishing the closed-loop supply chain system structure model of the waste electronic products recycling, the effects of remanufacturing capacity and recycling coefficient on the closed-loop supply chain recycling network are analysed by using system dynamics method. The simulation results show that, compared with the traditional supply chain, the total revenue of the supply chain under the recycling mode dominated by manufacturers has improved, that the increase of the remanufacturing capacity has promoted the growth of the electronic product's sales rate, which reaches a equilibrium when remanufacturing capacity is set as 0.36, and that the recycling efficiency of e-waste has improved significantly as the e-waste recycling coefficient constantly increased.     

Building up adjusted indicators of students’ evaluation of university courses using generalized item response models

This article advances a proposal for building up adjusted composite indicators of the quality of university courses from students’ assessments. The flexible framework of Generalized Item Response Models is adopted here for controlling the sources of heterogeneity in the data structure that make evaluations across courses not directly comparable. Specifically, it allows us to: jointly model students’ ratings to the set of items which define the quality of university courses; explicitly consider the dimensionality of the items composing the evaluation form; evaluate and remove the effect of potential confounding factors which may affect students’ evaluation; model the intra-cluster variability at course level. The approach simultaneously deals with: (i) multilevel data structure; (ii) multidimensional latent trait; (iii) personal explanatory latent regression models. The paper pays attention to the potential of such a flexible approach in the analysis of students evaluation of university courses in order to explore both how the quality of the different aspects (teaching, management, etc.) is perceived by students and how to make meaningful comparisons across them on the basis of adjusted indicators.     

A Monte Carlo comparison of Jarque–Bera type tests and Henze–Zirkler test of multivariate normality

In the paper, tests for multivariate normality (MVN) of Jarque-Bera type, based on skewness and kurtosis, have been considered. Tests proposed by Mardia and Srivastava, and the combined tests based on skewness and kurtosis defined by Jarque and Bera have been taken into account. In the Monte Carlo simulations, for each combination of p = 2, 3, 4, 5 number of traits and n = 10(5)50(10)100 sample sizes 10,000 runs have been done to calculate empirical Type I errors of tests under consideration, and empirical power against different alternative distributions. Simulation results have been compared to the Henze–Zirkler’s test. It should be stressed that no test yet proposed is uniformly better than all the others in every combination of conditions examined.     

Specific-to-general predictor selection in approximate autoregressions—Monte Carlo evidence and a large scale performance assessment with real data

This paper describes the performance of specific-to-general composition of forecasting models that accord with (approximate) linear autoregressions. Monte Carlo experiments are complemented with ex-ante forecasting results for 97 macroeconomic time series collected for the G7 economies in Stock and Watson (J. Forecast. 23:405–430, 2004). In small samples, the specific-to-general strategy is superior in terms of ex-ante forecasting performance in comparison with a commonly applied strategy of successive model reduction according to weakest parameter significance. Applied to real data, the specific-to-general approach turns out to be preferable. In comparison with successive model reduction, the successive model expansion is less likely to involve overly large losses in forecast accuracy and is particularly recommended if the diagnosed prediction schemes are characterized by a medium to large number of predictors.     

Modeling stock markets’ volatility using GARCH models with Normal,Student’s <Emphasis Type=Italic>t</Emphasis> and stable Paretian distributions

As GARCH models and stable Paretian distributions have been revisited in the recent past with the papers of Hansen and Lunde (J Appl Econom 20: 873–889, 2005) and Bidarkota and McCulloch (Quant Finance 4: 256–265, 2004), respectively, in this paper we discuss alternative conditional distributional models for the daily returns of the US, German and Portuguese main stock market indexes, considering ARMA-GARCH models driven by Normal, Student’s t and stable Paretian distributed innovations. We find that a GARCH model with stable Paretian innovations fits returns clearly better than the more popular Normal distribution and slightly better than the Student’s t distribution. However, the Student’s t outperforms the Normal and stable Paretian distributions when the out-of-sample density forecasts are considered.