A monte carlo study of robust estimators of location

Andrews et al (1972) carried out an extensive Monte Carlo study of robust estimators of location. Their conclusions were that the hampel and the skipped estimates, as classes, seemed to be preferable to some of the other currently fashionable estimators. The present study extends this work to include estimators not previously examined. The estimators are compared over short-tailed as well as long-tailed alternatives and also over some dependent data generated by first-order autoregressive schemes. The conclusions of the present study are threefold. First, from our limited study, none of the so-called robust estimators are very efficient over short-tailed situations. More work seems to be necessary in this situation. Second, none of the estimators perform very well in dependent data situations, particularly when the correlation is large and positive. This seems to be a rather pressing problem. Finally, for long-tailed alternatives, the hampel estimators and Hogg-type adaptive versions of the hampels are the strongest classes. The adaptive hampels neither uniformly outperform nor are they outperformed by the hampels. However, the superiority in terms of maximum relative efficiency goes to the adaptive hampels. That is, the adaptive hampels, under their worst performance.     

A monte carlo evaluation of response surface analysis based on paired-comparison data

The use of the logit transformation on paired-comparison data in the weighted least squares analysis of response surfaces for aesthetic qualities of products is discussed. Monte Carlo simulations are employed to investigate the small sample properties of the estimators and test statistics. A secondary objective of the Monte Carlo simulations is the comparison of two transformation procedures. The simulations are of standard-item paired-compar-ison experiments in which ties are not allowed.     

Volume estimation by monte carlo methods *

In estimating a multiple integral, it is known that Monte Carlo methods are more efficient than analytical techniques when the number of dimensions is beyond seven. In general, the sample-mean method is better than the hit-or-miss Monte Carlo method. However, when the volume of a domain in a high-dimensional space is of interest, the hit-or-miss method is usually preferred. It is because of the difficulty in generalizing the sample-mean method for the computation of the volume of a domain. This paper develops a technique to make such a generalization possible. The technique can be interpreted as a volume-preserving transformation procedure. A volume-preserving transformation is first performed to transform the concerned domain into a hypersphere. The volume of the domain is then evaluated by computing the volume of the hypersphere.     

A monte carlo study on the robustness of four MANOVA criterion tests

Four MANOVA tests (Wilk's Lambda, Roy's Largest Root Test, the Hotelling-Lawley Trace and the Pillai-Bartlett Trace) were studied when restricted sample data were drawn from normal populations. Robustness was compared by examining bias at critical points and fluctuations in the standard error of the empirical distributions. The Wilk's Lambda statistic was found to be the least affected by the restricted sampling.     

A simulation study of least squares and ridge estimaors for normal and nonnormal autocorrelated disturbances

The purpose of this paper is to examine the small sample properties of various ridge estimators along with least squares, in some special settings.Specifically, we consider a first order autoregressive structuure for normal and nonnormal disturbances, and report on a Monte Carlo study the small sample behavior of these estimators according to the criteria of bias and dispersion.The results suggest that under all the examined settings and for all the criteria used the HKB estimator exhibited a superior performance compared to the other estimators, while the LS and LW estimators gave consistently poor results.Also if the error term is only moderately autocorrelated the performance of the ridge estimators that do not account for autocorrelation outperform their counterparts as well as least squares that account for autocorrelation.     

A geometric approach to transdimensional markov chain monte carlo

The authors present theoretical results that show how one can simulate a mixture distribution whose components live in subspaces of different dimension by reformulating the problem in such a way that observations may be drawn from an auxiliary continuous distribution on the largest subspace and then transformed in an appropriate fashion. Motivated by the importance of enlarging the set of available Markov chain Monte Carlo (MCMC) techniques, the authors show how their results can be fruitfully employed in problems such as model selection (or averaging) of nested models, or regeneration of Markov chains for evaluating standard deviations of estimated expectations derived from MCMC simulations.     

A note on bounding monte carlo variances michael lavine

A density bounded class P of probability distributions on a space χ is the set of all probability distributions corresponding to probability densities bounded below by a given subprob-ability density and bounded above by a given superprobability density. Density bounded classes arise in robust Bayesian analysis (Lavine 1991) and also in Monte Carlo integration (Fishman Granovsky and Rubin 1989). Finding upper and lower bounds on the variance over all p? P allows one to bound the Monte Carlo variance. Fishman Granovsky and Rubin (1989) find bounds on the variance over all p ? P and also find the densities in P achieving those bounds in the case where χ is discrete; that is, where P is actually a set of probability mass functions. This article generalizes their result by showing how to bound the variance and find the densities achieving the bounds when χ is continuous.     

Small-sample behavior of weighted least squares in experimental design applications

In experimental design applications unbiased estimators s_i ² of the variances σ_i ² are possible. These estimators may be used in Weighted Least Squares (WLS) when estimating the parameters β. The resulting small-sample behavior is investigated in a Monte Carlo experiment. This experiment shows that an asymptotically valid covariance formula can be used if s_i ² is based on, say, at least 5 observations. The WLS estimator based on estimators s_i ² gives more accurate estimators of β, provided the σ_i ² differ by a factor, say, 10.     

Analysis of least squares regression estimates in case of additional errors in the variables

Estimation of a regression function from independent and identical distributed data is considered. The L₂ error with integration with respect to the design measure is used as error criterion. Upper bounds on the L₂ error of least squares regression estimates are presented, which bound the error of the estimate in case that in the sample given to the estimate the values of the independent and the dependent variables are pertubated by some arbitrary procedure. The bounds are applied to analyze regression-based Monte Carlo methods for pricing American options in case of errors in modelling the price process.     

The relevance of large sample properties of estimators for the errors-in-variables model:a monte carlo study

By means of a Monte Carlo study it is investigated whether moments of the asymptotic distributions of two estimators for the errors-in-variables model are appropriate for employment in small-sample applications.     

A monte carlo investigation of a statistic for a bivariate missing data problem

Testing the equal means hypothesis of a bivariate normal distribution with homoscedastic varlates when the data are incomplete is considered. If the correlational parameter, ρ, is known, the well-known theory of the general linear model is easily employed to construct the likelihood ratio test for the two sided alternative. A statistic, T, for the case of ρ unknown is proposed by direct analogy to the likelihood ratio statistic when ρ is known. The null and nonnull distribution of T is investigated by Monte Carlo techniques. It is concluded that T may be compared to the conventional t distribution for testing the null hypothesis and that this procedure results in a substantial increase in power-efficiency over the procedure based on the paired t test which ignores the incomplete data. A Monte Carlo comparison to two statistics proposed by Lin and Stivers (1974) suggests that the test based on T is more conservative than either of their statistics.     

Test for cointegration based on two-stage least squares

A residual-based test for cointegration is proposed. The method of two-stage least squares is used to estimate the cointegration model parameters. The residuals are then tested for the existence of a unit root using the augmented Dickey-Fuller test.     

A large-scale monte carlo study of the buckley-james estimator with censored data

Estimation in the presence of censoring is an important problem. In the linear model, the Buckley-James method proceeds iteratively by estimating the censored values than re-estimating the regression coeffi- cients. A large-scale Monte Carlo simulation technique has been developed to test the performance of the Buckley-James (denoted B-J) estimator. One hundred and seventy two randomly generated data sets, each with three thousand replications, based on four failure distributions, four censoring patterns, three sample sizes and four censoring rates have been investigated, and the results are presented. It is found that, except for Type I1 censoring, the B-J estimator is essentially unbiased, even when the data sets with small sample sizes are subjected to a high censoring rate. The variance formula suggested by Buckley and James (1979) is shown to be sensitive to the failure distribution. If the censoring rate is kept constant along the covariate line, the sample variance of the estimator appears to be insensitive to the censoring pattern with a selected failure distribution. Oscillation of the convergence values associated with the B-J estimator is illustrated and thoroughly discussed.     

A monte carlo analysis of two spectral tests of the martingale hypothesis

Summary The size, power, and robustness properties of the Kolmogorov-Smirnov and Cramér-von Mises spectral tests of the martingale (difference) hypothesis are investigated by Monte Carlo methods. The results highlight a marked superiority of the Cramér-von Mises with respect to the Kolmogorov-Smirnov test. The paper also shows that the Cramér-von Mises test is simple to compute, more general and more powerful than other converntionally used tests.     

Monte carlo comparison of estimation methods for additive two-way tables

We considered the problem of estimating effects in the following linear model for data arranged in a two-way table: Response = Common effect + Row effect + Column effect + Residual. This work was occasioned by a project to analyse Federal Aviation Administration (FAA) data on daily temporal deviations from flight plans for commercial US flights, with rows and columns representing origin and destination airports, respectively. We conducted a large Monte Carlo study comparing the accuracy of three methods of estimation: classical least squares, median polish and least absolute deviations (LAD). The experiments included a wide spectrum of tables of different sizes and shapes, with different levels of non-linearity, noise variance, and percentages of empty cells and outliers. We based our comparison on the accuracy of the estimates and on computational speed. We identified factors that significantly affect accuracy and speed, and compared the methods based on their sensitivity to these factors. We concluded that there is no dominant method of estimation and identified conditions under which each method is most attractive.     

Markov-chain monte carlo: Some practical implications of theoretical results

We review and discuss some recent progress in the theory of Markov-chain Monte Carlo applications, particularly oriented to applications in statistics. We attempt to assess the relevance of this theory for practical applications.     

Monte carlo approximation to edgeworth expansions

Since the 1930s, empirical Edgeworth expansions have been employed to develop techniques for approximate, nonparametric statistical inference. The introduction of bootstrap methods has increased the potential usefulness of Edgeworth approximations. In particular, a recent paper by Lee & Young introduced a novel approach to approximating bootstrap distribution functions, using first an empirical Edgeworth expansion and then a more traditional bootstrap approximation to the remainder. In principle, either direct calculation or computer algebra could be used to compute the Edgeworth component, but both methods would often be difficult to implement in practice, not least because of the sheer algebraic complexity of a general Edgeworth expansion. In the present paper we show that a simple but nonstandard Monte Carlo technique is a competitive alternative. It exploits properties of Edgeworth expansions, in particular their parity and the degrees of their polynomial terms, to develop particularly accurate approximations.     

A monte carlo study of the power of alternative tests under the generalized manova model

Monte Carlo simulations are performed for a broad range of conditions. These simulations indicate that the powers of alternative tests under the generalized MANOVA model for small samples differ significantly, if a large reduction of the number of polynomial parameters is applied. The results show that, if the response covariance matrix ∑ is known, the best alternative is to use ∑. If, however, ∑ is unknown, substitution of an identity matrix for ∑ is recommended. This alternative usually results in a test with more power than the test with the usual estimate of ∑ employing covariates or the test with an estimate of E obtained from another sample.     

A monte carlo study of the wald,lm, and lr tests in a heteroscedastic linear model

In this paper, we examine by Monte Carlo experiments the small sample properties of the W (Wald), LM (Lagrange Multiplier) and LR (Likelihood Ratio) tests for equality between sets of coefficients in two linear regressions under heteroscedasticity. The small sample properties of the size-corrected W, LM and LR tests proposed by Rothenberg (1984) are also examined and it is shown that the performances of the size-corrected W and LM tests are very good. Further, we examine the two-stage test which consists of a test for homoscedasticity followed by the Chow (1960) test if homoscedasticity is indicated or one of the W, LM or LR tests if heteroscedasticity should be assumed. It is shown that the pretest does not reduce much the bias in the size when the sizecorrected citical values are used in the W, LM and LR tests.     

Estimation of parameters in a generalized GMANOVA model based on an outer product analogy and least squares

This paper investigates estimation of parameters in a combination of the multivariate linear model and growth curve model, called a generalized GMANOVA model. Making analogy between the outer product of data vectors and covariance yields an approach to directly do least squares to covariance. An outer product least squares estimator of covariance (COPLS estimator) is obtained and its distribution is presented if a normal assumption is imposed on the error matrix. Based on the COPLS estimator, two-stage generalized least squares estimators of the regression coefficients are derived. In addition, asymptotic normalities of these estimators are investigated. Simulation studies have shown that the COPLS estimator and two-stage GLS estimators are alternative competitors with more efficiency in the sense of sample mean, standard deviations and mean of the variance estimates to the existing ML estimator in finite samples. An example of application is also illustrated.