|
|
How to down-weight observations in robust regression: A metalearning study
Kalina, Jan ; Pitra, Z.
Metalearning is becoming an increasingly important methodology for extracting knowledge from a data base of available training data sets to a new (independent) data set. The concept of metalearning is becoming popular in statistical learning and there is an increasing number of metalearning applications also in the analysis of economic data sets. Still, not much attention has been paid to its limitations and disadvantages. For this purpose, we use various linear regression estimators (including highly robust ones) over a set of 30 data sets with economic background and perform a metalearning study over them as well as over the same data sets after an artificial contamination.
|
|
|
Nonparametric Bootstrap Techniques for Implicitly Weighted Robust Estimators
Kalina, Jan
The paper is devoted to highly robust statistical estimators based on implicit weighting, which have a potential to find econometric applications. Two particular methods include a robust correlation coefficient based on the least weighted squares regression and the minimum weighted covariance determinant estimator, where the latter allows to estimate the mean and covariance matrix of multivariate data. New tools are proposed allowing to test hypotheses about these robust estimators or to estimate their variance. The techniques considered in the paper include resampling approaches with or without replacement, i.e. permutation tests, bootstrap variance estimation, and bootstrap confidence intervals. The performance of the newly described tools is illustrated on numerical examples. They reveal the suitability of the robust procedures also for non-contaminated data, as their confidence intervals are not much wider compared to those for standard maximum likelihood estimators. While resampling without replacement turns out to be more suitable for hypothesis testing, bootstrapping with replacement yields reliable confidence intervals but not corresponding hypothesis tests.
|
|
|
Nonparametric Bootstrap Techniques for Implicitly Weighted Robust Estimators
Kalina, Jan
The paper is devoted to highly robust statistical estimators based on implicit weighting, which have a potential to find econometric applications. Two particular methods include a robust correlation coefficient based on the least weighted squares regression and the minimum weighted covariance determinant estimator, where the latter allows to estimate the mean and covariance matrix of multivariate data. New tools are proposed allowing to test hypotheses about these robust estimators or to estimate their variance. The techniques considered in the paper include resampling approaches with or without replacement, i.e. permutation tests, bootstrap variance estimation, and bootstrap confidence intervals. The performance of the newly described tools is illustrated on numerical examples. They reveal the suitability of the robust procedures also for non-contaminated data, as their confidence intervals are not much wider compared to those for standard maximum likelihood estimators. While resampling without replacement turns out to be more suitable for hypothesis testing, bootstrapping with replacement yields reliable confidence intervals but not corresponding hypothesis tests.
|
|
|
Exploiting numerical linear algebra to accelerate the computation of the MCD estimator
Sommerová, Kristýna ; Duintjer Tebbens, Erik Jurjen (advisor) ; Hnětynková, Iveta (referee)
This work is dealing with speeding up the algorithmization of the MCD es- timator for detection of the mean and the covariance matrix of a normally dis- tributed multivariate data contaminated with outliers. First, the main idea of the estimator and its well-known aproximation by the FastMCD algorithm is discussed. The main focus was to be placed on possibilities of a speedup of the iteration step known as C-step while maintaining the quality of the estimations. This proved to be problematic, if not impossible. The work is, therefore, aiming at creating a new implementation based on the C-step and Jacobi method for eigenvalues. The proposed JacobiMCD algorithm is compared to the FastMCD in terms of floating operation count and results. In conclusion, JacobiMCD is not found to be fully equivalent to FastMCD but hints at a possibility of its usage on larger problems. The numerical experiments suggest that the computation can indeed be quicker by an order of magnitude, while the quality of results is close to those from FastMCD in some settings. 1
|
|
|
How to down-weight observations in robust regression: A metalearning study
Kalina, Jan ; Pitra, Zbyněk
Metalearning is becoming an increasingly important methodology for extracting knowledge from a data base of available training data sets to a new (independent) data set. The concept of metalearning is becoming popular in statistical learning and there is an increasing number of metalearning applications also in the analysis of economic data sets. Still, not much attention has been paid to its limitations and disadvantages. For this purpose, we use various linear regression estimators (including highly robust ones) over a set of 30 data sets with economic background and perform a metalearning study over them as well as over the same data sets after an artificial contamination. We focus on comparing the prediction performance of the least weighted squares estimator with various weighting schemes. A broader spectrum of classification methods is applied and a support vector machine turns out to yield the best results. While results of a leave-1-out cross validation are very different from results of autovalidation, we realize that metalearning is highly unstable and its results should be interpreted with care. We also focus on discussing all possible limitations of the metalearning methodology in general.
|
|
|
Exact Inference In Robust Econometrics under Heteroscedasticity
Kalina, Jan ; Peštová, B.
The paper is devoted to the least weighted squares estimator, which is one of highly robust estimators for the linear regression model. Novel permutation tests of heteroscedasticity are proposed. Also the asymptotic behavior of the permutation test statistics of the Goldfeld-Quandt and Breusch-Pagan tests is investigated. A numerical experiment on real economic data is presented, which also shows how to perform a robust prediction model under heteroscedasticity. Theoretical results may be simply extended to the context of multivariate quantiles
|
|
|
Computation and applications of the MCD estimator for robust statistical analysis
Sommerová, Kristýna ; Duintjer Tebbens, Erik Jurjen (advisor) ; Hnětynková, Iveta (referee)
This work describes one of the basic problems of robust statistics con- cerning outlier detection and its possible solution by using the Minimum covariance determinant estimator for estimates of the mean value and the covariance matrix with multivariate data. It explains how the estimator works and analyses its properties. The work concentrates on its approximation based on the fastMCD algorithm and specifies its numerical properties with emphasis on computational costs and stability of the standard implementation in MATLAB. It also discusses possible modifications of the algorithm and its effects on numerical properties. Lastly the work shows the usage of the fastMCD algorithm on a few real data experiments. Powered by TCPDF (www.tcpdf.org)
|
|
|
Exact Inference In Robust Econometrics under Heteroscedasticity
Kalina, Jan ; Peštová, Barbora
The paper is devoted to the least weighted squares estimator, which is one of highly robust estimators for the linear regression model. Novel permutation tests of heteroscedasticity are proposed. Also the asymptotic behavior of the permutation test statistics of the Goldfeld-Quandt and Breusch-Pagan tests is investigated. A numerical experiment on real economic data is presented, which also shows how to perform a robust prediction model under heteroscedasticity. Theoretical results may be simply extended to the context of multivariate quantiles
|
|
| |
|
|
Autocorrelated residuals of robust regression
Kalina, Jan
The work is devoted to the Durbin-Watson test for robust linear regression methods. First we explain consequences of the autocorrelation of residuals on estimating regression parameters. We propose an asymptotic version of the Durbin-Watson test for regression quantiles and trimmed least squares and derive an asymptotic approximation to the exact null distribution of the test statistic, exploiting the asymptotic representation for both regression estimators. Further, we consider the least weighted squares estimator, which is a highly robust estimator based on the idea to down-weight less reliable observations. We compare various versions of the Durbin-Watson test for the least weighted squares estimator. The asymptotic test is derived using two versions of the asymptotic representation. Finally, we investigate a weighted Durbin-Watson test using the weights determined by the least weighted squares estimator. The exact test is described and also an asymptotic approximation to the distribution of the weighted statistic under the null hypothesis is obtained.
|
guest ::
