• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site
Of all publications in the section: 5
Sort:
by name
by year
Article
Igor Kheifets. Computational Statistics & Data Analysis. 2018. Vol. 124. P. 1-14.

This paper considers parametric model adequacy tests for nonlinear multivariate dynamic models. It is shown that commonly used Kolmogorov-type tests do not take into account cross-sectional nor time-dependence structure, and a test, based on multi-parameter empirical processes, is proposed that overcomes these problems. The tests are applied to a nonlinear LSTAR-type model of joint movements of UK output growth and interest rate spreads. A simulation experiment illustrates the properties of the tests in finite samples. Asymptotic properties of the test statistics under the null of correct specification and under the local alternative, and justification of a parametric bootstrap to obtain critical values, are provided.

Added: Feb 23, 2021
Article
Kasianova K., Kelbert M., Mozgunov P. Computational Statistics & Data Analysis. 2021. No. 158.

In many rare disease Phase II clinical trials, two objectives are of interest to an investigator: maximising the statistical power and maximising the number of patients responding to the treatment. These two objectives are competing, therefore, clinical trial designs offering a balance between them are needed. Recently, it was argued that response-adaptive designs such as families of multi-arm bandit (MAB) methods could provide the means for achieving this balance. Furthermore, response-adaptive designs based on a concept of context-dependent (weighted) information criteria were recently proposed with a focus on Shannon’s differential entropy. The information-theoretic designs based on the weighted Renyi, Tsallis and Fisher informations are also proposed. Due to built-in parameters of these novel designs, the balance between the statistical power and the number of patients that respond to the treatment can be tuned explicitly. The asymptotic properties of these measures are studied in order to construct intuitive criteria for arm selection. A comprehensive simulation study shows that using the exact criteria over asymptotic ones or using information measures with more parameters, namely Renyi and Tsallis entropies, brings no sufficient gain in terms of the power or proportion of patients allocated to superior treatments. The proposed designs based on information-theoretical criteria are compared to several alternative approaches. For example, via tuning of the built-in parameter, one can find designs with power comparable to the fixed equal randomisation’s but a greater number of patients responded in the trials.

Added: Jun 30, 2021
Article
Kasianova K., Kelbert M., Mozgunov P. Computational Statistics & Data Analysis. 2021. Vol. 158.

In many rare disease Phase II clinical trials, two objectives are of interest to an investigator: maximising the statistical power and maximising the number of patients responding to the treatment. These two objectives are competing, therefore, clinical trial designs offering a balance between them are needed. Recently, it was argued that response-adaptive designs such as families of multi-arm bandit (MAB) methods could provide the means for achieving this balance. Furthermore, response-adaptive designs based on a concept of context-dependent (weighted) information criteria were recently proposed with a focus on Shannon’s differential entropy. The information-theoretic designs based on the weighted Renyi, Tsallis and Fisher informations are also proposed. Due to built-in parameters of these novel designs, the balance between the statistical power and the number of patients that respond to the treatment can be tuned explicitly. The asymptotic properties of these measures are studied in order to construct intuitive criteria for arm selection. A comprehensive simulation study shows that using the exact criteria over asymptotic ones or using information measures with more parameters, namely Renyi and Tsallis entropies, brings no sufficient gain in terms of the power or proportion of patients allocated to superior treatments. The proposed designs based on information-theoretical criteria are compared to several alternative approaches. For example, via tuning of the built-in parameter, one can find designs with powercomparable to the fixed equal randomisation’s but a greater number of patients responded in the trials.

Added: Feb 1, 2021
Article
Koldanov A. P., Kalyagin V. A., Koldanov P.A. et al. Computational Statistics & Data Analysis. 2013. Vol. 68. P. 17-29.

The statistical analysis of the method of construction of the market graph when considered as a multiple decision statistical procedure is investigated. It is shown that under the condition of additivity of the loss function the method can be optimal in different classes of unbiased multiple statistical procedures. The results are obtained by application of the Lehmann theory of multiple decision procedures to the method of construction of the market graph. The main findings are illustrated by numerical studies of the conditional risk of multiple decision statistical procedures for different loss functions and different return distributions

Added: Aug 22, 2013
Article
Jovanovic M., Milosevic B., Y.Y.Nikitin et al. Computational Statistics & Data Analysis. 2015. Vol. 90. P. 100-113.

Abstract Two families of scale-free exponentiality tests based on the recent characterization of exponentiality by Arnold and Villasenor are proposed. The test statistics are constructed using suitable functionals of U-empirical distribution functions. The family of integral statistics can be reduced to V- or U-statistics with relatively simple non-degenerate kernels. They are asymptotically normal and have reasonably high local Bahadur efficiency under common alternatives. This efficiency is compared with simulated powers of new tests. On the other hand, the Kolmogorov type tests demonstrate very low local Bahadur efficiency and rather moderate power for common alternatives, and can hardly be recommended to practitioners. The conditions of local asymptotic optimality of new tests are also explored and for both families special "most favourable" alternatives for which the tests are fully efficient are described. © 2015 Published by Elsevier B.V.

Added: Sep 3, 2015