{"title":"Comparison of tree-based methods used in survival data","authors":"A. Yabacı, D. Sığırlı","doi":"10.2478/stattrans-2022-0002","DOIUrl":"https://doi.org/10.2478/stattrans-2022-0002","url":null,"abstract":"Abstract Survival trees and forests are popular non-parametric alternatives to parametric and semi-parametric survival models. Conditional inference trees (Ctree) form a non-parametric class of regression trees embedding tree-structured regression models into a well-defined theory of conditional inference procedures. The Ctree is applicable in a varietyof regression-related issues, involving nominal, ordinal, numeric, censored, as well as multivariate response variables and arbitrary measurement scales of covariates. Conditional inference forests (Cforest) consitute a survival forest method which combines a large number of Ctrees. The Cforest provides a unified and flexible framework for ensemble learning in the presence of censoring. The random survival forests (RSF) methodology extends the random forests method enabling the approximation of rich classes of functions while maintaining generalisation errors low. In the present study, the Ctree, Cforest and RSF methods are discussed in detail and the performances of the survival forest methods, namely the Cforest and RSF have been compared with a simulation study. The results of the simulation demonstrate that the RSF method with a log-rank score distinction criteria outperforms the Cforest and the RSF with log-rank distinction criteria.","PeriodicalId":37985,"journal":{"name":"Statistics in Transition","volume":"23 1","pages":"21 - 38"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45603277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Estimation procedures for reliability functions of Kumaraswamy-G Distributions based on Type II Censoring and the sampling scheme of Bartholomew","authors":"A. Chaturvedi, Surinder Kumar","doi":"10.2478/stattrans-2022-0008","DOIUrl":"https://doi.org/10.2478/stattrans-2022-0008","url":null,"abstract":"Abstract In this paper, we consider Kumaraswamy-G distributions and derive a Uniformly Minimum Variance Unbiased Estimator (UMVUE) and a Maximum Likelihood Estimator (MLE) of the two measures of reliability, namely R(t) = P(X > t) and P = P(X > Y) under Type II censoring scheme and sampling scheme of Bartholomew (1963). We also develop interval estimates of the reliability measures. A comparative study of the different methods of point estimation has been conducted on the basis of simulation studies. An analysis of a real data set has been presented for illustration purposes.","PeriodicalId":37985,"journal":{"name":"Statistics in Transition","volume":" ","pages":"129 - 152"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47411418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Generalized extended Marshall-Olkin family of lifetime distributions","authors":"M. Goldoust, A. Mohammadpour","doi":"10.2478/stattrans-2022-0004","DOIUrl":"https://doi.org/10.2478/stattrans-2022-0004","url":null,"abstract":"Abstract We introduce a new generalized family of nonnegative continuous distributions by adding two extra parameters to a lifetime distribution, called the baseline distribution, by twice compounding a power series distribution. The new family, called the lifetime power series-power series family, has a serial arrangement of parallel structures, which extends the Marshall and Olkin structure. Four special models are discussed. A mathematical treatment of the new distributions is provided, including ordinary and incomplete moments, quantile, moment generating and mean residual functions. The maximum likelihood estimation technique is used to estimate the model parameters and a simulation study is conducted to investigate the performance of the maximum likelihood estimates. Its applicability is also illustrated by means of two real data sets.","PeriodicalId":37985,"journal":{"name":"Statistics in Transition","volume":"23 1","pages":"55 - 74"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47713026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Abu-Shawiesh, Juthaphorn Sinsomboonthong, B. M. G. Kibria
{"title":"A modified robust confidence interval for the population mean of distribution based on deciles","authors":"M. Abu-Shawiesh, Juthaphorn Sinsomboonthong, B. M. G. Kibria","doi":"10.2478/stattrans-2022-0007","DOIUrl":"https://doi.org/10.2478/stattrans-2022-0007","url":null,"abstract":"Abstract The confidence interval is an important statistical estimator of population location and dispersion parameters. The paper considers a robust modified confidence interval, which is an adjustment of the Student’s t confidence interval based on the decile mean and decile standard deviation for estimating the population mean of a skewed distribution. The efficiency of the proposed interval estimator is evaluated on the basis of an extensive Monte Carlo simulation study. The coverage ratio and average width of the proposed confidence interval are compared with certain existing and widely used confidence intervals. The simulation results show that, in general, the proposed interval estimator’s performance is highly effective. For illustrative purposes, three real-life data sets are analyzed, which, to a certain extent, support the findings obtained from the simulation study. Thus, we recommend that practitioners use the robust modified confidence interval for estimating the population mean when the data are generated by a normal or skewed distribution.","PeriodicalId":37985,"journal":{"name":"Statistics in Transition","volume":"23 1","pages":"109 - 128"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44099902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The odd power generalized Weibull-G power series class of distributions: properties and applications","authors":"B. Oluyede, Thatayaone Moakofi, Fastel Chipepa","doi":"10.2478/stattrans-2022-0006","DOIUrl":"https://doi.org/10.2478/stattrans-2022-0006","url":null,"abstract":"Abstract We develop a new class of distributions, namely, the odd power generalized Weibull-G power series (OPGW-GPS) class of distributions. We present some special classes of the proposed distribution. Structural properties, have also been derived. We conducted a simulation study to evaluate the consistency of the maximum likelihood estimates. Moreover, two real data examples on selected data sets, to illustrate the usefulness of the new class of distributions. The proposed model outperforms several non-nested models on selected data sets.","PeriodicalId":37985,"journal":{"name":"Statistics in Transition","volume":"23 1","pages":"89 - 108"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42151244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Long-term sovereign interest rates in Czechia, Hungary and Poland: a comparative assessment with an affine term structure model","authors":"J. Janus","doi":"10.2478/stattrans-2022-0009","DOIUrl":"https://doi.org/10.2478/stattrans-2022-0009","url":null,"abstract":"Abstract This paper provides a comparative evaluation of the behaviour of long-term sovereign yields in Czechia, Hungary and Poland from 2001 to 2019. An affine term structure model developed by Adrian, Crump and Moench (2013) is used as an empirical framework for the decomposition of the bond yields into term premium and risk-neutral components. We document a substantial compression in term premia which started in Central European economies around 2013 and played a decisive role in the changes that occurred in 10-year sovereign yields. This pattern, however, was more prevalent in Czechia and Poland than in Hungary. We show that long-term rates in all three economies remained higher than in Germany due to relatively large risk-neutral components. Nevertheless, cross-country correlations became increasingly dependent on term premium dynamics, both among Central European economies and between each of them and Germany. These results are robust to bias-correction in the baseline models and interpreted in the light of the general interest rates decline in the global economy. Potential policy implications are also discussed.","PeriodicalId":37985,"journal":{"name":"Statistics in Transition","volume":"23 1","pages":"153 - 171"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43998282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Variance estimation in stratified adaptive cluster sampling","authors":"Uzma Yasmeen, Muhammad Noor-ul-Amin, M. Hanif","doi":"10.2478/stattrans-2022-0010","DOIUrl":"https://doi.org/10.2478/stattrans-2022-0010","url":null,"abstract":"Abstract In many sampling surveys, the use of auxiliary information at either the design or estimation stage, or at both these stages is usual practice. Auxiliary information is commonly used to obtain improved designs and to achieve a high level of precision in the estimation of population density. Adaptive cluster sampling (ACS) was proposed to observe rare units with the purpose of obtaining highly precise estimations of rare and specially clustered populations in terms of least variances of the estimators. This sampling design proved to be more precise than its more conventional counterparts, including simple random sampling (SRS), stratified sampling, etc. In this paper, a generalised estimator is anticipated for a finite population variance with the use of information of an auxiliary variable under stratified adaptive cluster sampling (SACS). The bias and mean square error expressions of the recommended estimators are derived up to the first degree of approximation. A simulation study showed that the proposed estimators have the least estimated mean square error under the SACS technique in comparison to variance estimators in stratified sampling.","PeriodicalId":37985,"journal":{"name":"Statistics in Transition","volume":"23 1","pages":"173 - 184"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46429480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Adepoju, S. S. Abdulkadir, D. Jibasen, H. Chiroma
{"title":"Interval Type-2 fuzzy Exponentially Weighted Moving Average Control Chart","authors":"A. Adepoju, S. S. Abdulkadir, D. Jibasen, H. Chiroma","doi":"10.2478/stattrans-2022-0011","DOIUrl":"https://doi.org/10.2478/stattrans-2022-0011","url":null,"abstract":"Abstract Some industrial data often come with uncertainty, which in some cases depends on the decision of those responsible for taking the measurement in the production process. While the fuzzy approach helps to tackle the ambiguity that arises in the measurement, an interval type-2 fuzzy set deals with such uncertainty better due to its flexibility over the control limits of its control chart. This paper aims to develop an Interval Type-2 fuzzy Exponentially Weighted Moving Average Control Chart (IT2FEWMA) under the fuzzy type-2 condition. This development will facilitate monitoring small and moderate shifts in the production process in conditions of uncertainty.","PeriodicalId":37985,"journal":{"name":"Statistics in Transition","volume":"367 2","pages":"185 - 200"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41290892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"New improved Poisson and negative binomial item count techniques for eliciting truthful answers to sensitive questions","authors":"Barbara Kowalczyk, R. Wieczorkowski","doi":"10.2478/stattrans-2022-0005","DOIUrl":"https://doi.org/10.2478/stattrans-2022-0005","url":null,"abstract":"Abstract Item count techniques (ICTs) are indirect survey questioning methods designed to deal with sensitive features. These techniques have gained the support of many applied researchers and undergone further theoretical development. Latterly in the literature, two new item count methods, called Poisson and negative binomial ICTs, have been proposed. However, if the population parameters of the control variable are not provided by the outside source, the methods are not very efficient. Efficiency is an important issue in indirect methods of questioning due to the fact that the protection of respondents’ privacy is usually achieved at the expense of the efficiency of the estimation. In the present paper we propose new improved Poisson and negative binomial ICTs, in which two control variables are used in both groups, although in a different manner. In the paper we analyse best linear unbiased and maximum likelihood estimators of the proportion of the sensitive attribute in the population in the introduced new models. The theoretical findings presented in the paper are supported by a comprehensive simulation study. The improved procedure allowed the increase of the efficiency of the estimation compared to the original Poisson and negative binomial ICTs.","PeriodicalId":37985,"journal":{"name":"Statistics in Transition","volume":"23 1","pages":"75 - 88"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45991415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}