Odborné příspěvky

• Jimp – článek v odborném periodiku impaktovaném
• Jsc – článek v odborném periodiku obsaženém v databázi Scopus
• Jneimp – článek v odborném periodiku neimpaktovaném
• Jrec – článek v českém recenzovaném časopise
• B – odborná kniha
• C – kapitola v odborné knize
• D – článek ve sborníku
• Ostatní tištěné publikace

Jimp – článek  v odborném periodiku impaktovaném

ZIMMERMANN, P. Modeling mortality at old age with time-varying parameters. Mathematical Population Studies. 2017, 24(3), 172–180. ISSN: 0889-8480 (Print) 1547-724X (Online). DOI: 10.1080/08898480.2017.1330013. Available online: http://dx.doi.org/10.1080/08898480.2017.1330013

Abstract
Several models of old age mortality with time-varying parameters are expressed in a single formula. In these models, the existence of an age threshold above which mortality increases over time and below which mortality decreases over time is problematic. The conditions of appearance of this threshold are expressed and shown on logistic and exponential models with empirical data. The conditions of appearance of the threshold reflect actual situations in developed countries. Richards’ curve avoids the appearance of the threshold with empirical data.

Pdf: 2017_Zimmermann_Mathematical_Population_Studies.pdf

HULÍKOVÁ TESÁRKOVÁ, K. The Czech Republic and Slovakia in terms of mortality from malignant neoplasms: similar or opposite tendencies? Central European Journal of Public Health. 2017, Sep. 25(3), 177–184. ISSN 1803-1048 (Online), ISSN 1210-7778 (Print). DOI: 10.21101/cejph.a4360. Available online: https://doi.org/10.21101/cejph.a4360  

Abstract
In Europe, a steady mortality decline has been observed from the 1950s, however, Central and Eastern Europe underwent a period of stagnation or even worsening from the 1960s to 1980s. Since that time an evident mortality decline could be observed in that part of Europe too. Within the post-communist countries, mortality development has been most favourable in Slovenia, the Czech Republic and Slovakia. The aim of this study is to describe the latest development of cancer mortality in two selected countries - the Czech Republic and Slovakia. These two countries have much in common, including many similar long term trends in demographic or social indicators' development. The study evaluates whether cancer mortality development differs in the two countries or rather follows a similar trend. From the presented results it is clear that the development apparently differs namely according to sex. The results according to selected particular causes of death (from the group of malignant neoplasms) are presented as well. It could be assumed that many aspects could be improved by prevention programmes or screening.

Pdf : nelze publikovat na webu

RYCHTAŘÍKOVÁ, J. Délka života, zdraví a postoje v Evropské Unii (Length of life, health and attitudes in the European Union). Geografie – Sborník ČGS. 2015, 120(4), 542–563. Available online: https://www.geografie.cz/archiv/stahnout/54

Abstract
The contribution addresses three fields of investigation: mortality, health, and attitudes in the countries of EU28, Norway and Iceland. The data of EUROSTAT and EUROBAROMETER 378 were analyzed. In 2011, life expectancy at the age of 65 was shorter in post-Communist countries and there was also a smaller share of years lived in self-perceived good health. Two-level regression modelling has shown that the higher the age, the lower the satisfaction with health and with life. Higher-educated people and those living in a partnership are generally happier than the rest. Compared with other age and gender groups, young people and men perceive someone as old much sooner. Pessimistic attitudes are, to a smaller extent, intensified by living in former Communist countries.

Pdf: 2015_Rychtarikova_Geografie.pdf

HULÍKOVÁ TESÁRKOVÁ, K., KAŠPAR, D., ZIMMERMANN, P. Konvergenční a divergenční tendence v Evropě z hlediska úmrtnosti: Jaké je postavení Česka? (Convergent and divergent trends in the European mortality: What is the position of Czechia?). Geografie – Sborník ČGS. 2015, 120(1), 26–49. Available online: http://www.geografie.cz/archiv/stahnout/77

Abstract
Study of convergence and divergence tendencies could be taken almost as a separate field of study e.g. in demography or geography. In the article, a transparent method of quantification and visualization of convergence tendencies is introduced. Czechia was selected as a case country on which convergence tendencies can be studied and illustrated. The aim ofthe study is to find and apply a method of measuring and analyzing the convergence tendencies of this selected country to other countries. We focused on the process of mortality, for which necessary data are available in a unified structure for most of the European countries. The analysis was based on temporary life expectancy between ages 30 and 65 and life expectancy at the age of 65 years. It was proven that the “demographic nearest neighbor” in a mortality point of view for Czechia is Denmark. Such approach could be conveniently applied to any other studied process.

Pdf: 2015_Hulikova_Geografie.pdf

RYCHTAŘÍKOVÁ, J. GOURBIN, C., ŠÍPEK, A., WUNSCH, C. Impact of parental ages and other characteristics at childbearing on congenital anomalies. Results for the Czech Republic, 2000-2007. Demographic Research. 2013, 28(5), 137–156. DOI: 10.4054/DemRes.2013.28.5. Available online: https://www.demographic-research.org/volumes/vol28/5/28-5.pdf

Abstract
BACKGROUND
While it is widely known that maternal age at childbearing plays a role in the occurrence of Down syndrome, less is known about the effects of maternal age on other major congenital anomalies. Information on the possible effects of other maternal characteristics and of the age of the father is even scarcer.
OBJECTIVE
We present new results on the associations between parental ages and other maternal characteristics on the one hand, and congenital anomalies on the other, using linked data from three Czech registries on mothers, newborns, and malformations, for the period 2000-2007.
METHODS
As the variables are in a categorical format, binary logistic regression is used in order to investigate the relationship between the presence/absence of a congenital anomaly for each of the 11 types of anomalies considered, and for the set of predictors.
RESULTS
This research confirms that the age of the mother has an impact on the incidence of Down syndrome and other chromosomal anomalies. Paternal age is not associated with chromosomal anomalies, and, in this Czech population, has a rather slight effect on some of the congenital anomalies examined. Another finding of the present study is that various other maternal characteristics may affect the incidence of congenital malformations.
CONCLUSIONS
Based on a large dataset, this study concludes that the ages of both parents can be associated with congenital anomalies of the child, and that maternal characteristics other than age have also to be considered.
COMMENTS
Risk factors can be tentatively proposed if they are based on a plausible and suitably tested explanatory mechanism. Unfortunately, in the majority of individual cases of congenital anomaly, the cause of the condition is unknown, and is suspected to result from an interaction of multiple environmental and genetic factors.

Pdf: 2013_Rychtarikova_Demographic_Research.pdf

Jsc – článek v odborném periodiku obsaženém v databázi Scopus

ZIMMERMANN, Pavel. Comparison of Severity Estimators' Efficiency Based on Different Data Aggregation Levels. Statistika [online]. 2017, 97(4), 76–96. eISSN 1804-8765. ISSN 0322-788X. Available online: https://www.czso.cz/documents/10180/45606529/32019717q4076.pdf/7145182c-1f0b-4dfc-ac89-0cd8e1016356?version=1.0

Abstract
Estimates of the ultimate claim value occur in many actuarial models. Detailed data about each claim are available for estimation: each claim is at first booked at an initial value and processed over a random number of years, during which it is adjusted until closure. The ultimate value can be estimated based on observations of the ultimate value directly, which in this context, means using aggregated data. A more detailed, distribution-free estimator based on estimates of the initial claim value, the closure probability, and development factors is constructed in this article. It is proved that this estimator is asymptotically unbiased and an approximate analytical formula is derived for its variance. The efficiency of this estimator is compared to the efficiency of the simple arithmetic average of the ultimate claim value. Results are illustrated on an example and complemented with a simulation. The example results in significantly lower variability of the detailed estimator.

Pdf: 2017_Zimmermann_Statistika.pdf

PODOLSKÁ, K., RYCHTAŘÍKOVÁ, J. The impact of cosmic-origin background radiation on human survival in the Czech Republic. Demografie. 2017, 59(2), 132–149. Available online https://www.czso.cz/documents/10180/46203818/clanek+3_Podolska-Rychtarikova.pdf/1454147e-8a44-40ca-b76c-d1fe6e7b822c?version=1.0

Abstract
We evaluate the lifetime attributable risks induced by an increasing concentration of cosmic radiation and cosmogenic radionuclides during periods of low solar activity for the specific conditions in the Czech Republic. The concentration of cosmic radiation and cosmogenic radionuclides reaches its highest values during the solar minima when the Earth’s magnetosphere is more penetrable. The computed estimate of lifetime attributable risks from solid neoplasms (colon, lung, and stomach) induced by doses of natural background radiation is higher for the period of low activity in solar cycle No. 24 than for the forced solar activity in the previous solar cycle Nos. 19–23. We estimated the lifetime attributable risks induced by the annual dose of natural background radiation by sex for the Czech Republic and the USA. In addition, three different scenarios based on dose radiation level were explored. The cosmogenic radionuclides in our environment may thus play a greater role than in the last decades.

Pdf: 2017_Rychtarikova_Demografie.pdf

REISSIGOVÁ, J., RYCHTAŘÍKOVÁ, J. Základní pojmy a principy konstrukce modelů typu věk-období-kohorta. Demografie. 2015, 57(1), 21–39. Available online: https://www.czso.cz/documents/10180/20555397/13005315q1.pdf/ab1e4bae-e09d-46d8-803c-5027d9ecce10?version=1.0

Abstract
The aim of the article is to examine the age-period-cohort models that are used to evaluate the trends of various population indicators (e.g. mortality, fertility). This approach is mainly used when we have no available data on the potential risk or protective factors (e.g. lifestyle) affecting population indicators. The advantages and disadvantages of age-period-cohort modelling are described and their use is illustrated on the basis of examples of Czech male mortality.

Pdf: 2015_Rychtarikova_Demografie.pdf

HULÍKOVÁ TESÁRKOVÁ, K., KURTINOVÁ, O. A few notes on the Lexis diagram: The 100th anniversary of the death of Wilhelm Lexis. Demografie. 2014, 56(4). ISSN 0011-8265. Available online: https://www.czso.cz/documents/10180/20555381/13005314q4.pdf/e3140281-cec1-4b6b-82d3-590e442660d1?version=1.0

Abstract
This paper provides a brief introduction to Wilhelm Lexis, his life, and the basic demographic tool that is named after him: the Lexis diagram. This topic is chosen to commemorate the centenary of the death of Wilhelm Lexis, who had an unquestionable influence on demographic research. The Lexis diagram, which is used to display demographic events in a dual time dimension, is an essential instrument for working correctly with demographic data. Therefore, it is not far from the truth to claim that demographers all around the world would be unable to imagine demography without the Lexis diagram, in spite of the fact that the diagram’s ties to Lexis are not so direct.

Pdf: 2014_Hulikova_Demografie.pdf

PODOLSKÁ, K. Jak sluneční aktivita ovlivňuje Zemi a prostředí pro lidskou populaci. Historická demografie. 2014, 38(1+2), 127–155. Available online: http://eu.avcr.cz/miranda2/export/sitesavcr/data.avcr.cz/humansci/eu/Casopisy/Historicka_demografie/Obsahy_rocniku/HD_382_2014.pdf

Abstract
Solar activity has important effect on terrestrial environment in which human population lives. Long-term and short-term periodicities in solar activity had influence on secular climate changes, little ice ages and climatic optima. The article summarizes briefly the results and methods of historical climatology. The text resumes the methods of research of the solar activity variation over the last 1 500 years, through physical methods as well as through preserved written sources. The basic mechanisms of the effects of solar aktivity on terrestrial environment and human population are explained as well as the predictions of the upcoming solar activity. This may indicate that we are currently at the beginning of another long-term solar minimum.

Pdf: 2014_Podolska_Historicka_demografie.pdf

ZIMMERMANN, P., HULÍKOVÁ TESÁRKOVÁ, K., MAZOUCH, P. Missing categorical data imputation and individual observation level imputation. Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis. 2014, 62(6), 1527–1534. DOI: 10.11118/actaun201462061527 Available onine: https://doi.org/10.11118/actaun201462061527

Abstract
Traditional missing data techniques of imputation schemes focus on prediction of the missing value based on other observed values. In the case of continuous missing data the imputation of missing values often focuses on regression models. In the case of categorical data, usual techniques are then focused on classification techniques which sets the missing value to the ‘most likely’ category. This however leads to overrepresentation of the categories which are in general observed more often and hence can lead to biased results in many tasks especially in the case of presence of dominant categories. We present original methodology of imputation of missing values which results in the most likely structure (distribution) of the missing data conditional on the observed values. The methodology is based on the assumption that the categorical variable containing the missing values has multinomial distribution. Values of the parameters of this distribution are than estimated using the multinomial logistic regression. Illustrative example of missing value and its reconstruction of the highest education level of persons in some population is described.

Pdf: 2014_Zimmermann_Acta_Universitatis_Agriculturae.pdf

Jneimp – článek v odborném periodiku neimpaktovaném

RYCHTAŘÍKOVÁ, J. Le rideau de fer encore visible? Population & Avenir.  Novembre-Décembre 2016, no. 730, 15–17. ISSN 0223-5706. Available online: http://www.cairn.info/revue-population-et-avenir-2016-5-page-15.htm 

Abstract
Byla studována prostorová diferenciace vybraných ukazatelů (úhrnná plodnost, střední délka života při narození, hrubý domácí produkt na osobu, podíl cizinců a procento osob ve věku 65+) na základě územních jednotek NUTS 3 v zemích Česka, Slovenska, Maďarska a Rakouska kolem roku 2014. Nebyly nalezeny přeshraniční podobnosti uvedených ukazatelů s výjimkou regionu Bratislava-Vídeň. Typologie provedená pomocí seskupovací analýzy ukázala specifický profil hlavních měst a dále podobné chování v rámci státních hranic zkoumaných zemí. Pouze Rakousko se rozdělilo na dva různé typy. Několik málo rakouských územních jednotek se podobalo českým.

Pdf: 2016_Rychtarikova_Population_Avenir.pdf

Jrec – článek v českém odborném recenzovaném časopise

HULÍKOVÁ TESÁRKOVÁ, K., MAZOUCH, P. Basic cohort mortality analysis at higher ages: An analysis of the rectangularisation process based on cohorts born in 1890–1910 in the Czech Republic and France. Demografie. 2013, 55 (1), 27–46. ISSN 0011-8265. Available online: https://www.czso.cz/documents/10180/20555369/180313q1.pdf/4cbf606a-f9cf-4482-8710-a15cc5caed6c?version=1.0

Abstract
The aim of the article is to conduct a basic mortality analysis of persons aged 60 and over, focusing on the cohort perspective. The Czech Republic and France were selected for comparison. Owing to data availability theanalysis covered cohorts born in 1890–1910, where for each of the two countries it was possible to use data only from one particular source. Moreover, these cohorts can be assumed to be extinct today. People in these cohorts reached the age of 60 and over starting in the year 1950, so it is also possible to study significant period effects on cohort data caused by developments in the second half of the 20th century. This approach makes it possible to study mortality development at the highest ages while using the concept of rectangularisation of the survival curve, or mortality compression, as theoretical basis of the analysis. The assumptions of this concept were not however fully verified for any of the studied populations.

Pdf: 2013_Hulikova_Demografie.pdf

RYCHTAŘÍKOVÁ, J. Sedm miliard světové populace (Seven billions of World Population). Geografické rozhledy. 2012, 22(1), 2–5.

Abstract
Rychle rostoucí počet světového obyvatelstva po druhé světové válce překvapil a dal podnět k obavám o udržitelnost budoucího rozvoje lidských populací. Zejména v šedesátých a sedmdesátých letech vznikaly pesimistické až katastrofické scénáře o možných dopadech přelidnění. I když současný počet světového obyvatelstva činí 7 miliard a pravděpodobně dosáhne svého maxima 10 miliard koncem 21. století, ukazuje se, že lidé vždy nacházejí řešení, neboť minulé obavy z přelidnění se zatím nenaplnily.

Pdf: 2012_Rychtarikova_Geograficke_rozhledy.pdf

B – odborná kniha

HULÍKOVÁ TESÁRKOVÁ, K., KURTINOVÁ, O. Lexis in Demography. Springer International Publishing, 2018. SpringerBriefs in Population Studies, 89 p. Series ISSN 2211-3215, eBook ISBN 978-3-319-67992-1, Softcover ISBN 978-3-319-67990-7. DOI 10.1007/978-3-319-67992-1. Available online: http://www.springer.com/gp/book/9783319679907

Description
This book explores the life of economist and social scientist Wilhelm Lexis and the key demographic instrument named after him: the Lexis diagram. It describes this vital tool, which helps demographers visualize data, and examines its various forms through a specially designed example. As a result, readers get to see the Lexis diagram in practice and gain first-hand insight into its different forms.
The authors first present a brief description of the life of W. Lexis with information about his childhood, studies, and work. Coverage details the places closely related to him as well as his working positions. It also lists and characterizes his publications.
The book then goes on to summarize and describe the chronological development of the Lexis diagram, from initial developments through the specific contributions of W. Lexis to the refinements of those who followed. Throughout, it clearly describes as well as graphically and practically illustrates all the different versions of the diagram covered. Next, readers are presented with contemporary practical applications, including: Statistical Analysis System (SAS), R, and Stata software as well as selected key-studies from demographic, epidemiologic, and migration research.
The Lexis diagram is an essential tool for working correctly with demographic data. This book commemorates the man who helped to develop these diagrams and his unquestionable influence on demography. It also provides readers with deep knowledge and insights into this basic, yet important, tool.

Pdf: nelze publikovat na webu

HULÍKOVÁ TESÁRKOVÁ, K. Selected demographic methods of mortality analysis: Approaches focused on adults and the oldest age-groups using primarily cross-sectional data. LAP LAMBERT Academic Publishing, 2013 (June 5). 404 p. ISBN 978-3659404139.

Description
The monograph is partially based on the Doctoral Thesis defended in 2012 and describes selected methods of mortality analysis. The book also discusses several comparisons of mortality in the Czech Republic and other demographically developed countries. The topic fully corresponds with the grant project.

Pdf: nelze publikovat na webu

C – kapitola v odborné knize

RYCHTAŘÍKOVÁ, J., HULÍKOVÁ TESÁRKOVÁ, K. Potential reduction in mortality associated with the shifts of population educational structures in the Czech Republic. In: DORSZEWSKA, J., KOZUBSKI, W. (eds.). Senescence - Physiology or Pathology. InTech, 2017. ISBN 978-953-51-3462-6, Print ISBN 978-953-51-3461-9. Published: August 30, 2017 under CC BY 3.0 license. DOI: 10.5772/intechopen.69635. Available from: https://www.intechopen.com/books/senescence-physiology-or-pathology/potential-reduction-in-mortality-associated-with-the-shifts-of-population-educational-structures-in-  

Abstract
Educational inequalities in mortality are large in Central and Eastern Europe. Mortality levels are particularly high among low educated men as well as women in the Czech Republic. However, differences in male mortality by educational attainment exceed those of females. Two mortality patterns are apparent when dividing the Czech classification of education into four categories—basic, vocational, secondary, and university. Males with basic education experience much higher mortality when compared to their higher educated counterparts. An anomaly in the mortality gradient is observed among women when comparing basic and vocational education. Women with basic education show a rather lower mortality level compared to their vocational counterparts. Three scenarios show how the shifts toward a higher education could contribute to the change in mortality level using temporary life expectancies between ages 30 and 80 for males and females: (a) population structure by sex, age, and education remains the same as from the census 2011; (b) 60% of males having the basic education move into the next higher category (vocational) and 60% of women with basic and vocational education move into the secondary education; and (3) sex age education‐specific mortality rates will be shifted upwards by one level.

Pdf: nelze publikovat na webu

D – článek ve sborníku

MAZOUCH, P. Short period mortality shift and its effect to cohort mortality. 14th International Scientific Conference Economic Policy in the European Union Member Countries. Petrovice u Karviné, Karviná: School of Business Administration in Karvina, 14. 9. 2016 – 16. 9. 2016. Available online: http://www.slu.cz/opf/cz/struktura/katedry/katedra-ekonomie-a-verejne-spravy/konference-kek-2016/Conference_Proceedings_part-2.pdf

Abstract
For cohort life table information about mortality for 100 years is needed. As is known Czech Republic and many other regions have problem with this assumption because of some short time periods with weak or no information about mortality patterns in detailed structure. On the other hand information about cohort mortality is very important for many institutions as pension funds, government and others. How to solve problem with this periods with poor information about mortality patterns is the aim of the paper. We would like to quantify impact of short time over- or undervalued mortality (as effect of war or other crises) to total mortality of cohort. Different impact is expected as different period of the lifetime of the cohort is affected by the period with different mortality patterns. This is very important for regions where those periods were in history and where cohort life tables are not constructed yet because of this problem

Pdf: 2016_Mazouch_HPinEU.pdf

MAZOUCH, P. War effect to cohort life tables in the Czech Republic. AMSE 2016 (Applications of Mathematics and Statistics in Economics). Banská Štiavnica, 31. 8. 2016 – 4. 9. 2016. Available online: http://www.amse.umb.sk/proceedings/Mazouch.pdf

Abstract
Nowadays cohort life tables have become more important for many reasons. Information about mortality patterns in the cohort perspective is relevant for insurance companies, pension funds, but also for the professional public in general. For a cohort life table, data of about at least 100 years are needed. Official data of mortality in the Czech Republic have periods with no or very poor information. The aim of this paper is to describe a possibility how to bridge one of those periods – the Second World War where there is a lack of information – and to discuss influence of short term periods on the mortality level of all cohorts. Real data are compared with models and influence to total life expectancy is measured.

Pdf: 2016_Mazouch_AMSE.pdf

ZIMMERMANN, P., MAZOUCH, P., HULÍKOVÁ TESÁRKOVÁ, K. The difference in present value of retirement pensions for education groups. In: The 8th International Days of Statistics and Economics. Slaný: MELANDRIUM, 2014, p. 1715–1721. ISBN 978-80-87990-02-5. Available online: https://msed.vse.cz/msed_2014/article/397-Zimmermann-Pavel-paper.pdf

Abstract
The retirement pension in the Czech Republic is to some extend dependent on the preretirement average income. Due to the fact that the average income is higher for segments of population with higher education, the retirement pension will also tend to be higher for individuals with higher education. There is however also an additional aspect amplifying this difference which is rarely mentioned in this context. Namely the fact that the population segments with higher education have also higher expected lifetime and hence not only that they earn higher annuity amounts but also they on average earn the pension longer. Both these aspects contribute to the difference in the present value of a retirement pension. The purpose of this article is to quantify this difference of the retirement pension by four education groups using the income statistics and unique life tables constructed for different educational groups. The results show that differences are relatively large.

Pdf: 2014_Zimmermann_The_8th_International_Days_of_Statistics_and_Economics.pdf

KLADÍVKO, K., ZIMMERMANN, P. Index Clause Valuation under Stochastic Inflation and Interest Rate. In: Mathematical Methods in Economics 2014. Olomouc: Palacký University, 2014, p. 413–419. ISBN 978-80-244-4209-9. Available online: http://www.mme2014.upol.cz/downloads/MME_2014_Proceedings.pdf

Abstract
This work is focused on valuation of the reinsurer’s share on a particular accident, stemming from the excess of loss (XL) reinsurance contract that applies to a general insurance annuity compensation, e.g., motor liability or workmen’s compensation. The excess of loss (XL) reinsurance contract is an insurance contract between the insurer and reinsurer, which guarantees recovery payment to the insurance company for each accident in the amount of the accident that the insurance company pays off in excess of a contracted priority.
Special focus is set on the impact of the so called index clause which is usually included to the reinsurance contract. The index clause allows the reinsurer to increase the originally agreed priority by a coefficient which is, roughly said, calculated as a ratio of the sum of all nominal payments to the sum of all deflated payments.
Analytic valuation formula does not exist for the reinsurer’s share without the index clause. Hence simulation model is used to perform the study. We assume a geometric Brownian motion for the inflation index and an Ornstein-Uhlenbeck process for the discount rate, where we allow the two processes to be correlated.

Pdf: 2014_Kladivko_Mathematical_Methods_in_Economics_2014.pdf

ZIMMERMANN, P., MAZOUCH, P., HULÍKOVÁ TESÁRKOVÁ, K. Categorical data imputation under MAR missing scheme. In: Mathematical Methods in Economics 2013. Jihlava: College of Polytechnics, 2013, p. 1052–1056. ISBN 978-80-87035-76-4. Available online: https://www.vspj.cz/soubory/download/id/2259

Abstract
Traditional missing data techniques of imputation of the MAR (missing at random) schemes focus on prediction of the missing value based on other observed values. In the case of continuous missing data the imputation of missing values often focuses on regression models. In the case of categorical data, usual techniques are then focused on classification techniques which sets the missing value to the ‘most likely’ category. This however leads to overrepresentation of the categories which are in general observed more often and hence can lead to biased results in many tasks especially in the case of presence of dominant categories. We present original methodology of imputation of missing values which results in the most likely structure (distribution) of the missing data conditional on the observed values. The methodology is based on the assumption that the categorical variable containing the missing values has multinomial distribution. Values of the parameters of this distribution are than estimated using the multinomial logistic regression.

Pdf: 2013_Zimmermann_Mathematical_Methods_in_Economics_2013.pdf

Ostatní tištěné publikace

RYCHTAŘÍKOVÁ, J., HULÍKOVÁ TESÁRKOVÁ, K. Proměny světa očima demografů (Changes of the World from demographic perspective). Přírodovědci.cz – magazín Přírodovědecké fakulty UK v Praze. 2013, 1. p. 18-19. ISSN 1805-5591.

Description
The world population recently reached seven billion. The article briefly introduces past population development in the world as a whole, as well as in regional perspective and its particularities. Above all, the different developmental trends in the developing and developed countries are confronted. Furthermore, information about the expected future development is included, as well as the causes and consequences of future demographic changes in the world.

Available online: https://www.prirodovedci.cz/templates/modules/magazin/pc/index.php?uuid=7ed88634-bf09-11e2-9cdd-0015172001f0

MAZOUCH, P. Generační úmrtnost a její modelování. Prague, 2013. Master Thesis (Mgr.). Charles University in Prague. Faculty of Science, Department of Demography and Geodemography.

Description
The aim of the thesis is to introduce a simple alternative approach of mortality modeling (future estimates of mortality rates) which is based on cohort mortality patterns. The assumption of constant change of the force of mortality between two following ages across cohorts is the fundamental base of the proposed model. Theoretical aspects of the model are discussed and its assumptions are verified on time series of Swedish data which are long enough for this purpose. Results of the model application are compared with empirical results of already extinct cohorts and some estimates for still living cohorts are made too. Applications on real data showed good results which respected changes in the mortality development. In the last part of the thesis some possible modification are discussed which could cause results less variable.

Pdf: nelze publikovat na webu

HULÍKOVÁ TESÁRKOVÁ, K. Selected methods of mortality analysis focused on adults and the oldest age-groups. Prague, 2012. Doctoral Thesis (Ph.D.). Charles University in Prague. Faculty of Science, Department of Demography and Geodemography, 259 pp.

Description
The Doctoral Thesis introduces several different methods of mortality analysis and additionally contains basic comparison of mortality development in the Czech Republic in comparison to other (mostly European) countries. Some of the methods will be used in the grant project

Pdf: nelze publikovat na webu