Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

Results found: 3

first rewind previous Page / 1 next fast forward last

Search results

Search:
in the keywords:  COX MODEL
help Sort By:

help Limit search:
first rewind previous Page / 1 next fast forward last
1

WOMEN'S PARALLEL CAREERS IN POLAND BEFORE THE TRANSITION IN THE LIGHT OF RETROSPECTIVE SURVEYS OF 1988 AND 1991. PARAMETRIC AND SEMIPARAMETRIC MODELING

100%
Ptak-Chmielewska A.
Studia Demograficzne
|
2005
|
issue 1(147)
72-103
EN
This analysis focuses on three parallel careers (means realized at the same time and influencing each other): family, occupational and migratory careers, which together constitute the biography of the individual. The most important question is concerned with the diversity of courses those careers can take within an individual. There are three main purposes of this article: to describe the range of interdependencies between careers (events from those careers), to specify the course of each career realized by an individual, and to identify causal mechanisms. Two types of models were selected in order to answer the questions outlined above: parametric models and semi-parametric models. The piecewise constant exponential model accounts for the parametric model and the Cox model represents the semi-parametric one. The parametric model allows for a description of a hazard function shape and the semi-parametric controls for causality mechanisms by including time dependent variables. All analyses are based on data from two retrospective surveys, which were conducted in Poland in 1988 and 1991. Data from both surveys are complementary and has been constructed a common database. Results confirm that parallel processes influence each other, however, in the case of Polish women before the transformation period this influence was rather small. Economically inactive women had a higher (ca 10%) risk of having a child compared to working women. The subsequent migration decreased the risk of having a child (ca 12%). When deciding about whether or not to have a second child, occupational situation was not significant; the subsequent migration had a small negative influence (decreased hazard rate about 5%).
2

Modeling the disability-free life expectancy

100%
Gazinska M., Mojsiewicz M.
Studia Demograficzne
|
2004
|
issue 1(145)
75-91
EN
The life expectancy depends greatly on health - morbidity, disability and invalidity. A rise of life expectancy and increased morbidity make problems of the disabled people even more important; in many countries disability becomes more common. This paper presents methods of modeling the life expectancy without disability.The sample survey of disable persons was used to estimate the disability-free life table and to verify Gompertz, Weilbull, exponential and linear-expotential disability hazard functions. None of these functions was accepted to describe the disability hazard for the total surveyed population.The hypothesis that a probability of becoming disabled depends on age, sex, education, type of disability certificate, causes of disability, necessary support and subjective restraints from taking up a job was verified by the use of the semiparametric Cox model of proportional hazards. It was concluded that only age influence significantly the disability hazard. For people in the working age results of the disability-free life tables as well as Gompertz, Weilbull, exponential and linear-exponential disability hazard functions, estimated separately for the considered age groups, provided acceptable results except for the age 45-54. About 10 years before reaching the retirement age the disability hazard rate increased markedly and according to the estimated Cox model depends strongly on restraints in taking up jobs and needed care as well as on sex. Therefore disability hazard functions should be specified by sex.
3

Zastosowanie modelu Coxa do prognozowania upadłości przedsiębiorstw notowanych na Giełdzie Papierów Wartościowych w Warszawie

100%
Mihilewicz K.
Zeszyty Naukowe Uniwersytetu Ekonomicznego w Krakowie
|
2012
|
issue 895
79-88
EN
The article presents a proposal for modeling enterprise insolvency by means of survival analysis, which is used to study various occurrences that depend on the passage of time. The study used a popular model of survival analysis commonly known as the proportional hazard model, which takes into account both microeconomic conditions described by company financial indicators, and external macroeconomic factors associated with the overall economic situation. The study was conducted on the basis of companies listed on the Warsaw Stock Exchange.
first rewind previous Page / 1 next fast forward last
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.