Search results

1

SEMIPARAMETRIC COX REGRESSION MODEL IN ESTIMATION OF SMALL AND MICRO ENTERPRISES’ SURVIVAL IN THE MALOPOLSKA VOIVODESHIP

100%

Ptak-Chmielewska A.

Metody Ilościowe w Badaniach Ekonomicznych

|

2013

|

vol. 14

|

issue 2

169-180

EN

This paper aims at identifying factors (external and internal) affecting the ability of an enterprise to survive on the market. The analysis is based on the results of a retrospective study conducted in 2012 on a sample of enterprises from Malopolska voivodeship. Methods and models of event history analysis, including semiparametric Cox’s model were applied to analyse enterprises’ survival. The approach based on the event history analysis allows us to include dynamics of the process. The results provided extensive data on how factors such as size, activity sector, market range, legal form and internals conditions like: owner characteristics, investments, profits, reported barriers affect the survival of enterprises.

2

Survival analysis: a case study of micro and small enterprises in Dolnośląskie and Opolskie Voivodship (Poland)

100%

ŁOBOS K., SZEWCZYK M.

Central and Eastern European Journal of Management and Economics (CEEJME)

|

2013

|

vol. 1

|

issue 2

123-140

EN

The aim of the study is to achieve initial recognition of the factors that determine the survival rate of Polish micro and small enterprises. The research, conducted in June 2011 and covering a sample of 147 entities, constitutes a pilot study. We explore the determinants of companies’ survival and test whether firms with different characteristics exhibit different performances in terms of the duration of survival. The results indicate substantial differences in the survival rates. The factors taken into account in this study, which to the greatest extent possible differentiates the whole sample in view of survival, are: running the business with employees or alone and specialist vs. popular activity as regards the required competences. Larger firms (with employees) are significantly less likely to close than smaller firms. Firms in highly competitive markets are more prone to closure.

3

DEFAULT PREDICTION FOR SME USING DISCRIMINANT AND SURVIVAL MODELS, EVIDENCE FROM POLISH MARKET

100%

Ptak-Chmielewska A., Matuszyk A.

Metody Ilościowe w Badaniach Ekonomicznych

|

2014

|

vol. 15

|

issue 2

369-381

EN

The aim of this paper was to compare the new technique (survival analysis) used in the credit risk models with the traditional one (discriminant analysis), analyse the strengths and weaknesses of both methods and their usage in practice. This study attempts to use macroeconomic data to build models and examine its impact to the prediction. For this purpose, a number of models was built on the basis of the sample of 1547 enterprises including 494 defaults. The time range covered by sample was 2002-2012.

4

Slábne v ČR mezigenerační přenos rozvodu?

100%

Trávníčková M., Kreidl M.

Sociologický časopis. Czech Sociological Review

|

2021

|

vol. 57

|

issue 5

531-555

EN

This study investigates changes in the effect of parental divorce on the odds of union dissolution in children in the Czech Republic. Using survival analysis and Czech GGS data, it shows that the intergeneration transmission of divorce varied over marital cohorts to a significant degree. While parental divorce had insignificant effect in the oldest marriage cohort, it subsequently grew. In the 1980–1989 marriage cohort, the risk of divorce was 3.7 times higher among children of divorced parents than among children whose parents did not divorce. In the most recent marriage cohort (1990–2005), the parental divorce effect weakened but was still significant: children of divorced parents experienced a divorce risk that was twice as high that of children from intact families. This convergence of divorce risks resulted from two parallel trends: the rising divorce risk among children from non-divorced families and the declining divorce risk among children of divorce.

5

Determinants of premature mortality in a city population: An eight-year observational study concerning subjects aged 18–64

100%

Maniecka-Bryła I., Dziankowska-Zaborszczyk E., Bryła M., Drygas W.

International Journal of Occupational Medicine and Environmental Health

|

2013

|

vol. 26

|

issue 5

724-741

EN

Background: Premature deaths constitute 31.1% of all deaths in Łódź. Analysis of the causes of premature deaths may be helpful in the evaluation of health risk factors. Moreover, findings of this study may enhance prophylactic measures. Material and Methods: In 2001, 1857 randomly selected citizens, aged 18-64, were included in the Countrywide Integrated Noncommunicable Diseases Intervention (CINDI) Programme. In 2009, a follow-up study was conducted and information on the subjects of the study was collected concerning their health status and if they continued to live in Łódź. The Cox proportional hazards model was used for evaluation of hazard coefficients. We adjusted our calculations for age and sex. The analysis revealed statistically significant associations between the number of premature deaths of the citizens of Łódź and the following variables: a negative self-evaluation of health - HR = 3.096 (95% CI: 1.729-5.543), poor financial situation - HR = 2.811 (95% CI: 1.183‑6.672), occurring in the year preceding the study: coronary pain - HR = 2.754 (95% CI: 1.167-6.494), depression - HR = 2.001 (95% CI: 1.222-3.277) and insomnia - HR = 1.660 (95% CI: 1.029-2.678). Our research study also found a negative influence of smoking on the health status - HR = 2.782 (95% CI: 1.581-4.891). Moreover, we conducted survival analyses according to sex and age with Kaplan-Meier curves. Conclusions: The risk factors leading to premature deaths were found to be highly significant but possible to reduce by modifying lifestyle-related health behaviours. The confirmed determinants of premature mortality indicate a need to spread and intensify prophylactic activities in Poland, which is a post-communist country, in particular, in the field of cardiovascular diseases.

6

Does experience exert impact on a public-private partnership performance? The case of Poland

100%

Węgrzyn J.

Equilibrium. Quarterly Journal of Economics and Economic Policy

|

2018

|

vol. 13

|

issue 3

509-522

EN

Research background: Researchers traditionally assume that learning is a product of experience. In general, it means that learning can only take place through the attempt to solve a problem and therefore only takes place during activity (Arrow, 1962). On the ground of organizational theory, it has two implications. First, we can agree that repeated activity requires less effort. Second, we can argue that firms undertake activities, with which they have been the most successful in the past and that they expect to be the most successful in the future. Purpose of the article: The aim of the research is twofold. Firstly, this article aims to investigate if we can identify a relationship between the experience in PPP projects and the performance of initiatives of this kind. Secondly, the article aims to provide an interpretation of the relationship between experience and PPP performance. Methods: This research investigates factors influencing the survival of PPP projects in Poland over the period 2009?2015. Cox proportional hazard model is utilized to distinguish between PPPs that succeeded to the operation phase and those that were canceled on the procurement stage. Findings & Value added: The research confirms the existence of a positive relationship between experience in PPP and the outcome of a PPP development.

7

Modele predykcji upadłości MŚP w Polsce – analiza z wykorzystaniem modelu przeżycia Coxa i modelu regresji logistycznej

100%

Ptak-Chmielewska A.

Econometrics. Ekonometria. Advances in Applied Data Analytics

|

2014

|

issue 4(46)

9-21

EN

Modele predykcji upadłości MŚP w Polsce – analiza z wykorzystaniem modelu przeżycia Coxa i modelu regresji logistycznej

8

Płeć, wiek i wykształcenie osób bezrobotnych jako determinanty czasu poszukiwania pracy

100%

Bieszk-Stolorz B., Markowicz I.

Econometrics. Ekonometria. Advances in Applied Data Analytics

|

2013

|

issue 2(40)

74-86

EN

The paper presents results of survey concerning the influence of gender, age and education of the unemployed on job searching time. For the sake of specificity of survey, especially in case of censored data, the Cox’s proportional hazard model has been used for the identification of determinants and research their influence for time needed to take up a job. To the model, except independent variables, their interactions that enable the calculation of interplay of researched variables have been included. 20846 persons registered as unemployed in the Local Labour Office in Szczecin and due to various reasons unregistered in 2010 have been included in the research. If unregistering occurred due to different reasons than finding a job, such an observation has been considered as censored.

9

Extensions of cox model for non-proportional hazards purpose

100%

Borucka J.

Econometrics. Ekonometria. Advances in Applied Data Analytics

|

2014

|

issue 3(45)

85-101

EN

Cox proportional hazard model is one of the most common methods used in time to event analysis. The idea of the model is to define a hazard level as a dependent variable which is explained by the time-related component (so-called baseline hazard) and the covariates- related component. The model is based on several restrictive assumptions one of which is the assumption of proportional hazard. However, if this assumption is violated, this does not necessarily prevent an analyst from using Cox model. The current paper presents two ways of model modification in the case of non-proportional hazards: introducing interactions of selected covariates with function of time and stratification model. Calculations performed give the evidence that both methods result in better model fit as compared with the original model. Additionally, they allow interpreting the parameters estimates more precisely, taking into account the effect of the covariate at the hazard level that is changing over time. The choice of the appropriate method of tied events handling however is not straightforward and should be adjusted to the particular analysis purpose.

10

Analysis of the risk of liquidation depending on the age of the company: a study of entities established in Szczecin in period 1990--2010

100%

Markowicz I.

Econometrics. Ekonometria. Advances in Applied Data Analytics

|

2019

|

issue vol. 23 no. 2

49-62

EN

The aim of the research was an assessment of the relative risk of liquidation of a company depending on its age. The research covered economic entities established in Szczecin in the period 1990-2010. The analysis was carried out with the use of a logit model. The risk of company liquidation was examined depending on the entity’s age expressed both in months (continuous variable) and in grouped intervals (year, half-year). In this way, attention was drawn to the benefits of continuous variable coding (rank and 0-1 coding). The research covered companies established during 1990-2010 in total (over 120 thousand) and in time periods resulting from the cyclical character of liquidation of companies (in accordance with the earlier research findings). The research showed that the risk of company liquidation decreases as the company grows older (the use of a continuous variable and a rank variable). On the other hand, the risk of subsequent age groups (using the 0-1 variable) prevents the risk from being monotonous.

11

Analysis of Censored Life-tables with Covariates by Means of Log-linear Models

100%

Rossa A., University of Łódź D. o. S. M.

Acta Universitatis Lodziensis. Folia Oeconomica

|

2004

|

vol. 175

EN

88%

Jurkiewicz T., Wycinka E., Uniwersytet Gdański; Wydział Zarządzania; Katedra Statystyki

Acta Universitatis Lodziensis. Folia Oeconomica

|

2011

|

vol. 255

PL

Analiza przeżycia to zespół metod służących do modelowania czasu trwania kohorty, której jednostki są obserwowane od zdefiniowanego momentu początkowego do zdefiniowanego zdarzenia końcowego. Czas trwania jest traktowany jako zmienna losowa ciągła. Specyfika metod analizy przeżycia związana jest z występowaniem obserwacji cenzurowanych (uciętych) oraz tym, iż funkcje gęstości obserwowanej zmiennej są często nieznane, a rozkłady silnie asymetryczne, co uniemożliwia stosowanie metod klasycznej statystyki. Podstawową funkcją stosowaną w analizie przeżycia jest funkcja dalszego trwania wyrażająca prawdopodobieństwo, że jednostka nie doświadczy zdarzenia końcowego przed czasem t. Metodą oceny, czy pewne zmienne mają wpływ na zróżnicowanie czasu trwania jednostek, jest przeprowadzanie testów porównujących krzywe przeżycia na podstawie dwóch (lub więcej prób). Znaczna liczba tych testów została zaproponowana w ostatnich latach, w tym testy: Log-rank, będący jednym z lub najpopularniejszym, test Gehana, Tarone-Ware, Peto-Peto, Harringtona-Fleminga, testy typu Renyi. W literaturze mało uwagi poświęca się jednakże porównaniu własności tych testów. W poniższym opracowaniu przeprowadzono, przy wykorzystaniu metody Monte Carlo, analizę porównawczą mocy predykcyjnej testów dla dwóch krzywych przeżycia w małych próbach z różnym udziałem jednostek cenzurowanych. Losowano próby z populacji o założonym rozkładzie Weibulla przy różnych proporcjach jednostek kompletnych i cenzurowanych (o losowej kolejności pojawiania się ustalanej w oparciu o rozkład jednostajny) w celu określenia efektywnej wielkości prób dla poszczególnych testów. Szczególną wagę poświęcono problemowi krzyżowania się krzywych przeżycia i zdolności testów do wykrywania różnic między krzywymi przeżycia w takiej sytuacji.

18

Gender Disparities in the Duration of Unemployment Spells in Slovenia

75%

Pašič P., Kavkler A., Boršič D.

South East European Journal of Economics and Business

|

2011

|

vol. 6

|

issue 1

99-110

EN

The paper offers an overview of labor market characteristics in Slovenia with an emphasis on gender disparities. A survival analysis is conducted based on an extensive database obtained from the Employment Office of the Republic of Slovenia of more than 450,000 unemployment incidences between January 2004 and July 2008. Kaplan-Meier estimates of survival functions show specific disparities among unemployed women and men in Slovenia. Unemployed men are better off when re-entering the labor market as they are re-employed more quickly than women.

19

Faster health deterioration among nail technicians occupationally exposed to low levels of volatile organic compounds

75%

Grešner P., Świercz R., Wąsowicz W., Gromadzińska J.

International Journal of Occupational Medicine and Environmental Health

|

2016

|

vol. 30

|

issue 3

469-483

EN

Objectives The study has aimed at investigating the subjective assessment of an individual’s health status and comparing the prevalence of selected work-related symptoms among nail technicians occupationally exposed to volatile organic compounds (VOCs) to the one among control subjects. Associations between occupational exposure to VOCs and the incidence of adverse health effects were also analyzed. Material and Methods The study involved 145 female nail technicians and 152 control subjects. Data on the prevalence of adverse health effects was collected using the researcher- made questionnaire and then analyzed by means of survival analysis methods. Results Only 22% of nail technicians as compared to 45% of control subjects described their current health status as “excellent” or “very good” (odds ratio (OR) = 0.4, 95% confidence interval (CI): 0.2–0.6, p < 0.00005). In general, 61% of nail technicians confirmed to have experienced any out of all symptoms considered in the study since the commencement of the job, which was significantly higher as compared to 17% of control subjects (adjusted OR = 2.8, 95% CI: 2.1–3.7, p < 0.0001). Estimated median length of the employment period free of investigated symptoms was significantly shorter among nail technicians as compared to controls (12 years vs. 33 years, p < 0.0001), consistent with almost 4-times increased hazard of the occurrence of such symptoms among the technicians (hazard ratio (HR) = 3.9, 95% CI: 2.7–5.7, p < 0.0001). Cox proportional hazard regression modeling revealed almost 5-times increased hazard of the occurrence of any symptoms among nail technicians exposed to higher levels of the mixture of VOCs as compared to those exposed to lower levels (HR = 4.9, 95% CI: 1–24.1, p = 0.05). Conclusions All outcomes combined together indicate that nail technicians are subject to faster health deterioration, which may be assumed to be caused by occupational exposure to low levels of VOCs. Int J Occup Med Environ Health 2017;30(3):469–483

20

Modelowanie czasu do zaprzestania spłat rat kredytu lub wcześniejszej spłaty kredytu jako zdarzeń konkurujących

75%

Wycinka E.

Problemy Zarządzania

|

2015

|

issue 3/2015 (55), t.2

146-157

EN

Early repayment and default are two basic perils causing credit termination. Who of the borrowers and when are at the risk of both events is important information for the creditor. The article employs some of the estimators of the method of competing risks to model time to default or early repayment. The empirical part of the article consists of the results of the study on the sample of 5000 five-year loans that were observed for 24 months. Probabilities of default and early repayment have been evaluated by means of selected estimators. These estimators are also suitable for distinguishing borrowers with different risks of default.

PL

Ryzyko niewypłacalności i ryzyko przedwczesnej spłaty to dwa podstawowe zdarzenia powodujące przerwanie umowy kredytowej. Dla kredytodawcy istotna jest informacja, którzy kredytobiorcy i w jakim okresie od udzielenia kredytu są bardziej narażeni na każde z tych zdarzeń. W artykule zaproponowano wykorzystanie metody zdarzeń konkurujących umożliwiającej modelowanie w czasie obu powyższych zdarzeń. W części empirycznej artykułu przeprowadzono estymację na próbie 5000 pięcioletnich pożyczek, które były obserwowane przez okres 24 miesięcy od udzielenia. Za pomocą wybranych estymatorów wyznaczone zostały prawdopodobieństwa analizowanych zdarzeń. Omawiane estymatory służyć mogą również do wyodrębniania kredytobiorców o różnym ryzyku niewypłacalności.

Refine search results

SEMIPARAMETRIC COX REGRESSION MODEL IN ESTIMATION OF SMALL AND MICRO ENTERPRISES’ SURVIVAL IN THE MALOPOLSKA VOIVODESHIP

Survival analysis: a case study of micro and small enterprises in Dolnośląskie and Opolskie Voivodship (Poland)

DEFAULT PREDICTION FOR SME USING DISCRIMINANT AND SURVIVAL MODELS, EVIDENCE FROM POLISH MARKET

Slábne v ČR mezigenerační přenos rozvodu?

Determinants of premature mortality in a city population: An eight-year observational study concerning subjects aged 18–64

Does experience exert impact on a public-private partnership performance? The case of Poland

Modele predykcji upadłości MŚP w Polsce – analiza z wykorzystaniem modelu przeżycia Coxa i modelu regresji logistycznej

Płeć, wiek i wykształcenie osób bezrobotnych jako determinanty czasu poszukiwania pracy

Extensions of cox model for non-proportional hazards purpose

Analysis of the risk of liquidation depending on the age of the company: a study of entities established in Szczecin in period 1990--2010

Analysis of Censored Life-tables with Covariates by Means of Log-linear Models

Unbiased Estimation of Survival Probabilities for Censored Data with Known Censoring Times

Mobilita mezi zaměstnaností a nezaměstnaností u starších pracovníků v ČR

Další vzdělávání dospělých v České republice – kdo se ho účastní a s jakými důsledky?

Duration Models in Loan Management

Partnerské dráhy prvorodiček bez partnera ve společné domácnosti

Significance tests of differences between two crossing survival curves for small samples

Gender Disparities in the Duration of Unemployment Spells in Slovenia

Faster health deterioration among nail technicians occupationally exposed to low levels of volatile organic compounds

Modelowanie czasu do zaprzestania spłat rat kredytu lub wcześniejszej spłaty kredytu jako zdarzeń konkurujących