Resources, dynamic capabilities, and performance: evidence from Polish green innovative companies

• Autorzy: Pichlak Magdalena

Identyfikatory

DOI

10.29119/1641-3466.2021.153.26

• Języki publikacji: EN

Abstrakty

EN

Purpose: The development of technology has allowed creating and using the new, more complex computational tools in static and econometrics in recent years. Since then, resampling methods has become more popular techniques in estimating statistics from small samples. The aim of the article is to present and to compare the bootstrap and the jackknife methods in estimation of interested statistics with explaining and illustrating the usefulness and limitation in the context of using in econometric. Design/methodology/approach: To compare and present the methods, data of the length of bicycle paths divided into 371 polish counties from 2019 was received from Local Data Bank. From the data three samples were randomly selected and used as bootstrap and jackknife samples. Using the bootstrap and the jackknife simulations confidential intervals of the searching statistics with standard error were calculated. Results obtained for the methods were compared and described. Research limitations/implications: An analysis of these methods will allow improving the efficiency and reducing the error in estimating confidence intervals for searching statistics. Findings: As presented in the article, both the methods can be used to estimate mean, however, slightly better results are provided by the bootstrap. Furthermore, confidence intervals for confidence level at 95% created by these methods cover the population mean for each sample randomly selected from the population. To estimate standard deviation the better option is to choose the bootstrap method. Although, both confidence intervals for confidence at level 95% cover the population standard deviation, the bootstrap methods perform more accurate results with a smaller standard deviation. Originality/value: It was proven that the bootstrap method is slightly better in estimation confidence intervals based on the skewed data in comparison with the jackknife method.

Słowa kluczowe

EN

bootstrap; resampling; simulations; confidential interval; jackknife

PL

bootstrap; resampling; symulacje

• Wydawca: Wydawnictwo Politechniki Śląskiej
• Czasopismo: Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska
• Rocznik: 2021
• Tom: z. 153
• Strony: 445--455
• Opis fizyczny: Bibliogr. 11 poz.

Twórcy

autor

Pichlak Magdalena

• University of Economics, Katowice

• https://orcid.org/0000-0001-5721-2475

Bibliografia

• 1. Beran, R., and Ducharme, G.R. (1991). Asymptotic Theory for Bootstrap Methods in Statistics. Montreal: Les Publications CRM.
• 2. Dunaj, J. (2017). Bootstrap i jego zastosowania do analizy wrażliwości estymatora wartości zagrożonej, https://ftims.pg.edu.pl/katedra-analizy-nieliniowej-i-statystyki/prace-dyplomowe.
• 3. Efron, B., Stein, C. (1981). The jackknife in estimate of variance. The analyst of statistics Vol. 9, Iss. 3, pp. 586-596.
• 4. Efron, B., Tibshirani, J.R. (1993). An Introduction to the Bootstrap. New York: Chapman and Hall.
• 5. Hansen, E.B. (2001). Econometrics. Wisconsin: University of Wisconsin, Department of Economics, pp. 253-270.
• 6. Hasenberg, T., Monaghan, S., Moore, S.D., Clipson, A., Epstein, R. (2003). Bootstrap Methods and Permutation tests. New York: W.H. Freeman and Company, pp. 11-13.
• 7. Kamiński, A. (2010). Wykorzystanie algorytmów Bootstrap i Jacknife w estymacji parametrów regresji, http://docplayer.pl/36440257-Wykorzystanie-algorytmow-bootstrap-i-jacknife-w-estymacji-parametrow-regresji.html.
• 8. Kończak, G. (2012) Wprowadzenie do symulacji komputerowych. Katowice: Wydawnictwo Uniwersytetu Ekonomicznego.
• 9. McIntosh, A. (2016). The Jackknife Estimation Method, https://arxiv.org/abs/1606.00497.
• 10. Miller, G.R. (1974). The Jackknife – A Review. Biometrika, Vol. 61, Iss. 1, pp. 1-15.
• 11. Nguyenova, L. (2020). Bootstrapping vs. jackknife, https://medium.com/@ lymielynn/ bootstrapping-vs-jackknife-d5172965207b.