search query: @all failure / total: 1463
reference: 5 / 1463
| Author: | Cader, H.A. Leatherman, J.C. |
| Title: | Small business survival and sample selection bias |
| Journal: | Small business economics
2011 : SEP, VOL. 37:2, p. 155-165 |
| Index terms: | small business new enterprise business failures companies regression analysis economics bias |
| Freeterms: | United States |
| Language: | eng |
| Abstract: | Analyses of small business and the elements influencing their survival are quite common in the research literature. The level of research interest may result from the fact that in the US, only about half of all new small businesses survive the first 4 years (Headd 2003). However, attempts to understand the phenomenon that employs data using only information concerning surviving firms may lead to erroneous conclusions regarding the factors of firm survival and failure. This paper provides evidence that omitted information about the firms disappearing from the research data over time biases the coefficient estimates. Comparing the Heckman two-step estimation scheme of switching regression models to a semi-parametric Cox hazard model, the Accelerated Failure Time (AFT) model, the conclusion is that the Cox ATF approach performs best for firm survival analysis. |
SCIMA