Early warning model with statistical analysis procedures in Turkish insurance companies
Year: 2010
Type: article
Abstract: In this study, we have developed and tested a statistical early warning model to identify companiesexperiencing deteriorating financial health by examining 45 insurance companies acting in non-lifeelementary branches of insurance during the period between 1992 and 2006. We developed themodel using data regarding 45 dependent and 17 independent variables and logit model. Thepresent study extends previous analyses by using relatively more comprehensive accounting data inlogit analysis. This study compared the ability of logit, discriminant and regression analyses to predictinsurance company underperformance. The same model, comprised of identical variables, wasobtained as the result of the multiple regression and multiple discriminator methods. When comparingthe predictive ability of all three models, the logit model showed slightly better prediction ability thanthe other models. The three models used information from 2003 - 2006 to predict the performance ofinsurance companies in 2007. The research demonstrates that logit analysis has a strong potential.
DOI: 10.5897/ajbm.9000232
Authors: Gülsün İŞSEVEROĞLU, Ümit Gücenme
Language: English
Subfield: Accounting
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W2161997528