Multiple regression applications to capital structure modeling for life insurers

Like any other company, life insurance companies maintain a combination of debt and equity for their long-term financing, which forms their capital structure. Many theories have been developed in the literature to focus upon the determinants that are likely to affect leverage decisions of the life insurance firms in the post life Risk-Based Capital (RBC) regulation era. This report documents the application of multiple regression techniques to derive and analyze a Capital Asset Ratio (CAP) model based on the data pertaining to a large number of life insurance companies during 2000 to 2004. The data set is organized as panel data. Model coefficients, together with the error structure, are analyzed using SAS software to develop a valid model that tries to explain the Capital to Asset Ratio (CAP) for life insurers in terms of various variables of interest. The latter include return on capital, total assets, and two measures of risk: asset risk and product risk, etc. A balanced panel dataset was extracted from the given unbalanced input dataset containing missing entries. In addition, a selected few of the explanatory variables were chosen from a large group present in the input dataset based on previous work on relations among asset risk, product risk and capital in the life insurance industry by Etti G. Baranoff and Thomas W. Sager (2002). Fixed Effects model was chosen based on the assumption that the firm-specific effects were correlated to the explanatory variables. Differencing method was employed so that OLS estimator could safely be used for the coefficients in the regression model. Based on the proposed model, it is found that Capital to Asset Ratio has positive relationships with product risk and return on capital, with the corporate form of organization, and with membership in an affiliated group of companies. On the other hand, it has a negative relationship with company’s size and the ratio of life premiums or annuity premiums to the total premiums generated.