Jorge L. Urrutia

Analysis and Prediction of Insolvency in the Property-Liability Insurance Industry: A Comparison of Logit and Hazard Models

This article compares the performance of the logit and hazard models in predicting insolvency and detecting variables that have a statistically significant impact on the solvency of property-liability insurers. The empirical results indicate that the hazard model identifies more significant variables than the logit model and that both models have comparable forecasting accuracy. We conclude that the combined use of both models provides a more complete analysis of the insurance insolvency problem.

Volume and price relationships: Hypotheses and testing for agricultural futures

The relationship between trading volume and price variability has been examined extensively. The theoretical motivation of earlier studies such as Ying (1966), Crouch (1970), Clark (1973), Copeland (1976), Epps and Epps (1976), Westerfield (1977), Rogalski (1978), and Upton and Shannon (1979) was the demand and supply model of microeconomic theory. Some authors have investigated the price‐volume relationship with the use of data from futures markets; these include Cornell (1981), Tauchen and Pitts (1983), Rutledge (1984), Grammatikos and Saunders (1986), Garcia, Leuthold, and Zapata (1986), and Bhar and Malliaris (1996). Other researchers have studied the determinants of volume with the use of macroeconomic and financial variables other than price variWe are thankful for useful comments to David B. Mirza, Bruce D. Phelps, and Stanley Pliska. The article has also benefited from the comments and suggestions of three anonymous referees, Professor Hector Zapata and the Editor, Mark Powers. Earlier versions of the article were presented at the Futures and Options Seminar at the University of Illinois at Chicago, and at the annual meetings of the Financial Management Association, and the Midwest Finance Association. We are grateful to our research assistant Raffaella Cremonesi, and especially to Caglar Alkan for extensive computer work.

Short-term and long-term linkages among the Colombian capital market indexes

Abstract Emerging capital markets are complex and interesting. Colombias capital, although thin and small, is not the exception. A major restructuring underway makes this market more appealing to study. In effect, the three Colombian exchanges just merged into one, the “Bolsa de Colombia.” The purpose of this paper is to empirically examine the short-term and long-term linkages among the several stock indices of the former Medell inodot; n Stock Exchange, traditionally the most important equity market of Colombia. To answer relevant questions such as Do these indices behave similarly? Do they influence each other? Which is the direction of causality? How strongly do these indices respond?, etc., a methodology that includes tests of stationarity, causality, cointegration, impulse response and variance decomposition is used as well as a VEC model to a data set that covers daily prices from January 2, 1988 through August 9, 1994. The empirical findings reported might also be valid for other emerging markets around the world.

An empirical investigation among real, monetary and financial variables

Abstract This paper attempts to make an empirical contribution to the literature on the relationships among real, monetary and financial variables of the economy. Using the methodology of Grangers causality tests, our results indicate that: (i) Money Supply and SP (ii) Money Supply seems to lead the S&P 500 Index and, (iii) the S&P 500 Index seems to lead the Industrial Production Index. Our findings tend to confirm the important role played by Money Supply in the economy and the popular hypothesis that stock return fluctuations are a leading indicator of future real economic activity. However, our results also show that the causal relationships among these three economic variables are not as statistically significant as the economic and financial literature suggests.

A Comparative Economic Analysis of Tort Liability and No-Fault Compensation Systems in Automobile Insurance

Based on an analysis of annual loss ratio data by state for automobile liability insurance during 1975-1980, the economic impact of no-fault automobile insurance on the relative benefits and costs to consumers and on the predictability of relative loss costs for insurers is assessed. Several hypotheses are tested by using some regression models. The results suggest that no-fault automobile insurance tends to increase relative benefits or decrease relative costs (prices) to consumers, but in the short run it does not improve the predictability of relative loss costs for insurers. From a public policy viewpoint, these results seem to suggest that a no-fault compensation system performs more efficiently than a tort-liability system for automobile insurance consumers. I. Overview and Purpose Criticisms of the efficiency and fairness of the tort liability compensation system in automobile insurance culminated with the adoption of no-fault compensation systems in 24 states in the 1970s. No-fault automobile insurance is a first-party coverage under which each driver accepts financial responsibility for some or all losses and injuries sustained by occupants of his or her own car, pedestrians hit by his or her car, and himself or herself in exchange for partial immunity from liability for losses to third parties or other drivers and their passengers. This means that recovery of losses from automobile accidents within certain limits is available to victims without regard to fault. In contrast, under the tort liability compensation system, fault or

Variance ratio tests of random walk for foreign exchange rates

Abstract The paper presents variance ratio tests of the random walk hypothesis for foreign exchange rates. The data correspond to weekly exchange rates for four foreign currencies: British Pound, German Mark, Japanese Yen, and Swiss Franc. It is found that the series contain large permanent component and small temporary component, which suggests that exchange rates follow a random walk.

Nonlinearity and Low Deterministic Chaotic Behavior in Insurance Portfolio Stock Returns

This article presents new empirical evidence indicating a deterministic component in the portfolio return dynamics of life-health and property-liability insurance company stocks. Our research is motivated by the fact that nonlinearities are a fact of economic life for many financial applications the source of which is logically apparent, yet empirical evidence of their existence is at best weak. The primary reason attributed to the weak findings of nonlinearities reported in previous research is the use of aggregate data that can hide nonlinearities at the micro level. Insurance sector stock returns are analyzed because unique institutional characteristics indicate the possibility of identifying nonlinear dynamics. Tests based on the correlation dimension partially confirm the presence of nonlinearity. However, the more powerful Brock, Dechert, and Scheinkman (BDS) statistic strongly suggests the presence of nonlinearities in the insurance stock portfolio data. The BDS statistic applied to the standardized residuals of exponential generalized auto regressive conditional heteroskedasticity (EGARCH) models strongly rejects the null of independent and identically distributed, indicating that conditional heteroskedasticity is not responsible for the presence of the nonlinear structures in the data. In addition, tests for chaos based on locally weighted regressions indicate that insurance stock portfolio returns indicate low-complexity chaotic behavior. This is an important result since most previous research has failed to report evidence of chaotic behavior in the time series of stock returns. Important contributions of this article are the application of tests of nonlinearities and chaos to more desegregated data sets and the findings of statistically significant evidence indicating nonlinearities and low-deterministic chaotic behavior in insurance stock portfolio returns.

How big is the random walks in macroeconomic time series: Variance ratio tests

Abstract The paper applies the Lo and MacKinlay (1988) and Cochrane (1988) variance-ratio test to the data sample used by Nelson and Plosser (1982), who studies the stationarity properties of 14 macroeconomic variables. The results of our empirical tests indicate that the macroeconomic time series have significant random walk components, with the exception of unemployment, real wages, real per capita GNP and industrial production. These results generally agree with those reported earlier by Nelson and Plosser who found that 13 out of 14 macroeconomic variables followed random walk and with Cochrane who, more recently, found that GNP had a small random walk component. The contribution of this paper lies in its use of a very recent methodology to estimate the magnitude of the random walk component of certain macroeconomic time series.

Deposit Insurance Subsidies, Moral Hazard, and Bank Regulation

The model developed in the paper separates deposit insurance subsidies into two components: a premium-linked subsidy which arises from an ex-ante mispricing of the deposit insurance premium, and an asset-linked subsidy which arises from a lack of ex-post monitoring of the banks actions. The identification of these two subsidies provides important insight into the relation between deposit-insurance subsidies and bank risk. The asset-linked subsidy is higher for banks of average risk and lower for very-high and very-low risk banks. The premiumlinked subsidy behaves differently under risk-adjusted and fixed-rate premiums. The model also indicates that the implementation of a riskadjusted insurance-rate schedule alone would not be sufficient to eliminate the banks excessive risk-taking behavior. Thus, some combination of risk-sensitive deposit-insurance pricing and regulatory control is necessary to reduce the moral hazard problem.

A Poisson Model with Common Shocks for CDO Valuation

A collateralized debt obligation is a credit risk product created in tranches from a portfolio of debt instruments. To value tranches, it is critical to model multiple default correlations in order to derive the appropriate loss function. Conditional independence is the usual assumption in this regard, but it ignores meaningful correlated shocks. Models assuming conditional dependence are improvements except that the number of parameters makes model calibration very challenging. A Poisson model with common shocks for derivation of the CDO loss function assumes conditional dependence and reduces the number of model parameters by grouping firms with equal credit ratings. Implementation becomes more efficient, and such a model can correct the tranche mispricing produced by the assumption of conditional independence.