Search results

We study the statistical properties of Pearson correlation coefficients of Gaussian ranks, and Gaussian rank regressions – ordinary least-squares (OLS) models applied to those ranks. We show that these procedures are fully efficient when the true copula is Gaussian and the margins are non-parametrically estimated, and remain consistent for their population analogs otherwise. We compare them to Spearman and Pearson correlations and their regression counterparts theoretically and in extensive Monte Carlo simulations. Empirical applications to migration and growth across US states, the augmented Solow growth model and momentum and reversal effects in individual stock returns confirm that Gaussian rank procedures are insensitive to outliers.

Gaussian copula is by far the most popular copula used in the financial industry in default dependency modeling. However, it has a major drawback – it does not exhibit tail dependence, a very important property for copula. The essence of tail dependence is the interdependence when extreme events occur, say, defaults of corporate bonds. In this paper, we show that some tail dependence can be restored by introducing stochastic volatility on a Gaussian copula. Using perturbation methods we then derive an approximate copula – called perturbed Gaussian copula in this paper.

What copulas are, their estimation, and use is illustrated using a geographical diversification example. To accomplish this, dependencies between county-level yields are calculated for non-irrigated wheat, upland cotton, and sorghum using Pearson linear correlation and Kendall's tau. The use of Kendall's tau allows the implementation of copulas to estimate the dependency between county-level yields. The paper aims to discuss these issues.

Four parametric copulas, Gaussian, Frank, Clayton, and Gumbel, are used to estimate Kendall's tau. These four estimates of Kendall's tau are compared to Pearson's linear correlation, a more typical measure of dependence. Using this information, functions are estimated to determine the relationships between dependencies and changes in geographic and climate data.

The effect on county-level crop yields based on changes of geographical and climate variables differed among the different dependency measures among the three different crops. Implementing alternative dependency measures changed the statistical significance and the signs of the coefficients in the sorghum and cotton dependence functions. Copula-based elasticities are consistently less than the linear correlation elasticities for wheat and cotton. For sorghum, however, the copula-based elasticities are generally larger. The results indicate that one should not take the issue of measuring dependence as a trivial matter.

This research not only extends the current literature on geographical diversification by taking a more detailed examination of factors impacting yield dependence, but also extends the copula literature by comparing estimation results using linear correlation and copula-based rank correlation.

Copula modeling enables the analysis of multivariate count data that has previously required imposition of potentially undesirable correlation restrictions or has limited attention to models with only a few outcomes. This article presents a method for analyzing correlated counts that is appealing because it retains well-known marginal distributions for each response while simultaneously allowing for flexible correlations among the outcomes. The proposed framework extends the applicability of the method to settings with high-dimensional outcomes and provides an efficient simulation method to generate the correlation matrix in a single step. Another open problem that is tackled is that of model comparison. In particular, the article presents techniques for estimating marginal likelihoods and Bayes factors in copula models. The methodology is implemented in a study of the joint behavior of four categories of US technology patents. The results reveal that patent counts exhibit high levels of correlation among categories and that joint modeling is crucial for eliciting the interactions among these variables.

Revenue insurance is the most popular form of insurance available in the US federal crop insurance program. The majority of crop revenue policies are sold with a harvest price replacement feature that pays out on lost crop yields at the maximum of a realized or projected harvest price. The authors introduce a novel actuarial and statistical approach to rate revenue insurance policies with exotic price coverage: the payout depends on an order statistic or average of prices. The authors examine the price implications of different dependence models and demonstrate the feasibility of policies of this type.

Hierarchical Archimedean copulas and vine copulas are used to model dependence between prices and yields and serial dependence of prices. The authors construct several synthetic exotic price coverage insurance policies and evaluate the impact of copula models on policies covering different types of risk.

The authors’ findings show that the price of exotic price coverage policies is sensitive to the choice of dependence model. Serial dependence varies across the growing season. It is possible to accurately price exotic coverage policies and we suggest these add-ons as a possible avenue for developing private crop insurance markets.

The authors apply hierarchical Archimedean copulas and vine copulas that allow for flexibility in the modeling of multivariate dependence. Unlike previous research, which has primarily considered dependence across space, the form of exotic price coverage requires modeling serial dependence in relative prices. Results are important for this segment of the agricultural insurance market: one of the main areas that insurers can develop private products around the federal program.

The implementation of credit risk models has largely relied either on the use of historical default dependence, as proxied by the correlation of equity returns, or on risk neutral equicorrelation, as extracted from CDOs. Contrary to both approaches, the purpose of this paper is to infer risk neutral dependence from CDS data, taking counterparty risk into consideration and avoiding equicorrelation. The impact of risk neutral correlation on the fees of some higher dimensional credit derivatives is also explored.

Copula functions are used in order to capture dependency. An application to market data is provided.

Both in the FtD and CDO cases, using (the correct) risk neutral measure instead of equity dependency has the same effect as the adoption of a copula with tail dependency instead of a Gaussian one. This should be important for those who resort to copulas in credit derivative pricing.

As far as is known, several attempts have been made in order to compare the behavior of different copulas in derivative pricing; however, no attempt has been made in order to extract risk neutral dependence without using the equicorrelation assumption. Therefore no attempt has been made to understand which copula features could proxy for risk neutrality, whenever risk neutral dependency cannot be inferred (for instance because CDS involving that name are not actively traded)

Portfolio credit derivatives, such as basket credit default swaps (basket CDS), require for their pricing an estimation of the dependence structure of defaults, which is known to exhibit tail dependence as reflected in observed default contagion. A popular model with this property is the (Student's) t-copula; unfortunately there is no fast method to calibrate the degree of freedom parameter.

In this paper, within the framework of Schönbucher's copula-based trigger-variable model for basket CDS pricing, we propose instead to calibrate the full multivariate t distribution. We describe a version of the expectation-maximization algorithm that provides very fast calibration speeds compared to the current copula-based alternatives.

The algorithm generalizes easily to the more flexible skewed t distributions. To our knowledge, we are the first to use the skewed t distribution in this context.

Portfolio risk in crop insurance due to the systemic nature of crop yield losses has inhibited the development of private crop insurance markets. Government subsidy or reinsurance has therefore been used to support crop insurance programs. The purpose of this paper is to investigate the possibility of converting systemic crop yield risk into “poolable” risk. Specifically, this study examines whether it is possible to remove the co-movement as well as tail dependence of crop yield variables by enlarging the risk pool across different crops and countries.

Hierarchical Kendall copula (HKC) models are used to model potential non-linear correlations of the high-dimensional crop yield variables. A Bayesian estimation approach is applied to account for estimation risk in the copula parameters. A synthetic insurance portfolio is used to evaluate the systemic risk and diversification effect.

The results indicate that the systemic nature – both positive correlation and lower tail dependence – of crop yield risks can be eliminated by combining crop insurance policies across crops and countries.

The study applies the HKC in the context of agricultural risks. Compared to other advanced copulas, the HKC achieves both flexibility and parsimony. The flexibility of the HKC makes it appropriate to precisely represent various correlation structures of crop yield risks while the parsimony makes it computationally efficient in modeling high-dimensional correlation structure.

This paper investigates the dependence structure and market risk of the currency exchange rate portfolio from the Malaysian ringgit perspective.

The marginal return of the five major exchange rates series, i.e. United States dollar (USD), Japanese yen (JPY), Singapore dollar (SGD), Thai baht (THB) and Chinese Yuan Renminbi (CNY) are modelled by the Bayesian generalized autoregressive conditional heteroskedasticity (GARCH) (1,1) model with Student's t innovations. In addition, five different copulas, such as Gumbel, Clayton, Frank, Gaussian and Student's t, are applied for modelling the joint distribution for examining the dependence structure of the five currencies. Moreover, the portfolio risk is measured by Value at Risk (VaR) that considers the extreme events through the extreme value theory (EVT).

The finding shows that Gumbel and Student's t are the best-fitted Archimedean and elliptical copulas, for the five currencies. The dependence structure is asymmetric and heavy tailed.

The findings of this paper have important implications for diversification decision and hedging problems for investors who involving in foreign currencies. The authors found that the portfolio is diversified with the consideration of extreme events. Therefore, investors who are holding an individual currency with VaR higher than the portfolio may consider adding other currencies used in this paper for hedging.

This is the first paper estimating VaR of a currency exchange rate portfolio using a combination of Bayesian GARCH model, EVT and copula theory. Moreover, the VaR of the currency exchange rate portfolio can be used as a benchmark of the currency exchange market risk.

This study aims to use a novel methodology to investigate the performance of several multivariate value at risk (VaR) and expected shortfall (ES) models implemented to assess the risk of an equally weighted portfolio consisting of high-frequency (1-min) observations for five foreign currencies, namely, EUR/USD, GBP/USD, EUR/JPY, USD/JPY and GBP/JPY.

By applying the multiplicative component generalised autoregressive conditional heteroskedasticity (MC-GARCH) model on each return series and by modelling the dependence structure using copulas, the 95 per cent intraday portfolio VaR and ES are forecasted for an out-of-sample set using Monte Carlo simulation.

In terms of VaR forecasting performance, the backtesting results indicated that four out of the five models implemented could not be rejected at 5 per cent level of significance. However, when the models were further evaluated for their ES forecasting power, only the Student’s t and Clayton models could not be rejected. The fact that some ES models were rejected at 5 per cent significance level highlights the importance of selecting an appropriate copula model for the dependence structure.

To the best of the authors’ knowledge, this is the first study to use the MC-GARCH and copula models to forecast, for the next 1 min, the VaR and ES of an equally weighted portfolio of foreign currencies. It is also the first study to analyse the performance of the MC-GARCH model under seven distributional assumptions for the innovation term.