Victims of infanticide and conspecific bite wounding in a female-dominant primate: a long-term study.

The aggression animals receive from conspecifics varies between individuals across their lifetime. As poignantly evidenced by infanticide, for example, aggression can have dramatic fitness consequences. Nevertheless, we understand little about the sources of variation in received aggression, particularly in females. Using a female-dominant species renowned for aggressivity in both sexes, we tested for potential social, demographic, and genetic patterns in the frequency with which animals were wounded by conspecifics. Our study included 243 captive, ring-tailed lemurs (Lemur catta), followed from infancy to adulthood over a 35-year time span. We extracted injury, social, and life-history information from colony records and calculated neutral heterozygosity for a subset of animals, as an estimate of genetic diversity. Focusing on victims rather than aggressors, we used General Linear Models to explain bite-wound patterns at different life stages. In infancy, maternal age best predicted wounds received, as infants born to young mothers were the most frequent infanticide victims. In adulthood, sex best predicted wounds received, as males were three times more likely than females to be seriously injured. No relation emerged between wounds received and the other variables studied. Beyond the generally expected costs of adult male intrasexual aggression, we suggest possible additive costs associated with female-dominant societies - those suffered by young mothers engaged in aggressive disputes and those suffered by adult males aggressively targeted by both sexes. We propose that infanticide in lemurs may be a costly by-product of aggressively mediated, female social dominance. Accordingly, the benefits of female behavioral 'masculinization' accrued to females through priority of access to resources, may be partially offset by early costs in reproductive success. Understanding the factors that influence lifetime patterns of conspecific wounding is critical to evaluating the fitness costs associated with social living; however, these costs may vary substantially between societies.

Prediction in dynamic models with time-dependent conditional variances

This paper considers forecasting the conditional mean and variance from a single-equation dynamic model with autocorrelated disturbances following an ARMA process, and innovations with time-dependent conditional heteroskedasticity as represented by a linear GARCH process. Expressions for the minimum MSE predictor and the conditional MSE are presented. We also derive the formula for all the theoretical moments of the prediction error distribution from a general dynamic model with GARCH(1, 1) innovations. These results are then used in the construction of ex ante prediction confidence intervals by means of the Cornish-Fisher asymptotic expansion. An empirical example relating to the uncertainty of the expected depreciation of foreign exchange rates illustrates the usefulness of the results. © 1992.

Weighted and two-stage least squares estimation of semiparametric truncated regression models

This paper provides a root-n consistent, asymptotically normal weighted least squares estimator of the coefficients in a truncated regression model. The distribution of the errors is unknown and permits general forms of unknown heteroskedasticity. Also provided is an instrumental variables based two-stage least squares estimator for this model, which can be used when some regressors are endogenous, mismeasured, or otherwise correlated with the errors. A simulation study indicates that the new estimators perform well in finite samples. Our limiting distribution theory includes a new asymptotic trimming result addressing the boundary bias in first-stage density estimation without knowledge of the support boundary. © 2007 Cambridge University Press.

Bayesian Analysis of Latent Threshold Dynamic Models

We discuss a general approach to dynamic sparsity modeling in multivariate time series analysis. Time-varying parameters are linked to latent processes that are thresholded to induce zero values adaptively, providing natural mechanisms for dynamic variable inclusion/selection. We discuss Bayesian model specification, analysis and prediction in dynamic regressions, time-varying vector autoregressions, and multivariate volatility models using latent thresholding. Application to a topical macroeconomic time series problem illustrates some of the benefits of the approach in terms of statistical and economic interpretations as well as improved predictions. Supplementary materials for this article are available online. © 2013 Copyright Taylor and Francis Group, LLC.

Modeling economy-wide vs sectoral climate policies using combined aggregate-sectoral models

Economic analyses of climate change policies frequently focus on reductions of energy-related carbon dioxide emissions via market-based, economy-wide policies. The current course of environment and energy policy debate in the United States, however, suggests an alternative outcome: sector-based and/or inefficiently designed policies. This paper uses a collection of specialized, sector-based models in conjunction with a computable general equilibrium model of the economy to examine and compare these policies at an aggregate level. We examine the relative cost of different policies designed to achieve the same quantity of emission reductions. We find that excluding a limited number of sectors from an economy-wide policy does not significantly raise costs. Focusing policy solely on the electricity and transportation sectors doubles costs, however, and using non-market policies can raise cost by a factor of ten. These results are driven in part by, and are sensitive to, our modeling of pre-existing tax distortions. Copyright © 2006 by the IAEE. All rights reserved.