Group sequential tests for treatment effect on survival and cumulative incidence at a fixed time point

Lifetime Data Analysis - Medical research frequently involves comparing an event time of interest between treatment groups. Rather than comparing the entire survival or cumulative incidence curves,...     

Conservatism, institutionalism, and the social control of intergroup conflict

This research investigates the state social control of intergroup conflict by assessing the sociopolitical determinants of hate crime prosecutions. Consistent with insights from the political sociology of punishment, group-threat accounts of intergroup relations and the state, and neoinstitutional theory, the findings suggest that hate crime prosecutions are fewer where political conservatism, Christian fundamentalism, and black population size are higher, although this last effect is nonlinear. Linkages between district attorneys' offices and communities, on the other hand, increase hate crime prosecutions and the likelihood of offices' creating hate crime policies. Yet these policies are sometimes decoupled from actual enforcement, and such decoupling is more likely in politically conservative districts. The results indicate that common correlates of criminal punishment have very different effects on types of state social control that are protective of minority groups, and also suggest conditions under which policy and practice become decoupled in organizational settings.     

Decomposition of urban atmospheric carbon in Sonoran Desert soils

Urban atmospheres can have high concentrations of particulate organic carbon (oC) but the rate and fate oC deposition in near-urban ecosystems are rarely quantified. We collected atmospheric particulate matter in Phoenix, AZ and applied these samples to Sonoran Desert soils in a series of laboratory incubation experiments. The addition of fine particulate matter (<2.5 μm aerodynamic diameter) increased microbial respiration in soils collected from the interspaces between desert shrubs. The increase in soil respiration was equivalent to 25% to 30% of the added oC. In contrast, we did not detect increases in respiration when coarse particulate matter (>2.5 μm aerodynamic diameter) was added to interspace soils, suggesting that coarse particulate oC is recalcitrant to microbial decomposition. Due to comparatively higher background levels of C mineralization, we rarely detected changes in microbial respiration when fine or coarse particulate oC was added to soils collected beneath shrub canopies. We measured total atmospheric C concentrations within and surrounding Phoenix and, using inferential methods, estimated rates of deposition that ranged from 0.02 to 0.58 mg C m⁻² d⁻¹ for fine particles and from 0 to 6.15 mg C m⁻² d⁻¹ for coarse particles. Results show that fine atmospheric particulate matter deposited at low rates downwind of Phoenix is a labile oC substrate for soil heterotrophs. In contrast, oC deposited at higher rates as coarse particulate matter may accumulate in soils due to slow microbial decomposition rates.     

Pseudo-likelihood inference for clustered binary data

The maximum likelihood procedure to estimate paraneters of a model has scveral attractive properties including the existence of the covariance matrix which yield asymptotic covariances: for a sample size N the asymptotics are in general of order 1/N. Here we give an asymptotic for the skewness of the distribution of the maximum likelihood estimator of a parameter; this is of order 1/ n2 and this expression is new. Applications relate to the parameters of (i) the Poisson, binomial, and normal density. (ii) the gamna density and (iii) the Beta debsity. Other application are being considered. The expression for the asymptotic skowness at one phase of the study tured out to be unusually complicated involving the asymptotic expressions for variance and bias. When these were identified a much simpler compact expression appeared which we now describe. The work is a much improved treatment of the subject described in Shenton and Bowman (Mariunm likelihood estimation in small samples, Griffin. 1977).     

Local and omnibus goodness-of-fit tests in classical measurement error models

We consider functional measurement error models, i.e. models where covariates are measured with error and yet no distributional assumptions are made about the mismeasured variable. We propose and study a score-type local test and an orthogonal series-based, omnibus goodness-of-fit test in this context, where no likelihood function is available or calculated-i.e. all the tests are proposed in the semiparametric model framework. We demonstrate that our tests have optimality properties and computational advantages that are similar to those of the classical score tests in the parametric model framework. The test procedures are applicable to several semiparametric extensions of measurement error models, including when the measurement error distribution is estimated non-parametrically as well as for generalized partially linear models. The performance of the local score-type and omnibus goodness-of-fit tests is demonstrated through simulation studies and analysis of a nutrition data set.     

Capacity Updating Rules and Rational Belief Change

Choquet expected utility substitutes capacities for subjective probabilities to explain uncertainty aversion and related phenomena. This paper studies capacities as models of belief. The notions of inner and outer acceptance context are defined. These are shown to be the natural acceptance contexts when belief expansion is described by naïve Bayesian and Dempster–Shafer updating of capacities respectively. We also show that Eichberger and Kelsey's (1999b) use of Dempster–Shafer updating as a model of belief revision may lead to violations of the AGM axioms for rational belief change.