A Mixed Model Approach for Geoadditive Hazard Regression

Abstract.  Mixed model based approaches for semiparametric regression have gained much interest in recent years, both in theory and application. They provide a unified and modular framework for penalized likelihood and closely related empirical Bayes inference. In this article, we develop mixed model methodology for a broad class of Cox-type hazard regression models where the usual linear predictor is generalized to a geoadditive predictor incorporating non-parametric terms for the (log-)baseline hazard rate, time-varying coefficients and non-linear effects of continuous covariates, a spatial component, and additional cluster-specific frailties. Non-linear and time-varying effects are modelled through penalized splines, while spatial components are treated as correlated random effects following either a Markov random field or a stationary Gaussian random field prior. Generalizing existing mixed model methodology, inference is derived using penalized likelihood for regression coefficients and (approximate) marginal likelihood for smoothing parameters. In a simulation we study the performance of the proposed method, in particular comparing it with its fully Bayesian counterpart using Markov chain Monte Carlo methodology, and complement the results by some asymptotic considerations. As an application, we analyse leukaemia survival data from northwest England.     

TRENDS IN TOLERANCE TOWARD RIGHTIST AND LEFTIST GROUPS, 1976-1988: EFFECTS OF ATTITUDE CHANGE AND COHORT SUCCESSION

Trends in tolerance are tested for groups on the Right and onthe Left of the political spectrum with 1976–88 GeneralSocial Survey data. Findings are that (1) tolerance increasedtoward leftist groups but not toward rightist groups; (2) succession,the replacement of older cohorts by more recent cohorts, increased tolerance toward leftists and rightists alike, partiallyon account of more recent cohorts' higher levels of education;and (3) attitude change within cohorts reduced tolerance butonly toward rightists. Overall, trends toward greater toleranceseem not to be mere reflections of reduced opposition to unpopulargroups but instead reflect changes in willingness to allow expressionof opposed ideas.     

Sidestepping Capitalism: on the Ottoman Road to Elsewhere*

Abstract Mapping productivist logic derived from the history of capitalism onto the rest of the world blocks the view of alternative systems, and their internal logic. Theories of the capitalist state can capture neither the nature of the non-capitalist states nor those states’ social and economic relations. Our alternative formulation of the Ottoman state disassociates class, property, and distribution from the sphere of production and associates them with the state. Thereby, Ottoman history sheds its petrified cloak and the Ottoman state comes to life; motion, change and class conflict are things Ottoman once again.     

THE ALLOCATIVE EFFECT OF NON-BINDING PRICE CONTROLS*

This paper shows that the imposition of non-binding price controls affects the allocation of resources. Given uncertainty the imposition of such controls will affect expectations of future prices and therefore current investment and output decisions. Non-binding ceilings (floors) will cause future market clearing prices to be higher (lower). More surprisingly they may cause a current period shortage (surplus). The effects of threatened (stochastic) price and profit controls are also examined.     

LOGROLLING IN THE U.S. CONGRESS

Does exchange, i.e., vote trading, occur in legislatures?!f so, is it quantitatively important or optimal? How important are political parties for the organization of logrolling coalitions? To address these questions, this paper investigates a broad range of votes where logrolling has been reported among interests favoring subsidies for urban, labor, and farm interests. The findings suggest that logrolling agreements are widespread, that many Democratic congressmen changed votes because of logrolling agreements, and that the Democratic party served to facilitate logrolling between its members. Furthermore, logrolling coalitions exhibited a strong degree if stability.     

DEVIATIONS FROM CONSTITUENT INTERESTS: THE ROLE OF LEGISLATIVE STRUCTURE AND POLITICAL PARTIES IN THE STATES

This paper investigates the determinants of state spending over 1960—1990. Recent empirical studies suggest that state government expenditure is greater than the electorate desires. Our main finding is that expenditure was positively related to the number of seats in a state's legislature. This is consistent with the hypothesis that logrolling leads representatives to spend more than their constituents would like. We also find that political parties do not have a pronounced effect on overall levels of expenditure, but do influence the composition of spending. In particular, Democratic control of state government is associated with higher levels of welfare spending.