Discrete time modelling of disease incidence time series by using Markov chain Monte Carlo methods

Summary.  A stochastic discrete time version of the susceptible–infected–recovered model for infectious diseases is developed. Disease is transmitted within and between communities when infected and susceptible individuals interact. Markov chain Monte Carlo methods are used to make inference about these unobserved populations and the unknown parameters of interest. The algorithm is designed specifically for modelling time series of reported measles cases although it can be adapted for other infectious diseases with permanent immunity. The application to observed measles incidence series motivates extensions to incorporate age structure as well as spatial epidemic coupling between communities.     

The Implicit Curriculum: Student Engagement and the Role of Social Media

This article presents results from an exploratory study conducted as a component of an assessment of the implicit curriculum in one master’s-level social work program. Web-based surveys were used to collect data from 80 graduate social work students in online and face-to-face programs. Findings indicate students who perceived social media as more useful reported higher levels of engagement and participation in program governance. The implications for social work education deal with the ability to competently use social media as a tool to increase student engagement. Students will only be exposed to elements of the implicit curriculum if they are active participants in their academic environments.     

Imputation procedures for categorical data: their effects on the goodness-of-fit chi-square statistic

An imputation procedure is a procedure by which each missing value in a data set is replaced (imputed) by an observed value using a predetermined resampling procedure. The distribution of a statistic computed from a data set consisting of observed and imputed values, called a completed data set, is affecwd by the imputation procedure used. In a Monte Carlo experiment, three imputation procedures are compared with respect to the empirical behavior of the goodness-of- fit chi-square statistic computed from a completed data set. The results show that each imputation procedure affects the distribution of the goodness-of-fit chi-square statistic in 3. different manner. However, when the empirical behavior of the goodness-of-fit chi-square statistic is compared u, its appropriate asymptotic distribution, there are no substantial differences between these imputation procedures.     

Socio-economic effects of relative income and relative cohort size

A nonlinear three-stage least-squares technique is used to estimate a four-equation model in which age-specific fertility, marriage, divorce, and female labor force participation rates are the dependent variables. In addition to a range of explanatory variables, two proxies for the Easterlin hypothesis are tested within the model, one measuring relative income and the other measuring relative cohort size. Findings indicate that the Easterlin proxies, while not statistically significant in all cases, help to explain time-series movements in various socio-economic variables in the postwar United States.     

ON THE EFFICIENCY OF THE QUASI-LIKELIHOOD ESTIMATORS FOR EXPONENTIAL FAMILIES WITH EXTRA VARIATION

Bounds are obtained for the asymptotic efficiency of the quasi-likelihood estimator relative to the likelihood estimators for exponential families with random variables in the exponent. We conclude that the quasi-likelihood is very efficient in the Poisson case for small means or small extra variation.     

Strategic voting in repeated referenda

This paper analyzes learning and voting strategy when a budget maximizing bureaucrat has several chances to obtain referendum approval. The process is modeled as a sequential game with a continuum of heterogeneous voters and a dominant bureaucrat in which all agents are uncertain about the true distribution of voter preferences. The equilibrium concept is perfect Bayes Nash, so voting is strategic in the sense of foresighted but nevertheless noncooperative.Thanks to R. Gretlein, J. Hamilton, T. Palfrey, T. Romer, H. Rosenthal, S. Slutsky and the referees of this journal for their comments and encouragement. They are not responsible for any errors or omissions.     

Content and citation analyses of public relations review

This study analyzed 161 cited and 177 uncited articles published in Public Relations Review (1975–1993) to determine if three independent variables—research methods, type of statistics, and topics—influenced whether or not articles were cited in other research articles. Significant differences were found between quantitative and qualitative research methods ( = 3.20, = .002) and topics (χ²(3,1)) = 10.47, = .01), but not by type of statistics. Topics also differed by years with professional topics the most published category and technical topics the least published. The authors provide tables listing the most cited authors, their university affiliations, and the journals citing their articles.     

EVIDENCE ON ELECTORAL ACCOUNTABILITY IN THE U.S. SENATE: ARE UNFAITHFUL AGENTS REALLY PUNISHED?

Many have questioned whether voters are able to hold incumbent officials electorally accountable through a retrospective voting strategy. We examine U.S. Senate elections from 1962 to 1990 in forty-one states, explaining which incumbents ran for reelection and their success in seeking reelection. We find that an incumbent's deviation from her state party platform decreases the probability that she will run for reelection and win if she runs. Furthermore, the electoral mechanism is found to be more efficient when voters are better informed. Finally, we find that our divergent party platform model provides a better fit than the median voter model.