Suchergebnisse

This article compares three approaches to handling missing data at the state level under three distinct conditions. Using Monte Carlo simulation experiments, I compare the results from a linear model using listwise deletion (LD), Markov Chain Monte Carlo with the Gibbs sampler algorithm (MCMC), and multiple imputation by chained equations (MICE) as approaches to dealing with different severity levels of missing data: missing completely at random (MCAR), missing at random (MAR), and nonignorable missingness (NI). I compare the results from each of these approaches under each condition for missing data to the results from the fully observed dataset. I conclude that the MICE algorithm performs best under most missing data conditions, MCMC provides the most stable parameter estimates across the missing data conditions (but often produced estimates that were moderately biased), and LD performs worst under most missing data conditions. I conclude with recommendations for handling missing data in state-level analysis.

This article compares three approaches to handling missing data at the state level under three distinct conditions. Using Monte Carlo simulation experiments, I compare the results from a linear model using listwise deletion (LD), Markov Chain Monte Carlo with the Gibbs sampler algorithm (MCMC), and multiple imputation by chained equations (MICE) as approaches to dealing with different severity levels of missing data: missing completely at random (MCAR), missing at random (MAR), and nonignorable missingness (NI). I compare the results from each of these approaches under each condition for missing data to the results from the fully observed dataset. I conclude that the MICE algorithm performs best under most missing data conditions, MCMC provides the most stable parameter estimates across the missing data conditions (but often produced estimates that were moderately biased), and LD performs worst under most missing data conditions. I conclude with recommendations for handling missing data in state-level analysis. Adapted from the source document.

The need to develop a system of collecting & circulating data concerning state politics is articulated. Although data regarding state politics have become more available during the late 20th century, it is argued that methods for collocating & disseminating such data remain inadequate. Three problems that have arisen from this failure to properly categorize state politics data are identified, eg, using informal networks for gathering information may reduce the empirical quality of state politics data. Consequently, it is announced that the journal State Politics & Policy Quarterly has initiated measures to periodically inform scholars about existing state politics data, especially from sources available via the Internet. Short synopses of the content of several Web sites that have state politics data readily available are also provided. 3 References. J. W. Parker

The race for superdelegate support during the extended competition between Hillary Clinton and Barack Obama for the 2008 Democratic presidential nomination offers a unique opportunity to examine the behavior of party elites with regard to their party's rank and file. The choice and timing of superdelegates' endorsements were examined, as well as measures of superdelegate loyalty, enthusiasm, considerations of candidate viability, and strategic endorsements. Did superdelegates endorse candidates based on personal or political ties, or to settle old political scores, as much of the press coverage suggested? Did superdelegates try to hijack the nomination for a candidate other than the one preferred by party rank‐and‐file participants in primaries and caucuses? We find that, taken in the aggregate, superdelegate endorsements were based on systematic considerations about candidates' standing as measured by national opinion polling, state support for candidates, and the candidate delegate count. Furthermore, female superdelegates showed more enthusiastic support for Clinton, while elected officials who were superdelegates were more likely to support Obama.Related Articles
DeWitt, Jeff R. and Richard N. Engstrom. 2011. "." Politics & Policy 39 (): 741‐759. http://onlinelibrary.wiley.com/doi/10.1111/j.1747‐1346.2011.00311.x/abstract

Bode, Leticia, and Valerie M. Hennings. 2012. "." Politics & Policy 40 (): 221‐257. http://onlinelibrary.wiley.com/doi/10.1111/j.1747‐1346.2012.00350.x/abstract


Shafie, David M. 1998. ". Southeastern Political Review 26 (): 45‐77. http://onlinelibrary.wiley.com/doi/10.1111/j.1747‐1346.1998.tb00471.x/abstract
Related Media
Film Clips: 2008. "." . http://www.youtube.com/watch?v=CpzCBPE3j6k


. 2008 "Hillary Clinton Speech." http://www.c‐spanvideo.org/program/204090‐3
La carrera por el apoyo de los superdelegados durante la extensa competencia entre Hillary Clinton y Barack Obama por la nominación presidencial en 2008 del partido Demócrata ofrece una oportunidad única para examinar el comportamiento de la élite del partido en relación al resto de sus miembros. Se examinó la elección y coordinación de los superdelegados para expresar su apoyo, así como sus niveles de lealtad, entusiasmo, consideraciones de viabilidad del candidato, y ratificaciones estratégicas. ¿Fueron las ratificaciones de los superdelegados basadas en lazos políticos o personales? ¿Trataron los superdelegados de adueñarse de la nominación de un candidato que fuera diferente del preferido debido a su posición en el partido en las elecciones primarias y los cáucuses? Encontramos que en agregado, las ratificaciones de los superdelegados se basaron en consideraciones sistemáticas de la posición de los candidatos, medida por encuestas de opinión nacional, apoyo estatal por el candidato, y la cuenta de delegados del candidato. Además, las mujeres superdelegadas mostraron un apoyo más entusiasta por Clinton, mientras que oficiales elegidos que a su vez eran superdelegados mostraban una mayor probabilidad a apoyar a Obama.