Does Reweighted Least Squares (RLS) perform better in small samples than maximum likelihood (ML) for mean and covariance structure? ML statistics in covariance structure analysis are based on the asymptotic normality assumption; however, actual applications of structural equation modeling (SEM) in social and behavioral science research usually involve small samples. It has been found that chi-square tests often incorrectly over-reject the null hypothesis: Σ=Σ(θ), because when sample is small the sample covariance matrix becomes ill-conditioned and entails unstable estimates. In certain SEM models, the vector of parameter must contain both means, variances and covariances. Yet, whether RLS also works in mean and covariance structure remains unexamined. This research is an extended examination of reweighted least squares in mean and covariance structure. Specifically, we replace biased covariance matrix in traditional GLS function (Browne, 1974) with the unbiased sample covariance matrix that derives from ML estimation. Moreover, under the assumption of multivariate normality, a Monte Carlo simulation study was carried out to examine the statistical performance as compared with ML methods in different sample sizes. Based on empirical rejection frequencies and empirical averages of test statistic, this study shows that RLS performs much better than ML in mean and covariance structure models when sample sizes are small.

This dissertation examines the acquisition of partisan attitudes among Asian American immigrants in the United States. It is an empirical inquiry into the processes in which Asian American immigrants learn about American politics, adjust their attitudes, prioritize their issue concerns, and develop political conceptions of the Democratic and Republican Party. This dissertation engages theories of social and cognitive psychology by examining individual-level partisan opinion formation as mediated by political conceptualization, partisan schemas, policy preference, and psychological attachment to the parties. Evidence is drawn from a series of original in-depth interviews, surveys, and survey experiments conducted as part of the dissertation, as well as from large, publicly available national surveys.

The development of partisanship among Asian Americans is a multi-stage process. It begins with pre-migration predispositions which lay the foundation for post-migration learning. But while Asian American immigrants arrive in the United States with distinct political leanings, they tend to have weak understandings of how they relate to American political parties, candidates, ideologies, and standard political debates. Hence, they tend to be uncertain, ambivalent and inconsistent in their partisanship. As Asian Americans spend more time in the U.S., they develop increasingly sophisticated conceptions of American politics. Their growing understanding comprehends more than just the parties and the candidates; it also includes their notion of themselves as Asian Americans and how this group fits into the political system and American ethno-racial categories. At its highest level of development, their conceptualization merges personal and political identities into a profound guide to action in politics. Taken together, coherent cumulative experiences and gradual exposure to American politics lead to stronger and more sophisticated political conceptualization and greater consistency in partisan preference. In most cases this process nudges Asian Americans to identify with the Democratic Party. In certain cases, however, different life experiences, such as experience running a personal business, result in different partisan trajectories.