Kenneth Bollen - US grants

This proposed research will construct a valuable data set of annual national indicators of political democracy across nations; and using statistical modeling methods considered 'state-of-the-art' in sociology, it will analyze the degree to which systematic bias and random 'noise' are present in the various measures, attempt to undercover the sources of systematic bias (e.g., political influence of the country, or perhaps its size) and then correct the original data for such bias. Advances toward a more adequate measurement of political democracy across very different nations that are promised by this work would benefit theoretically grounded studies of the relationship between democratization and economic and social inequality, as well as economic growth and development. The same advances would set important measurement standards and enhance the very substance of human rights determinations currently mandated as a condition of continuing or renewing both foreign aid and trade relationships. The PI is a sociologist well known both for his previous contributions to work in this area and for his statistical and methodological skills with the methods to be used.

Most recently the dissolution of the Soviet Union, but also the preceding experiments with democracy by Eastern European countries and the return to democracy in several Latin American countries have heightened international interest in democracy. Essential to advancing our knowledge of the causes and consequences of liberal democracy--the extent that a political system allows political liberties and democratic rule--as well as to policy decisions facilitating democratic initiatives is the accurate measurement of democracy. The goal of this continuation project is to advance the measurement of liberal democracy of countries. The project will complete a cross-national time series (1950-1990) data set containing indicators of liberal democracy. Measurement models to estimate the validity, source biases, and random errors in the indicators will be developed. In this veritable age of democratization, access to the data set developed in this project will permit systematic comparative time series analyses by political sociologists and political scientists of the causes and consequences of democracy on a variety of political and economic conditions. The project's findings on the measurement properties of the indicators of liberal democracy will be useful not only to the scholarly community, but also to a number of U.S. government and international agencies that are seeking ways of assessing democratic developments in countries.

GER-9554569 Calhoun The present proposal seeks to enhance the interdisciplinary training of graduate students in sociology, history, anthropology, and political science to be better able to contribute to understanding of (a) the social conditions of democracy (b) the nature of transitions to democracy and their consolidation, (c) democracy in historical perspective, and (d) cultural and ethnic issues in democratic development. The UNC Traineeship program aims specifically to overcome the unfortunately sharp divisions between three major styles of work: studies of large scale quantitative data sets; comparative quantitative and qualitative historical studies and ethnographic studies of smaller numbers of cases (including single cases set in comparative context); and social and political theory. All trainees will gain competence in all three of these major approaches to the field. The Traineeship program will be centered in a two-semester interdisciplinary course sequence required of all trainees and offered annually, and a proseminar for trainees, other interested graduate students, and faculty. All trainees will be eligible for up to four years of further financial support from UNC, contingent on satisfactory progress. Trainees will be selected by a committee composed of the Principal Investigator and faculty from the four departments. Trainees will have the option of an international field practicum in the summer after their Traineeship year. Programs are in place with the Constitutional Commission of Eritrea, the Ford Foundation and a cluster of NGOs in India, and university-based research centers in Russia and Eastern Europe, Asia, Africa and Latin America.

In exploring the sources of political democracy in developing nations, this project examines how religion indirectly promoted democracy in former British colonies. Because religious groups gained more independence from state control in British (and American) colonies, they had more power to fight for their interests in dealing with governments in the colonizing nations. For example, despite the opposition of most colonial governments, religious groups in British colonies advocated mass education in order to foster conversion. This led to high literacy rates and successful democracies in the colonized countries. To test these arguments, the project gathers data on education from missionary records, and merges the data with digitalized maps of British colonies. It also collects and codes reports from missionary committees. The findings help identify the mechanisms behind diverse colonial outcomes and contribute to literature on world systems and cultural imperialism.

...
SES-0548858
Henry Frierson
University of North Carolina at Chapel Hill

SES-0549031
Robert Schwab
University of Maryland, College Park

SES- 0548909
Steven Ullmann
University of Miami

SES-0549057
Anne Donnelly
University of Florida

SES-0548986
Orlando Taylor
Howard University

The goal of the Atlantic Coast Social, Behavioral, and Economic Sciences (AC-SBE) Alliance, consisting of Howard University, the University of Florida, the University of Maryland at College Park, the University of Miami, and the University of North Carolina at Chapel Hill, is to increase the number of under-represented minority students receiving PhD degrees in the social, behavioral, and economic (SBE) sciences and ultimately entering the professoriate. All five universities are among the nation's leaders in awarding PhDs in the SBE fields to underrepresented minority students. The plan for the AC-SBE Alliance includes elements designed to help students at each step as they move from undergraduate school into graduate programs and onto the professoriate. The consortium has four objectives: (1) Recruit and prepare undergraduates to pursue a PhD in SBE fields, (2) Assist students in the transition from undergraduate to graduate study, (3) Retain PhD students and increase degree completion rates, and (4) Prepare future SBE faculty for success. Although each of the five schools in the AC-SBE alliance has unique features, the AC-SBE Alliance will include a number of overarching activities that will involve all five universities. For one example, the Alliance will build upon Howard University's Summer Institute that prepares future faculty in the STEM disciplines to launch a parallel SBE component. Also, entering AC-SBE students will be invited to participate in a one-week course Introduction to Data Analysis for the Social Sciences at the Odum Institute for Research in the Social Sciences at the University of North Carolina at Chapel Hill. The Odum Institute will also offer a number of videoconference short courses for AC-SBE students. Efforts will be made to ensure that the students in the SBE Alliance have further opportunities to interact and network at conferences such as the NSF-supported EMERGE.

Broader Impacts. Through integrating the resources of the five AC-SBE Alliance institutions, AC-SBE will have a broad impact across a wide region of the country in the eventual production of SBE PhD recipients. Thus, AC-SBE will serve as a comprehensive project for recruiting, mentoring, and graduating URM students in SBE PhD programs, and to carry out strategies to identify and broadly support URM students who want to pursue graduate studies and academic careers. The norms of inclusiveness at the AC-SBE Alliance institutions and the relationships that have been forged will endure well past the termination of grant support to continue efforts to ensure the significant numbers of minority students pursue and receive PhD degrees and enter the professoriate.

Structural misspecifications refer to flaws in a statistical model such as omitted variables, having the erroneous number of latent variables to represent a concept, or formulating the incorrect set of relationships between variables. Structural misspecifications are understudied, particularly considering their frequency and their serious consequences for explaining, predicting, and understanding outcome variables. The project addresses four common structural misspecification problems that emerge in latent variable Structural Equation Models (SEMs) for which there have been no widely accepted solutions. These are: (1) negative sample estimates of variances, (2) sample correlation estimates with absolute values greater than or equal to one, (3) tests of dimensionality of latent variables, and (4) tests of the presence of latent variables such as random effects or method factors. The first two problems reflect either sampling fluctuations or structural misspecification. The last two problems are checks on the necessity for latent variables. Each of these problems present conditions under which the usual significance tests are not justified by classical maximum likelihood theory and significance tests. This research project examines the robustness of the usual classical significance tests for such problems and develops alternative significance tests that should be robust to these conditions in large samples. The project uses analytic results to justify the robust significance tests and employs empirical examples and Monte Carlo simulation techniques to examine the finite sample performance of the classical and the robust significance tests for a variety of correct and incorrect models. The project will lead to recommendations of the conditions under which researchers should employ classical and robust significance tests.

This project will provide researchers with diagnostic tools to assess the quality of their statistical models. For example, the project will provide the best way to test whether improper solutions such as negative error variance estimates or correlation estimates whose absolute value exceeds one are due to sample fluctuations or due to a more serious error in the model. It also will provide tests of whether two latent variables are really the same variable or whether some latent variables are really needed in a model. Due to wide proliferation of SEMs as an analytical tool in sociology, psychology, education, marketing, and other social and natural sciences, the refinements in the methodology of SEMs developed in this project will improve the quality of research and validity of the findings in those areas of science. This will lead to better understanding of social and natural processes studied by means of structural equation models. The research is supported by the Methodology, Measurement, and Statistics Program and a consortium of federal statistical agencies as part of a joint activity to support research on survey and statistical methodology.

SES-0750385
Henry Frierson
Anne Donnelly
Carolyn Tucker
University of Florida

SES-0750663
Kim Nickerson
Johnetta Davis
Robert Schwab
University of Maryland, College Park

SES-0750657
Steven Ullmann
University of Miami

SES-0549057
Anne Donnelly
University of Florida

SES-0750683
Orlando Taylor
Florence Bonner
Angela Cole
Howard University

The grant provides three years of continued support to the Atlantic Coast Social, Behavioral, and Economic Sciences (AC-SBE) Alliance. AC-SBE, comprised of Howard University, University of Florida (lead institution), University of Maryland at College Park, University of Miami, and University of North Carolina at Chapel Hill, to complete a range of activities with the goal of increasing the number of under-represented minority students receiving doctorate degrees in the social, behavioral, and economic (SBE) sciences and ultimately entering the professoriate. All five universities are currently among the nation's leaders in awarding PhDs in the SBE fields to underrepresented minority students. The AC-SBE Alliance includes elements designed to help students at each step as they move from undergraduate school into graduate programs and onto the professoriate. The Alliance will continue to: (1) recruit and prepare undergraduates to pursue a PhD in SBE fields, (2) assist students in the transition from undergraduate to graduate study, (3) retain PhD students and increase degree completion rates, and (4) prepare future SBE faculty for success. Although each of the five schools in the AC-SBE alliance has unique features, the AC-SBE Alliance includes a number of overarching or "value-added" activities that involve sharing resources across the five universities. For example, the Alliance builds upon Howard University's Summer Institute that prepares future faculty in the STEM (science, engineering and technology) fields, adding a parallel SBE component. Also, entering AC-SBE students participate in a one-week course--Introduction to Data Analysis for the Social Sciences--at the Odum Institute for Research in the Social Sciences at the University of North Carolina at Chapel Hill. The Odum Institute also offers a number of videoconference short courses to AC-SBE students.

Broader Impacts. Through integrating the resources of the five Alliance institutions, AC-SBE has the potential to realize a broad impact across a wide region of the country in the production of SBE PhD recipients. Thus, AC-SBE serves as a comprehensive project for recruiting, mentoring, and graduating underrepresented students in SBE PhD programs, and further to more broadly support students who want to pursue graduate studies and academic careers. It is anticipated that the norms of inclusiveness at the AC-SBE Alliance institutions and the relationships that have been forged will endure well past the termination of grant support to continue efforts to ensure the significant numbers of minority students pursue and receive PhD degrees and enter the professoriate.

PROJECT SUMMARY With the increasing availability of ecological momentary assessments (EMA) such as daily dairy and experience sampling measurements, behavioral scientists are better able to investigate the within-person dynamic patterns (i.e., relations among variables across time) underlying symptoms, behaviors, and life events. One prominent challenge in this endeavor is the inherent heterogeneity in individual mental health processes. Others have demonstrated that this heterogeneity requires personalized measurement models to accurately assess constructs of interest. By measurement model, we mean the pattern of how observed variables relate to a latent construct. As an example, depression can be thought of as a latent construct that psychologists often seek to measure. Individuals may differ with regards to which (observed) symptoms relate to their overall (latent) depression levels at a given time point. For one person, the symptoms of sadness, feelings of hopelessness, and irritability may be the best measures of depression over time whereas for another, perhaps sadness, anhedonia, and fatigue are the symptoms that indicate depression.Allowing individuals to have personalized assessments will enable the field to get even closer to personalized treatment plans by better quantifying these somewhat abstract constructs.The current standard is to force all individuals to have the same measurement model, but the field is quickly moving towards adopting personalized measurement models for assessments. Critically, the available methods have a number of issues that prevent reliable personalized measurement models. First, some approaches (such as simply using observed variables) ignore the reality of measurement errors. This causes bias in the effects among latent constructs of interest and can lead to inaccurate inferences regarding anindividuals' process. Second, the number of observations obtained for a given individual is often too small to arrive at person-specific measurement models. Third, the current methods require the assumption of multivariate normality to be met; this is typically not seen in many forms of ecological momentary assessment data. Fourth, many available approaches for arriving at individual- level models do not perform well when the model is misspecified (i.e., the pattern of relations among observed symptoms and latent constructs is incorrect). This prevents a considerable hurdle when attempting to arrive at model structures in an exploratory manner where by definition the correct model is unknown in the beginning.Our project, if funded, would provide researchers with an easy-to-use tool for arriving at personalized measurement models. This can be achieved by building an exploratory approach within a well- understood estimation approach that has a number of desirable properties. Measurement errors would be accounted for, the method will work well even when the number of time points (observations) is less than the number of variables, multivariate normality will not be a required assumption, and misspecifications will not influence the identification of a reliable personalized measurement model.