Andrews Farm House

On verso: Cassopolis to Pokagon, Mich. Andrews Farm House

Lapeer County courthouse

On verso: Lapeer County Courthouse. Lapeer, Michigan

Combining Information from Multiple Sources in Bayesian Modeling

Surveys can collect important data that inform policy decisions and drive social science research. Large government surveys collect information from the U.S. population on a wide range of topics, including demographics, education, employment, and lifestyle. Analysis of survey data presents unique challenges. In particular, one needs to account for missing data, for complex sampling designs, and for measurement error. Conceptually, a survey organization could spend lots of resources getting high-quality responses from a simple random sample, resulting in survey data that are easy to analyze. However, this scenario often is not realistic. To address these practical issues, survey organizations can leverage the information available from other sources of data. For example, in longitudinal studies that suffer from attrition, they can use the information from refreshment samples to correct for potential attrition bias. They can use information from known marginal distributions or survey design to improve inferences. They can use information from gold standard sources to correct for measurement error.

This thesis presents novel approaches to combining information from multiple sources that address the three problems described above.

The first method addresses nonignorable unit nonresponse and attrition in a panel survey with a refreshment sample. Panel surveys typically suffer from attrition, which can lead to biased inference when basing analysis only on cases that complete all waves of the panel. Unfortunately, the panel data alone cannot inform the extent of the bias due to attrition, so analysts must make strong and untestable assumptions about the missing data mechanism. Many panel studies also include refreshment samples, which are data collected from a random sample of new

individuals during some later wave of the panel. Refreshment samples offer information that can be utilized to correct for biases induced by nonignorable attrition while reducing reliance on strong assumptions about the attrition process. To date, these bias correction methods have not dealt with two key practical issues in panel studies: unit nonresponse in the initial wave of the panel and in the

refreshment sample itself. As we illustrate, nonignorable unit nonresponse

can significantly compromise the analyst's ability to use the refreshment samples for attrition bias correction. Thus, it is crucial for analysts to assess how sensitive their inferences---corrected for panel attrition---are to different assumptions about the nature of the unit nonresponse. We present an approach that facilitates such sensitivity analyses, both for suspected nonignorable unit nonresponse

in the initial wave and in the refreshment sample. We illustrate the approach using simulation studies and an analysis of data from the 2007-2008 Associated Press/Yahoo News election panel study.

The second method incorporates informative prior beliefs about

marginal probabilities into Bayesian latent class models for categorical data.

The basic idea is to append synthetic observations to the original data such that

(i) the empirical distributions of the desired margins match those of the prior beliefs, and (ii) the values of the remaining variables are left missing. The degree of prior uncertainty is controlled by the number of augmented records. Posterior inferences can be obtained via typical MCMC algorithms for latent class models, tailored to deal efficiently with the missing values in the concatenated data.

We illustrate the approach using a variety of simulations based on data from the American Community Survey, including an example of how augmented records can be used to fit latent class models to data from stratified samples.

The third method leverages the information from a gold standard survey to model reporting error. Survey data are subject to reporting error when respondents misunderstand the question or accidentally select the wrong response. Sometimes survey respondents knowingly select the wrong response, for example, by reporting a higher level of education than they actually have attained. We present an approach that allows an analyst to model reporting error by incorporating information from a gold standard survey. The analyst can specify various reporting error models and assess how sensitive their conclusions are to different assumptions about the reporting error process. We illustrate the approach using simulations based on data from the 1993 National Survey of College Graduates. We use the method to impute error-corrected educational attainments in the 2010 American Community Survey using the 2010 National Survey of College Graduates as the gold standard survey.

Methods for Imputing Missing Values and Synthesizing Confidential Values for Continuous and Magnitude Data

Abstract

Continuous variable is one of the major data types collected by the survey organizations. It can be incomplete such that the data collectors need to fill in the missingness. Or, it can contain sensitive information which needs protection from re-identification. One of the approaches to protect continuous microdata is to sum them up according to different cells of features. In this thesis, I represents novel methods of multiple imputation (MI) that can be applied to impute missing values and synthesize confidential values for continuous and magnitude data.

The first method is for limiting the disclosure risk of the continuous microdata whose marginal sums are fixed. The motivation for developing such a method comes from the magnitude tables of non-negative integer values in economic surveys. I present approaches based on a mixture of Poisson distributions to describe the multivariate distribution so that the marginals of the synthetic data are guaranteed to sum to the original totals. At the same time, I present methods for assessing disclosure risks in releasing such synthetic magnitude microdata. The illustration on a survey of manufacturing establishments shows that the disclosure risks are low while the information loss is acceptable.

The second method is for releasing synthetic continuous micro data by a nonstandard MI method. Traditionally, MI fits a model on the confidential values and then generates multiple synthetic datasets from this model. Its disclosure risk tends to be high, especially when the original data contain extreme values. I present a nonstandard MI approach conditioned on the protective intervals. Its basic idea is to estimate the model parameters from these intervals rather than the confidential values. The encouraging results of simple simulation studies suggest the potential of this new approach in limiting the posterior disclosure risk.

The third method is for imputing missing values in continuous and categorical variables. It is extended from a hierarchically coupled mixture model with local dependence. However, the new method separates the variables into non-focused (e.g., almost-fully-observed) and focused (e.g., missing-a-lot) ones. The sub-model structure of focused variables is more complex than that of non-focused ones. At the same time, their cluster indicators are linked together by tensor factorization and the focused continuous variables depend locally on non-focused values. The model properties suggest that moving the strongly associated non-focused variables to the side of focused ones can help to improve estimation accuracy, which is examined by several simulation studies. And this method is applied to data from the American Community Survey.

Linking the American Time Use Survey (ATUS) and the Compendium of Physical Activities : methods and rationale

Background: The 2003 Bureau of Labor Statistics American Time Use Survey (ATUS) contains 438 distinct primary activity variables that can be analyzed with regard to how time is spent by Americans. The Compendium of Physical Activities is used to code physical activities derived from various surveys, logs, diaries, etc to facilitate comparison of coded intensity levels across studies. ------ ----- Methods: This paper describes the methods, challenges, and rationale for linking Compendium estimates of physical activity intensity (METs, metabolic equivalents) with all activities reported in the 2003 ATUS. ----- ----- Results: The assigned ATUS intensity levels are not intended to compute the energy costs of physical activity in individuals. Instead, they are intended to be used to identify time spent in activities broadly classified by type and intensity. This function will complement public health surveillance systems and aid in policy and health-promotion activities. For example, at least one of the future projects of this process is the descriptive epidemiology of time spent in common physical activity intensity categories. ----- ----- Conclusions: The process of metabolic coding of the ATUS by linking it with the Compendium of Physical Activities can make important contributions to our understanding of Americans’ time spent in health-related physical activity.

The distribution and size composition of finfish, American lobster, and long-finned squid in Long Island Sound based on the Connecticut Fisheries Division Bottom Trawl Survey, 1984–1994

The distribution, abundance, and length composition of marine finfish, lobster, and squid in Long Island Sound were examined relative to season and physical features of the Sound, using Connecticut Department of Environmental Protection trawl survey data collected from 1984 to 1994. The following are presented: seasonal distribution maps for 59 species, abundance indices for 41 species, and length frequencies for 26 species. In addition, a broader view of habitat utilization in the Sound was examined by mapping aggregated catches (total catch per tow, demersal catch per tow, and pelagic catch per tow) and by comparing species richness and mean aggregate catch/tow by analysis of variance (ANOVA) among eight habitat types defined by depth interval and bottom type. For many individual species, seasonal migration patterns and preference for particular areas within Long Island Sound were evident. The aggregate distribution maps show that overall abundance was lower in the eastern Sound than the central and western portions. Demersal and pelagic temporal abundance show opposite trends—demersals were abundant in spring and declined through summer and fall, whereas pelagic abundance was low in spring and increased into fall. The analysis of habitat types revealed significant differences for both species richness and mean catch per tow. Generally, species richness was highest in habitats within the central area of the Sound and lowest in eastern habitats. The aggregate mean catch was highest in the western and central habitats, and declined eastward. (PDF file contains 199 pages.)

Estimating Sighting Proportions of American Alligator Nests during Helicopter Survey

Proportions of American alligator (Alligator mississippiensis) nests sighted during aerial survey in Florida were estimated based upon multiple surveys by different observers. We compared sighting proportions across habitats, nesting seasons, and observer experience levels. The mean sighting proportion across all habitats and years was 0.736 (SE=0.024). Survey counts corrected by the mean sighting proportion reliably predicted total nest counts (R2=0.933). Sighting proportions did not differ by habitat type (P=0.668) or year P=0.328). Experienced observers detected a greater proportion of nests (P

A comparison of two fishery-independent survey programs used to define the population structure of American lobster (Homarus americanus) in the Gulf of Maine

The population structure and abundance of the American lobster (Homarus americanus) stock in the Gulf of Maine are defined by data derived from a fishery-independent trawl survey program conducted by the National Marine Fisheries Service (NMFS). Few sampling stations in the survey area are located inshore, in particular along coastal Maine. According to statistics, however, more than two thirds of the lobster landings come from inshore waters within three miles off the coast of Maine. In order to include an inshore survey program, complementary to the NMFS survey, the Maine Department of Marine Resources (DMR) initialized an inshore survey program in 2000. The survey was modeled on the NMFS survey program, making these two survey programs comparable. Using data from both survey programs, we evaluated the population structure of the American lobster in the Gulf of Maine. Our findings indicate that lobsters in the Gulf of Maine tend to have a size-dependent inshore-off-shore distribution; smaller lobsters are more likely to stay inshore and larger lobsters are more likely to stay offshore. The DMR inshore and NMFS survey programs focused on different areas in the Gulf of Maine and likely targeted different segments of the stock. We suggest that data from both survey programs be used to assess the lobster stock and to describe the dynamics of the stock in the Gulf of Maine.

Latin American migration in the central area of Iquique: New fronts of residential location and unequal forms of access to housing

Historically the central area of the city of Iquique has been established as residential space migrants choosing from different backgrounds , however since the late 2000s migration flows are diversified being mostly Latin American immigrants who live in precarious conditions , accessing tugurizados properties , deteriorated in an increasingly growing informal market. The results presented here are derived from quantitative residential location of migrants , as well as the implementation of 13 in-depth interviews . From these results emerge that Latin American migrants access to the same places where once lived internal migrants, however they inhabit a restrictive market , uneven and inadequate living conditions lease, but allows them to articulate residence and proximity to industrial networks , social and popular trade.

The avatars of housing in Latin American urban and regional research (1990-2012)

The review of the terms used as keywords in three journals (published in Mexico and Chile) and the Brazilian meetings of regional and urban research are used to analyze the trends in housing research. Their dynamics are interpreted in the light of the general changes identified for urban and regional  research, synthesized by other authors as the emergence of new research topics and agents of urban change (civil society, participation, environment, gender) and the process of globalization (in its facets  of productive restructuration, job flexibility, social exclusion) as a general framework of analysis. It is found that the central themes of research in housing relate primarily to government action in  housing. New concerns, such as citizen participation, the environment or gender are linked to these actions as normative elements to the evaluation of programs or policies, but not as autonomous fields of study of the housing.In addition to this central concern, a significant growth of academic  production and  ome indication of the internationalization of research are mentioned