Methods to Control for Bias in Observational Studies

Thesis (Master's)--University of Washington, 2016-06

Quantum transport and integrability of the Anderson model for a quantum dot with multiple leads

We show that an Anderson Hamiltonian describing a quantum dot connected to multiple leads is integrable. A general expression for the nonlinear conductance is obtained by combining the Bethe ansatz exact solution with Landauer-Buttiker theory. In the Kondo regime, a closed form expression is given for the matrix conductance at zero temperature and when all the leads are close to the symmetric point. A bias-induced splitting of the Kondo resonance is possible for three or more leads. Specifically, for N leads, with each at a different chemical potential, there can be N-1 Kondo peaks in the conductance.

"We do it, but they don't": Multiple categorizations and work team communication

The present study adopted an intergroup approach to information sharing and ratings of work team communication in a public hospital (N = 142) undergoing large-scale restructuring. Consistent with predictions, ratings of communication followed a double ingroup serving bias: while team members reported sending about the same levels of information to double ingroup members (same work team/same occupational group) as they did to partial ingroup members (same work team/different occupational group), they reported receiving less information from partial ingroup members than from double ingroup members and rated the communication that they received from partial ingroup members as less effective. We discuss the implication of these results for the management of information sharing and organizational communication.

Participants who left a multiple-wave cohort study had similar baseline characteristics to participants who returned

PURPOSE: Research on determinants of an individual's pattern of response, considered as a profile across time, for cohort studies with multiple waves is limited. In this prospective population-based pregnancy cohort, we investigated baseline characteristics of participants after partitioning them according to their history of response to different interview waves. METHODS: Data are from the Mater-University of Queensland Study of Pregnancy 1981 to 1983 cohort, Brisbane, Australia. Complete baseline information was collected for 7223 of 7535 eligible individuals (95.9%). Follow-up occurred at 6 months, 5 years, and 14 years. Response rates were 93.0%, 72.5%, and 71.8%. Participants were allowed to leave and reenter the study. Participants were categorized as always, intermittent, or never responders. Intermittent responders were categorized further as leavers (responded at least once before leaving the study) or returners (left the study before reentering). RESULTS: Participants who always responded were older, more educated, married, Caucasian, and nonsmokers and had higher incomes. Intermittent responders shared similar baseline characteristics. Relative risk for being an intermittent responder was located between risks for always or never responding. CONCLUSIONS: Participants who left and reentered the study had baseline characteristics similar to participants who responded at least once and then left the study.

Bias, precision and heritability of self-reported and clinically measured height in Australian twins

Many studies of quantitative and disease traits in human genetics rely upon self-reported measures. Such measures are based on questionnaires or interviews and are often cheaper and more readily available than alternatives. However, the precision and potential bias cannot usually be assessed. Here we report a detailed quantitative genetic analysis of stature. We characterise the degree of measurement error by utilising a large sample of Australian twin pairs (857 MZ, 815 DZ) with both clinical and self-reported measures of height. Self-report height measurements are shown to be more variable than clinical measures. This has led to lowered estimates of heritability in many previous studies of stature. In our twin sample the heritability estimate for clinical height exceeded 90%. Repeated measures analysis shows that 2-3 times as many self-report measures are required to recover heritability estimates similar to those obtained from clinical measures. Bivariate genetic repeated measures analysis of self-report and clinical height measures showed an additive genetic correlation > 0.98. We show that the accuracy of self-report height is upwardly biased in older individuals and in individuals of short stature. By comparing clinical and self-report measures we also showed that there was a genetic component to females systematically reporting their height incorrectly; this phenomenon appeared to not be present in males. The results from the measurement error analysis were subsequently used to assess the effects of error on the power to detect linkage in a genome scan. Moderate reduction in error (through the use of accurate clinical or multiple self-report measures) increased the effective sample size by 22%; elimination of measurement error led to increases in effective sample size of 41%.

Carrier lifetime and exciton saturation in a strain-balanced InGaAs/InAsP multiple-quantum-well

The bleaching of the n = 1 heavy-hole and light-hole exciton absorption has been studied at room temperature and zero bias in a strain-balanced InGaAs/InAsP multiple quantum well. Pump-probe spectroscopy was used to measure the decay of the light-hole absorption saturation, giving a hole lifetime of only 280 ps. As only 16 meV separates the light- and heavy-hole bands, the short escape time can be explained by thermalization between these bands followed by thermionic emission over the heavy-hole barrier. The saturation density was estimated to be 1 × 1016 cm-3; this is much lower than expected for tensile-strained wells where both heavy and light holes have large in-plane masses. © 1998 American Institute of Physics.

The multiple hierarchical legislatures in representative democracy

Multiple hierarchical models of representative democracies in which, for instance, voters elect county representatives, county representatives elect district representatives, district representatives elect state representatives and state representatives a president, reduces the number of electors a representative is answerable for, and therefore, considering each level separately, these models could come closer to direct democracy. In this paper we show that worst case policy bias increases with the number of hierarchical levels. This also means that the opportunities of a gerrymanderer increase in the number of hierarchical levels.

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.

Investigating Multiple Roles of Vocal Confidence in Persuasion

Although persuasion often occurs via oral communication, it remains a comparatively understudied area. This research tested the hypothesis that changes in three properties of voice influence perceptions of speaker confidence, which in turn differentially affects attitudes according to different underlying psychological processes that the Elaboration Likelihood Model (ELM, Petty & Cacioppo, 1984), suggests should emerge under different levels of thought. Experiment 1 was a 2 (Elaboration: high vs. low) x 2 (Vocal speed: increased speed vs. decreased speed) x 2 (Vocal intonation: falling intonation vs. rising intonation) between participants factorial design. Vocal speed and vocal intonation influenced perceptions of speaker confidence as predicted. In line with the ELM, under high elaboration, confidence biased thought favorability, which in turn influenced attitudes. Under low elaboration, confidence did not bias thoughts but rather directly influenced attitudes as a peripheral cue. Experiment 2 used a similar design as Experiment 1 but focused on vocal pitch. Results confirmed pitch influenced perceptions of confidence as predicted. Importantly, we also replicated the bias and cue processes found in Experiment 1. Experiment 3 investigated the process by which a broader spectrum of speech rate influenced persuasion under moderate elaboration. In a 2 (Argument quality: strong vs. weak) x 4 (Vocal speed: extremely slow vs. moderately slow vs. moderately fast vs. extremely fast) between participants factorial design, results confirmed the hypothesized non-linear relationship between speech rate and perceptions of confidence. In line with the ELM, speech rate influenced persuasion based on the amount of processing. Experiment 4 investigated the effects of a broader spectrum of vocal intonation on persuasion under moderate elaboration and used a similar design as Experiment 3. Results indicated a partial success of our vocal intonation manipulation. No evidence was found to support the hypothesized mechanism. These studies show that changes in several different properties of voice can influence the extent to which others perceive them as confident. Importantly, evidence suggests different vocal properties influence persuasion by the same bias and cue processes under high and low thought. Evidence also suggests that under moderate thought, speech rate influences persuasion based on the amount of processing.

Investigating bias in recreational fishing surveys: Fishers listed in public telephone directories fish similarly to their unlisted counterparts

Several recent offsite recreational fishing surveys have used public landline telephone directories as a sampling frame. Sampling biases inherent in this method are recognised, but are assumed to be corrected through demographic data expansion. However, the rising prevalence of mobile-only households has potentially increased these biases by skewing raw samples towards households that maintain relatively high levels of coverage in telephone directories. For biases to be corrected through demographic expansion, both the fishing participation rate and fishing activity must be similar among listed and unlisted fishers within each demographic group. In this study, we tested for a difference in the fishing activity of listed and unlisted fishers within demographic groups by comparing their avidity (number of fishing trips per year), as well as the platform used (boat or shore) and species targeted on their most recent fishing trip. 3062 recreational fishers were interviewed at 34 tackle stores across 12 residential regions of Queensland, Australia. For each fisher, data collected included their fishing avidity, the platform used and species targeted on their most recent trip, their gender, age, residential region, and whether their household had a listed telephone number. Although the most avid fishers were younger and less likely to have a listed phone number, cumulative link models revealed that avidity was not affected by an interaction of phone listing status, age group and residential region (p > 0.05). Likewise, binomial generalized linear models revealed that there was no interaction between phone listing, age group and avidity acting on platform (p > 0.05), and platform was not affected by an interaction of phone listing status, age group, and residential region (p > 0.05). Ordination of target species using Bray-Curtis dissimilarity indices found a significant but irrelevant difference (i.e. small effect size) between listed and unlisted fishers (ANOSIM R < 0.05, p < 0.05). These results suggest that, at this time, the fishing activity of listed and unlisted fishers in Queensland is similar within demographic groups. Future research seeking to validate the assumptions of recreational fishing telephone surveys should investigate fishing participation rates of listed and unlisted fishers within demographic groups.

Correcting for bias when estimating the cost of hospital-acquired infection : an analysis of lower respiratory tract infections in non-surgical patients

Hospital acquired infections (HAI) are costly but many are avoidable. Evaluating prevention programmes requires data on their costs and benefits. Estimating the actual costs of HAI (a measure of the cost savings due to prevention) is difficult as HAI changes cost by extending patient length of stay, yet, length of stay is a major risk factor for HAI. This endogeneity bias can confound attempts to measure accurately the cost of HAI. We propose a two-stage instrumental variables estimation strategy that explicitly controls for the endogeneity between risk of HAI and length of stay. We find that a 10% reduction in ex ante risk of HAI results in an expected savings of £693 ($US 984).