Explaining a phenomenon often requires identification of an underlying relationship between two variables. However, it is common practice in psychological research to sample only a few values of an independent variable. Young, Cole, and Sutherland (2012) showed that this practice can impair model selection in between-subject designs. The current study expands that line of research to within-subjects designs. In two Monte Carlo simulations, model discrimination under systematic sampling of 2, 3, or 4 levels of the IV was compared with that under random uniform sampling and sampling from a Halton sequence. The number of subjects, number of observations per subject, effect size, and between-subject parameter variance in the simulated experiments were also manipulated. Random sampling out-performed the other methods in model discrimination with only small, function-specific costs to parameter estimation. Halton sampling also produced good results but was less consistent. The systematic sampling methods were generally rank-ordered by the number of levels they sampled.

Este trabalho tem como objetivo aplicar a teoria de modelos mistos ao estudo do teor de nitrogênio e carbono no solo, em diversas profundidades. Devido a grande quantidade de matéria orgânica no solo, o teor de nitrogênio e carbono apresentam alta variabilidade nas primeiras profundidades, além de apresentar um comportamento não linear. Assim, fez-se necessário utilizar a abordagem de modelos não lineares mistos a dados longitudinais. A utilização desta abordagem proporciona um modelo que permite modelar dados não lineares, com heterogeneidade de variâncias, fornecendo uma curva para cada amostra. / This paper has as an objective to apply the theory of mixed models to the content of nitrogen and carbon in the soil at various depths. Due to the large amount of organic material in the soil, the content of nitrogen and carbon present high variability in the depths of soil surface, and present a nonlinear behavior. Thus, it was necessary to use the approach of nonlinear mixed models to longitudinal data analysis. The use of this approach provides a model that allows to model nonlinear data with heterogeneity of variances by providing a curve for each sample.

Despite the growing promise of pharmaceutical research, inferior experimentation or interpretation of data can inhibit breakthrough molecules from finding their way out of research institutions and reaching patients. This thesis provides evidence that better characterization of pre-clinical and clinical data can be accomplished using non-linear mixed effect modeling (NLMEM) and more effective experiments can be conducted using optimal design (OD).  To demonstrate applicability of NLMEM and OD in pre-clinical applications, in vitro ligand binding studies were examined. NLMEMs were used to evaluate precision and accuracy of ligand binding parameter estimation from different ligand binding experiments using sequential (NLR) and simultaneous non-linear regression (SNLR). SNLR provided superior resolution of parameter estimation in both precision and accuracy compared to NLR.  OD of these ligand binding experiments for one and two binding site systems including commonly encountered experimental errors was performed.  OD was employed using D- and ED-optimality.  OD demonstrated that reducing the number of samples, measurement times, and separate ligand concentrations provides robust parameter estimation and more efficient and cost effective experimentation. To demonstrate applicability of NLMEM and OD in clinical applications, a phase advanced sleep study formed the basis of this investigation. A mixed-effect Markov-chain model based on transition probabilities as multinomial logistic functions using polysomnography data in phase advanced subjects was developed and compared the sleep architecture between this population and insomniac patients. The NLMEM was sufficiently robust for describing the data characteristics in phase advanced subjects, and in contrast to aggregated clinical endpoints, which provide an overall assessment of sleep behavior over the night, described the dynamic behavior of the sleep process. OD of a dichotomous, non-homogeneous, Markov-chain phase advanced sleep NLMEM was performed using D-optimality by computing the Fisher Information Matrix for each Markov component.  The D-optimal designs improved the precision of parameter estimates leading to more efficient designs by optimizing the doses and the number of subjects in each dose group.  This thesis provides examples how studies in drug development can be optimized using NLMEM and OD. This provides a tool than can lower the cost and increase the overall efficiency of drug development. / <p>My name should be listed as "Charles Steven Ernest II" on cover.</p>

The question of adverbs and the meaning of the present perfect across varieties of English is central to sociolinguistic variationist methodologies that have approached the study of the present perfect (Winford, 1993; Tagliamonte, 1997; van Herk, 2008, 2010; Davydova, 2010; Tagliamonte, 2013). This dissertation attempts to disentangle the effect of adverbial support from the three canonical readings of the present perfect (Resultative, Experiential and Continuative). Canadian English, an understudied variety of English, is used to situate the results seen in the Early Modern English data. Early Modern English reflects the time period in which English has acquired the full modern use of the present perfect with the three readings. In order to address both these questions and current controversies over statistical models in sociolinguistics, different statistical models are used: both the traditional Goldvarb X (Sankoff, Tagliamonte and Smith, 2005) and the newer mixed-effects logistic regression (Johnson, 2009). What is missing from the previous literature in sociolinguistics that advocates logistic mixed-effects models, and provided in this dissertation, is a clear statement of where they are inappropriate to use and their limitations. The rate of adverbial marking of the present perfect in Canadian English falls between rates reported for US and British English in previous studies. The data show in both time periods that while adverbs are highly favored in continuative contexts, they are strongly disfavored in experiential and resultative contexts. In Early Modern English, adverbial support functions statistically differently for resultatives and experientials, but that difference collapses in the Canadian English sample. Both this and the other linguistic contexts support a different analysis for each set of data with respect to adverbial independence from the meaning of the present perfect form. Finally, when the focus of the analysis is on linguistic rather than social factors, both the traditional and newer models provide similar results. Where there are differences, however, these can be accounted for by the number of tokens and different estimation techniques for each model.

Background: Stunting prevalence in children less than 5 years has remained stagnated in Peru from 1992 to 2007, with a rapid reduction thereafter. We aimed to assess the role of different predictors on stunting reduction over time and across departments, from 2000 to 2012. Methods: We used various secondary data sources to describe time trends of stunting and of possible predictors that included distal to proximal determinants. We determined a ranking of departments by annual change of stunting and of different predictors. To account for variation over time and across departments, we used an ecological hierarchical approach based on a multilevel mixed-effects regression model, considering stunting as the outcome. Our unit of analysis was one department-year. Results: Stunting followed a decreasing trend in all departments, with differing slopes. The reduction pace was higher from 2007–2008 onwards. The departments with the highest annual stunting reduction were Cusco (−2.31%), Amazonas (−1.57%), Puno (−1.54%), Huanuco (−1.52%), and Ancash (−1.44). Those with the lowest reduction were Ica (−0.67%), Ucayali (−0.64%), Tumbes (−0.45%), Lima (−0.37%), and Tacna (−0.31%). Amazon and Andean departments, with the highest baseline poverty rates and concentrating the highest rural populations, showed the highest stunting reduction. In the multilevel analysis, when accounting for confounding, social determinants seemed to be the most important factors influencing annual stunting reduction, with significant variation between departments. Conclusions: Stunting reduction may be explained by the adoption of anti-poverty policies and sustained implementation of equitable crosscutting interventions, with focus on poorest areas. Inclusion of quality indicators for reproductive, maternal, neonatal and child health interventions may enable further analyses to show the influence of these factors. After a long stagnation period, Peru reduced dramatically its national and departmental stunting prevalence, thanks to a combination of social determinants and crosscutting factors. This experience offers useful lessons to other countries trying to improve their children’s nutrition. / Revisión por pares

京都大学 / 0048 / 新制・課程博士 / 博士(人間健康科学) / 甲第21703号 / 人健博第69号 / 新制||人健||5(附属図書館) / 京都大学大学院医学研究科人間健康科学系専攻 / (主査)教授 山田 重人, 教授 古田 真里枝, 教授 万代 昌紀 / 学位規則第4条第1項該当 / Doctor of Human Health Sciences / Kyoto University / DFAM

Reduced eye fixation and deficits in emotion identification accuracy have been commonly reported in individuals with autism spectrum disorder (AS), but are not ubiquitous. There is growing evidence that emotion processing deficits may be better accounted for by comorbid alexithymia (i.e., difficulty understanding and describing one's emotional state), rather than AS symptoms per se. Another possible explanation is anxiety, which is often comorbid with AS; emotion processing difficulties, including attentional biases, have also been observed in anxiety disorders, suggesting that anxiety symptoms may also influence emotion processing within AS. The purpose of the current study was to test the role of dimensional symptoms of autism, anxious apprehension (AA), and alexithymia in mediating eye fixation across two different facial processing tasks with three adult samples: adults diagnosed with autism (AS; n = 30), adults with clinically-elevated anxiety without autism (HI-ANX; n = 29), and neurotypical adults without high anxiety (NT; n = 46). Experiment 1 involved participants completing an emotion identification task involving short video clips. Experiment 2 was a luminescence change detection task with an emotional-expression photo paired with a neutral-expression photo. Joy, anger, and fear video and photo stimuli were used. Dimensional, mixed-effects models showed that symptoms of autism, but not alexithymia, predicted lower eye fixation across two separate face processing tasks. There were no group differences or significant dimensional effects for accuracy. Anxious apprehension was negatively related to response time in Experiment 1 and positively related to eye fixation in Experiment 2. An attentional avoidance of negative emotions was observed in the NT and HI-ANX group, but not the AS group. The bias was most pronounced at lower levels of AS symptoms and higher levels of AA symptoms. The results provide some evidence for a possible anxiety-related subtype in AS, with participants endorsing high autism symptoms, but low anxious apprehension, demonstrating more classic emotion processing deficits of reduced eye fixation.

In this dissertation we propose novel Bayesian methods of analysis of patterns of neuropsychological testing. We first focus attention to situations in which the goal of the analysis is to discover risk factors of cognitive decline using longitudinal assessment of tests scores. Variable selection in the Bayesian setting is still challenging, particularly for analysis of longitudinal data. We propose a novel approach to selection of the fixed effects in mixed effect models that combines a backward selection algorithm and a metrics based on the posterior credible intervals of the model parameters. The heuristic of this approach is based on searching for those parameters that are most likely to be different from zero based on their posterior credible intervals, without requiring ad hoc approximations of model parameters or informative prior distributions. We show via a simulation study that this approach produces more parsimonious models than other popular criteria such as the Bayesian deviance information criterion. We then apply this approach to test the hypothesis that genotypes of the APOE gene have different effects on the rate of cognitive decline of participants in the Long Life Family Study. In the second part of the dissertation we shift focus on analysis of neuropsychological tests administered using emerging digital technologies. The challenge of analyzing these data is that for each study participant the test is a data stream that records time and spatial coordinates of the digitally executed test and the goal is to extract some useful and informative summary univariate variables that can be used for analysis. Toward this goal, we propose a novel application of Bayesian Hidden Markov Models to analyze digitally recorded Trail Making Tests. Applying the Hidden Markov Model enables us to perform automatic segmentation of the digital data stream and allows us to extract meaningful metrics that correlate the Trail Making Tests performance to other cognitive and physical function test scores. We show that the extracted metrics provide information in addition to the traditionally used scores. / 2023-10-06T00:00:00Z

Understanding tuberculosis transmission is vital for efforts at interrupting the spread of disease. Household contact studies that follow persons sharing a household with a TB case—so-called household contacts—and test for latent TB infection by tuberculin skin test conversion give investigators vital information about risk factors for TB transmission. In these studies, investigators often assume secondary cases are infected by the primary TB case, despite substantial evidence that infection from a source outside the home is often equally likely, especially in high-prevalence settings. Investigators may discard information on contacts who test positive at study initiation due to uncertainty of the infection source, or assume infected contacts were infected from the index case prior to study initiation. With either assumption, information on transmission dynamics is lost or incomplete, and estimates of household risk factors for transmission will be biased. This dissertation describes an approach to modeling TB transmission that accounts for community-acquired transmission in the estimation of transmission risk factors from household contact study data. The proposed model generates population-specific estimates of the probability a contact of an infectious case will be infected from a source outside the home—a vital statistic for planning effective interventions to halt disease spread—in additional to estimates of household transmission predictors. We first describe the model analytically, and then apply it to synthetic datasets under different risk scenarios. We then fit the model to data taken from three household contact studies in different locations: Brazil, India, and Uganda. Infection predictors such as contact sleeping proximity to the index case and index case disease severity are underestimated in standard models compared to the proposed method, and non-household TB infection risk increases with age stratum, reflecting longer at-risk duration for community-based exposure for older contacts. This analysis will aid public health planners in understanding how best to interrupt TB spread in disparate populations by characterizing where transmission risk is greatest and which risk factors influence household-acquired transmission. Finally, we present an open-source software package in the R environment titled upmfit for modular implementation of the Bayesian Markov Chain Monte Carlo methods used to estimate the model. / 2018-05-10T00:00:00Z

abstract: Longitudinal recursive partitioning (LRP) is a tree-based method for longitudinal data. It takes a sample of individuals that were each measured repeatedly across time, and it splits them based on a set of covariates such that individuals with similar trajectories become grouped together into nodes. LRP does this by fitting a mixed-effects model to each node every time that it becomes partitioned and extracting the deviance, which is the measure of node purity. LRP is implemented using the classification and regression tree algorithm, which suffers from a variable selection bias and does not guarantee reaching a global optimum. Additionally, fitting mixed-effects models to each potential split only to extract the deviance and discard the rest of the information is a computationally intensive procedure. Therefore, in this dissertation, I address the high computational demand, variable selection bias, and local optimum solution. I propose three approximation methods that reduce the computational demand of LRP, and at the same time, allow for a straightforward extension to recursive partitioning algorithms that do not have a variable selection bias and can reach the global optimum solution. In the three proposed approximations, a mixed-effects model is fit to the full data, and the growth curve coefficients for each individual are extracted. Then, (1) a principal component analysis is fit to the set of coefficients and the principal component score is extracted for each individual, (2) a one-factor model is fit to the coefficients and the factor score is extracted, or (3) the coefficients are summed. The three methods result in each individual having a single score that represents the growth curve trajectory. Therefore, now that the outcome is a single score for each individual, any tree-based method may be used for partitioning the data and group the individuals together. Once the individuals are assigned to their final nodes, a mixed-effects model is fit to each terminal node with the individuals belonging to it. I conduct a simulation study, where I show that the approximation methods achieve the goals proposed while maintaining a similar level of out-of-sample prediction accuracy as LRP. I then illustrate and compare the methods using an applied data. / Dissertation/Thesis / Doctoral Dissertation Psychology 2019