Whither PQL?

Generalized linear mixed models (GLMM) are generalized linear models with normally distributed random effects in the linear predictor. Penalized quasi-likelihood (PQL), an approximate method of inference in GLMMs, involves repeated fitting of linear mixed models with “working” dependent variables and iterative weights that depend on parameter estimates from the previous cycle of iteration. The generality of PQL, and its implementation in commercially available software, has encouraged the application of GLMMs in many scientific fields. Caution is needed, however, since PQL may sometimes yield badly biased estimates of variance components, especially with binary outcomes. Recent developments in numerical integration, including adaptive Gaussian quadrature, higher order Laplace expansions, stochastic integration and Markov chain Monte Carlo (MCMC) algorithms, provide attractive alternatives to PQL for approximate likelihood inference in GLMMs. Analyses of some well known datasets, and simulations based on these analyses, suggest that PQL still performs remarkably well in comparison with more elaborate procedures in many practical situations. Adaptive Gaussian quadrature is a viable alternative for nested designs where the numerical integration is limited to a small number of dimensions. Higher order Laplace approximations hold the promise of accurate inference more generally. MCMC is likely the method of choice for the most complex problems that involve high dimensional integrals.

Computational Techniques for Spatial Logistic Regression with Large Datasets

In epidemiological work, outcomes are frequently non-normal, sample sizes may be large, and effects are often small. To relate health outcomes to geographic risk factors, fast and powerful methods for fitting spatial models, particularly for non-normal data, are required. We focus on binary outcomes, with the risk surface a smooth function of space. We compare penalized likelihood models, including the penalized quasi-likelihood (PQL) approach, and Bayesian models based on fit, speed, and ease of implementation. A Bayesian model using a spectral basis representation of the spatial surface provides the best tradeoff of sensitivity and specificity in simulations, detecting real spatial features while limiting overfitting and being more efficient computationally than other Bayesian approaches. One of the contributions of this work is further development of this underused representation. The spectral basis model outperforms the penalized likelihood methods, which are prone to overfitting, but is slower to fit and not as easily implemented. Conclusions based on a real dataset of cancer cases in Taiwan are similar albeit less conclusive with respect to comparing the approaches. The success of the spectral basis with binary data and similar results with count data suggest that it may be generally useful in spatial models and more complicated hierarchical models.

Semiparametric Estimation in General Repeated Measures Problems

This paper considers a wide class of semiparametric problems with a parametric part for some covariate effects and repeated evaluations of a nonparametric function. Special cases in our approach include marginal models for longitudinal/clustered data, conditional logistic regression for matched case-control studies, multivariate measurement error models, generalized linear mixed models with a semiparametric component, and many others. We propose profile-kernel and backfitting estimation methods for these problems, derive their asymptotic distributions, and show that in likelihood problems the methods are semiparametric efficient. While generally not true, with our methods profiling and backfitting are asymptotically equivalent. We also consider pseudolikelihood methods where some nuisance parameters are estimated from a different algorithm. The proposed methods are evaluated using simulation studies and applied to the Kenya hemoglobin data.

MODELING DIFFERENTIATED TREATMENT EFFECTS FOR MULTIPLE OUTCOMES DATA

Multiple outcomes data are commonly used to characterize treatment effects in medical research, for instance, multiple symptoms to characterize potential remission of a psychiatric disorder. Often either a global, i.e. symptom-invariant, treatment effect is evaluated. Such a treatment effect may over generalize the effect across the outcomes. On the other hand individual treatment effects, varying across all outcomes, are complicated to interpret, and their estimation may lose precision relative to a global summary. An effective compromise to summarize the treatment effect may be through patterns of the treatment effects, i.e. "differentiated effects." In this paper we propose a two-category model to differentiate treatment effects into two groups. A model fitting algorithm and simulation study are presented, and several methods are developed to analyze heterogeneity presenting in the treatment effects. The method is illustrated using an analysis of schizophrenia symptom data.

PENALIZED FUNCTIONAL REGRESSION

We develop fast fitting methods for generalized functional linear models. An undersmooth of the functional predictor is obtained by projecting on a large number of smooth eigenvectors and the coefficient function is estimated using penalized spline regression. Our method can be applied to many functional data designs including functions measured with and without error, sparsely or densely sampled. The methods also extend to the case of multiple functional predictors or functional predictors with a natural multilevel structure. Our approach can be implemented using standard mixed effects software and is computationally fast. Our methodology is motivated by a diffusion tensor imaging (DTI) study. The aim of this study is to analyze differences between various cerebral white matter tract property measurements of multiple sclerosis (MS) patients and controls. While the statistical developments proposed here were motivated by the DTI study, the methodology is designed and presented in generality and is applicable to many other areas of scientific research. An online appendix provides R implementations of all simulations.

Knowledge and valuation of Andean agroforestry species: the role of sex, age, and migration among members of a rural community in Bolivia

Background Agroforestry is a sustainable land use method with a long tradition in the Bolivian Andes. A better understanding of people’s knowledge and valuation of woody species can help to adjust actor-oriented agroforestry systems. In this case study, carried out in a peasant community of the Bolivian Andes, we aimed at calculating the cultural importance of selected agroforestry species, and at analysing the intracultural variation in the cultural importance and knowledge of plants according to peasants’ sex, age, and migration. Methods Data collection was based on semi-structured interviews and freelisting exercises. Two ethnobotanical indices (Composite Salience, Cultural Importance) were used for calculating the cultural importance of plants. Intracultural variation in the cultural importance and knowledge of plants was detected by using linear and generalised linear (mixed) models. Results and discussion The culturally most important woody species were mainly trees and exotic species (e.g. Schinus molle, Prosopis laevigata, Eucalyptus globulus). We found that knowledge and valuation of plants increased with age but that they were lower for migrants; sex, by contrast, played a minor role. The age effects possibly result from decreasing ecological apparency of valuable native species, and their substitution by exotic marketable trees, loss of traditional plant uses or the use of other materials (e.g. plastic) instead of wood. Decreasing dedication to traditional farming may have led to successive abandonment of traditional tool uses, and the overall transformation of woody plant use is possibly related to diminishing medicinal knowledge. Conclusions Age and migration affect how people value woody species and what they know about their uses. For this reason, we recommend paying particular attention to the potential of native species, which could open promising perspectives especially for the young migrating peasant generation and draw their interest in agroforestry. These native species should be ecologically sound and selected on their potential to provide subsistence and promising commercial uses. In addition to offering socio-economic and environmental services, agroforestry initiatives using native trees and shrubs can play a crucial role in recovering elements of the lost ancient landscape that still forms part of local people’s collective identity.

Changes in the PQRST intervals and heart rate variability associated with rewarming in two newborns undergoing hypothermia therapy.

BACKGROUND: Little is known about the effects of hypothermia therapy and subsequent rewarming on the PQRST intervals and heart rate variability (HRV) in term newborns with hypoxic-ischemic encephalopathy (HIE). OBJECTIVES: This study describes the changes in the PQRST intervals and HRV during rewarming to normal core body temperature of 2 newborns with HIE after hypothermia therapy. METHODS: Within 6 h after birth, 2 newborns with HIE were cooled to a core body temperature of 33.5 degrees C for 72 h using a cooling blanket, followed by gradual rewarming (0.5 degrees C per hour) until the body temperature reached 36.5 degrees C. Custom instrumentation recorded the electrocardiogram from the leads used for clinical monitoring of vital signs. Generalized linear mixed models were calculated to estimate temperature-related changes in PQRST intervals and HRV. Results: For every 1 degrees C increase in body temperature, the heart rate increased by 9.2 bpm (95% CI 6.8-11.6), the QTc interval decreased by 21.6 ms (95% CI 17.3-25.9), and low and high frequency HRV decreased by 0.480 dB (95% CI 0.052-0.907) and 0.938 dB (95% CI 0.460-1.416), respectively. CONCLUSIONS: Hypothermia-induced changes in the electrocardiogram should be monitored carefully in future studies.

Genes to blood pressure: The effects of variation in genes of the renin-angiotensin system on the hormonal and renal control of blood pressure

Objective. Essential hypertension affects 25% of the US adult population and is a leading contributor to morbidity and mortality. Because BP is a multifactorial phenotype that resists simple genetic analysis, intermediate phenotypes within the complex network of BP regulatory systems may be more accessible to genetic dissection. The Renin-Angiotensin System (RAS) is known to influence intermediate and long-term blood pressure regulation through alterations in vascular tone and renal sodium and fluid resorption. This dissertation examines associations between renin (REN), angiotensinogen (AGT), angiotensin-converting enzyme (ACE) and angiotensin II type 1 receptor (AT1) gene variation and interindividual differences in plasma hormone levels, renal hemodynamics, and BP homeostasis.^ Methods. A total of 150 unrelated men and 150 unrelated women, between 20.0 and 49.9 years of age and free of acute or chronic illness except for a history of hypertension (11 men and 7 women, all off medications), were studied after one week on a controlled sodium diet. RAS plasma hormone levels, renal hemodynamics and BP were determined prior to and during angiotensin II (Ang II) infusion. Individuals were genotyped by PCR for a variable number tandem repeat (VNTR) polymorphism in REN, and for the following restriction fragment length polymorphisms (RFLP): AGT M235T, ACE I/D, and AT1 A1166C. Associations between clinical measurements and allelic variation were examined using multiple linear regression statistical models.^ Results. Women homozygous for the AT1 1166C allele demonstrated higher intracellular levels of sodium (p = 0.044). Men homozygous for the AGT T235 allele demonstrated a blunted decrement in renal plasma flow in response to Ang II infusion (p = 0.0002). There were no significant associations between RAS gene variation and interindividual variation in RAS plasma hormone levels or BP.^ Conclusions. Rather than identifying new BP controlling genes or alleles, the study paradigm employed in this thesis (i.e., measured genes, controlled environments and interventions) may provide mechanistic insight into how candidate genes affect BP homeostasis. ^

Higher emotional distress in female partners of cancer patients: prevalence and patient-partner interdependencies in a 3-year cohort

OBJECTIVE: Assessment and treatment of psychological distress in cancer patients was recognized as a major challenge. The role of spouses, caregivers, and significant others became of salient importance not only because of their supportive functions but also in respect to their own burden. The purpose of this study was to assess the amount of distress in a mixed sample of cancer patients and their partners and to explore the dyadic interdependence. METHODS: An initial sample of 154 dyads was recruited, and distress questionnaires (Hospital Anxiety and Depression Scale, Symptom Checklist 9-Item Short Version and 12-Item Short Form Health Survey) were assessed over four time points. Linear mixed models and actor-partner interdependence models were applied. RESULTS: A significant proportion of patients and their partners (up to 40%) reported high levels of anxiety, depression, psychological distress, and low quality of life over the course of the investigation. Mixed model analyses revealed that higher risks for clinical relevant anxiety and depression in couples exist for female patients and especially for female partners. Although psychological strain decreased over time, the risk for elevated distress in female partners remained. Modeling patient-partner interdependence over time stratified by patients' gender revealed specific effects: a moderate correlation between distress in patients and partners, and a transmission of distress from male patients to their female partners. CONCLUSIONS: Our findings provide empirical support for gender-specific transmission of distress in dyads coping with cancer. This should be considered as an important starting point for planning systemic psycho-oncological interventions and conceptualizing further research.

Determinants of Weight Evolution Among HIV-Positive Patients Initiating Antiretroviral Treatment in Low-Resource Settings.

BACKGROUND In resource-limited settings, clinical parameters, including body weight changes, are used to monitor clinical response. Therefore, we studied body weight changes in patients on antiretroviral treatment (ART) in different regions of the world. METHODS Data were extracted from the "International Epidemiologic Databases to Evaluate AIDS," a network of ART programmes that prospectively collects routine clinical data. Adults on ART from the Southern, East, West, and Central African and the Asia-Pacific regions were selected from the database if baseline data on body weight, gender, ART regimen, and CD4 count were available. Body weight change over the first 2 years and the probability of body weight loss in the second year were modeled using linear mixed models and logistic regression, respectively. RESULTS Data from 205,571 patients were analyzed. Mean adjusted body weight change in the first 12 months was higher in patients started on tenofovir and/or efavirenz; in patients from Central, West, and East Africa, in men, and in patients with a poorer clinical status. In the second year of ART, it was greater in patients initiated on tenofovir and/or nevirapine, and for patients not on stavudine, in women, in Southern Africa and in patients with a better clinical status at initiation. Stavudine in the initial regimen was associated with a lower mean adjusted body weight change and with weight loss in the second treatment year. CONCLUSIONS Different ART regimens have different effects on body weight change. Body weight loss after 1 year of treatment in patients on stavudine might be associated with lipoatrophy.

Effectiveness of non-steroidal anti-inflammatory drugs for the treatment of pain in knee and hip osteoarthritis: a network meta-analysis.

BACKGROUND Non-steroidal anti-inflammatory drugs (NSAIDs) are the backbone of osteoarthritis pain management. We aimed to assess the effectiveness of different preparations and doses of NSAIDs on osteoarthritis pain in a network meta-analysis. METHODS For this network meta-analysis, we considered randomised trials comparing any of the following interventions: NSAIDs, paracetamol, or placebo, for the treatment of osteoarthritis pain. We searched the Cochrane Central Register of Controlled Trials (CENTRAL) and the reference lists of relevant articles for trials published between Jan 1, 1980, and Feb 24, 2015, with at least 100 patients per group. The prespecified primary and secondary outcomes were pain and physical function, and were extracted in duplicate for up to seven timepoints after the start of treatment. We used an extension of multivariable Bayesian random effects models for mixed multiple treatment comparisons with a random effect at the level of trials. For the primary analysis, a random walk of first order was used to account for multiple follow-up outcome data within a trial. Preparations that used different total daily dose were considered separately in the analysis. To assess a potential dose-response relation, we used preparation-specific covariates assuming linearity on log relative dose. FINDINGS We identified 8973 manuscripts from our search, of which 74 randomised trials with a total of 58 556 patients were included in this analysis. 23 nodes concerning seven different NSAIDs or paracetamol with specific daily dose of administration or placebo were considered. All preparations, irrespective of dose, improved point estimates of pain symptoms when compared with placebo. For six interventions (diclofenac 150 mg/day, etoricoxib 30 mg/day, 60 mg/day, and 90 mg/day, and rofecoxib 25 mg/day and 50 mg/day), the probability that the difference to placebo is at or below a prespecified minimum clinically important effect for pain reduction (effect size [ES] -0·37) was at least 95%. Among maximally approved daily doses, diclofenac 150 mg/day (ES -0·57, 95% credibility interval [CrI] -0·69 to -0·46) and etoricoxib 60 mg/day (ES -0·58, -0·73 to -0·43) had the highest probability to be the best intervention, both with 100% probability to reach the minimum clinically important difference. Treatment effects increased as drug dose increased, but corresponding tests for a linear dose effect were significant only for celecoxib (p=0·030), diclofenac (p=0·031), and naproxen (p=0·026). We found no evidence that treatment effects varied over the duration of treatment. Model fit was good, and between-trial heterogeneity and inconsistency were low in all analyses. All trials were deemed to have a low risk of bias for blinding of patients. Effect estimates did not change in sensitivity analyses with two additional statistical models and accounting for methodological quality criteria in meta-regression analysis. INTERPRETATION On the basis of the available data, we see no role for single-agent paracetamol for the treatment of patients with osteoarthritis irrespective of dose. We provide sound evidence that diclofenac 150 mg/day is the most effective NSAID available at present, in terms of improving both pain and function. Nevertheless, in view of the safety profile of these drugs, physicians need to consider our results together with all known safety information when selecting the preparation and dose for individual patients. FUNDING Swiss National Science Foundation (grant number 405340-104762) and Arco Foundation, Switzerland.

Health outcomes, quality improvement and cost-effectiveness of the Community Diabetes Education (CoDE) program: Results of a randomized controlled trial

The objectives of this dissertation were to evaluate health outcomes, quality improvement measures, and the long-term cost-effectiveness and impact on diabetes-related microvascular and macrovascular complications of a community health worker-led culturally tailored diabetes education and management intervention provided to uninsured Mexican Americans in an urban faith-based clinic. A prospective, randomized controlled repeated measures design was employed to compare the intervention effects between: (1) an intervention group (n=90) that participated in the Community Diabetes Education (CoDE) program along with usual medical care; and (2) a wait-listed comparison group (n=90) that received only usual medical care. Changes in hemoglobin A1c (HbA1c) and secondary outcomes (lipid status, blood pressure and body mass index) were assessed using linear mixed-models and an intention-to-treat approach. The CoDE group experienced greater reduction in HbA1c (-1.6%, p<.001) than the control group (-.9%, p<.001) over the 12 month study period. After adjusting for group-by-time interaction, antidiabetic medication use at baseline, changes made to the antidiabetic regime over the study period, duration of diabetes and baseline HbA1c, a statistically significant intervention effect on HbA1c (-.7%, p=.02) was observed for CoDE participants. Process and outcome quality measures were evaluated using multiple mixed-effects logistic regression models. Assessment of quality indicators revealed that the CoDE intervention group was significantly more likely to have received a dilated retinal examination than the control group, and 53% achieved a HbA1c below 7% compared with 38% of control group subjects. Long-term cost-effectiveness and impact on diabetes-related health outcomes were estimated through simulation modeling using the rigorously validated Archimedes Model. Over a 20 year time horizon, CoDE participants were forecasted to have less proliferative diabetic retinopathy, fewer foot ulcers, and reduced numbers of foot amputations than control group subjects who received usual medical care. An incremental cost-effectiveness ratio of $355 per quality-adjusted life-year gained was estimated for CoDE intervention participants over the same time period. The results from the three areas of program evaluation: impact on short-term health outcomes, quantification of improvement in quality of diabetes care, and projection of long-term cost-effectiveness and impact on diabetes-related health outcomes provide evidence that a community health worker can be a valuable resource to reduce diabetes disparities for uninsured Mexican Americans. This evidence supports formal integration of community health workers as members of the diabetes care team.^

Fine spatial pattern of an epiphytic lichen species is affected by habitat conditions in two forest types in the Iberian Mediterranean region

Persistence and abundance of species is determined by habitat availability and the ability to disperse and colonize habitats at contrasting spatial scales. Favourable habitat fragments are also heterogeneous in quality, providing differing opportunities for establishment and affecting the population dynamics of a species. Based on these principles, we suggest that the presence and abundance of epiphytes may reflect their dispersal ability, which is primarily determined by the spatial structure of host trees, but also by host quality. To our knowledge there has been no explicit test of the importance of host tree spatial pattern for epiphytes in Mediterranean forests. We hypothesized that performance and host occupancy in a favourable habitat depend on the spatial pattern of host trees, because this pattern affects the dispersal ability of each epiphyte and it also determines the availability of suitable sites for establishment. We tested this hypothesis using new point pattern analysis tools and generalized linear mixed models to investigate the spatial distribution and performance of the epiphytic lichen Lobaria pulmonaria, which inhabits two types of host trees (beeches and Iberian oaks). We tested the effects on L. pulmonaria distribution of tree size, spatial configuration, and host tree identity. We built a model including tree size, stand structure, and several neighbourhood predictors to understand the effect of host tree on L. pulmonaria. We also investigated the relative importance of spatial patterning on the presence and abundance of the species, independently of the host tree configuration. L. pulmonaria distribution was highly dependent on habitat quality for successful establishment, i.e., tree species identity, tree diameter, and several forest stand structure surrogates. For beech trees, tree diameter was the main factor influencing presence and cover of the lichen, although larger lichen-colonized trees were located close to focal trees, i.e., young trees. However, oak diameter was not an important factor, suggesting that bark roughness at all diameters favoured lichen establishment. Our results indicate that L. pulmonaria dispersal is not spatially restricted, but it is dependent on habitat quality. Furthermore, new spatial analysis tools suggested that L. pulmonaria cover exhibits a distinct pattern, although the spatial pattern of tree position and size was random.

Fine spatial pattern of an epiphytic lichen species is affected by habitat conditions in two forest types in the Iberian Mediterranean region

Persistence and abundance of species is determined by habitat availability and the ability to disperse and colonize habitats at contrasting spatial scales. Favourable habitat fragments are also heterogeneous in quality, providing differing opportunities for establishment and affecting the population dynamics of a species. Based on these principles, we suggest that the presence and abundance of epiphytes may reflect their dispersal ability, which is primarily determined by the spatial structure of host trees, but also by host quality. To our knowledge there has been no explicit test of the importance of host tree spatial pattern for epiphytes in Mediterranean forests. We hypothesized that performance and host occupancy in a favourable habitat depend on the spatial pattern of host trees, because this pattern affects the dispersal ability of each epiphyte and it also determines the availability of suitable sites for establishment. We tested this hypothesis using new point pattern analysis tools and generalized linear mixed models to investigate the spatial distribution and performance of the epiphytic lichen Lobaria pulmonaria, which inhabits two types of host trees (beeches and Iberian oaks). We tested the effects on L. pulmonaria distribution of tree size, spatial configuration, and host tree identity. We built a model including tree size, stand structure, and several neighbourhood predictors to understand the effect of host tree on L. pulmonaria. We also investigated the relative importance of spatial patterning on the presence and abundance of the species, independently of the host tree configuration. L. pulmonaria distribution was highly dependent on habitat quality for successful establishment, i.e., tree species identity, tree diameter, and several forest stand structure surrogates. For beech trees, tree diameter was the main factor influencing presence and cover of the lichen, although larger lichen-colonized trees were located close to focal trees, i.e., young trees. However, oak diameter was not an important factor, suggesting that bark roughness at all diameters favoured lichen establishment. Our results indicate that L. pulmonaria dispersal is not spatially restricted, but it is dependent on habitat quality. Furthermore, new spatial analysis tools suggested that L. pulmonaria cover exhibits a distinct pattern, although the spatial pattern of tree position and size was random.