In a generalized linear mixed model (GLMM), the random effects are typically uncorrelated and assumed to follow a normal distribution. However, findings from recent studies on how the misspecification of the random effects distribution affects the estimated model parameters are inconclusive. In the thesis, we extend the randomization approach for deriving linear models to the GLMM framework. Based on this approach, we develop an algorithm for estimating the model parameters of the randomization-based GLMM (RBGLMM) for the completely randomized design (CRD) which does not require normally distributed random effects. Instead, the discrete uniform distribution on the symmetric group of permutations is used for the random effects. Our simulation results suggest that the randomization-based algorithm may be an alternative when the assumption of normality is violated. In the second part of the thesis, we consider an RB-GLMM for the randomized complete block design (RCBD) with random block effects. We investigate the effect of misspecification of the correlation structure and of the random effects distribution via simulation studies. In the simulation, we use the variance covariance matrices derived from the randomization approach. The misspecified model with uncorrelated random effects is fitted to data generated from the model with correlated random effects. We also fit the model with normally distributed random effects to data simulated from models with different random effects distributions. The simulation results show that misspecification of both the correlation structure and of the random effects distribution has hardly any effect on the estimates of the fixed effects parameters. However, the estimated variance components are frequently severely biased and standard errors of these estimates are substantially higher.

Displays are ubiquitous throughout the animal kingdom. While many have been thoroughly documented, the factors affecting the expression of such displays are still not fully understood. We tested the hypotheses that display production would be affected by ecological context (i.e. the identity of the receiver) and intrinsic qualities of the signaler (i.e. heavyweight and lightweight size class) in the green anole lizard, Anolis carolinensis. Our results supported these predictions and show that a) ecological context, specifically displaying to conspecifics, has the greatest impact on display production; b) size class influenced display rate with heavyweight males displaying more to green females and lightweight males displaying more to green males in similar frequency between the two size classes to their respective target stimuli. Furthermore, our results provide empirical support for differential use of the three major display types (A, B and C displays), and uncover unexpected complexity in green anole display production.

Doctor of Philosophy / Department of Statistics / Gary L. Gadbury / Studies commonly focus on estimating a mean treatment effect in a population. However, in some applications the variability of treatment effects across individual units may help to characterize the overall effect of a treatment across the population. Consider a set of treatments, {T,C}, where T denotes some treatment that might be applied to an experimental unit and C denotes a control. For each of N experimental units, the duplet {r[subscript]i, r[subscript]Ci}, i=1,2,…,N, represents the potential response of the i[superscript]th experimental unit if treatment were applied and the response of the experimental unit if control were applied, respectively. The causal effect of T compared to C is the difference between the two potential responses, r[subscript]Ti- r[subscript]Ci. Much work has been done to elucidate the statistical properties of a causal effect, given a set of particular assumptions. Gadbury and others have reported on this for some simple designs and primarily focused on finite population randomization based inference. When designs become more complicated, the randomization based approach becomes increasingly difficult. Since linear mixed effects models are particularly useful for modeling data from complex designs, their role in modeling treatment heterogeneity is investigated. It is shown that an individual treatment effect can be conceptualized as a linear combination of fixed treatment effects and random effects. The random effects are assumed to have variance components specified in a mixed effects “potential outcomes” model when both potential outcomes, r[subscript]T,r[subscript]C, are variables in the model. The variance of the individual causal effect is used to quantify treatment heterogeneity. Post treatment assignment, however, only one of the two potential outcomes is observable for a unit. It is then shown that the variance component for treatment heterogeneity becomes non-estimable in an analysis of observed data. Furthermore, estimable variance components in the observed data model are demonstrated to arise from linear combinations of the non-estimable variance components in the potential outcomes model. Mixed effects models are considered in context of a particular design in an effort to illuminate the loss of information incurred when moving from a potential outcomes framework to an observed data analysis.

Master of Science / Department of Statistics / Leigh Murray / This case study was motivated by the need for effective statistical analysis for a series of poultry feeding experiments conducted in 2006 by Kansas State University researchers in the department of Animal Science. Some of these experiments involved an automated auger feed line system commonly used in commercial broiler houses and continuous, proportion response data. Two of the feed line experiments are considered in this case study to determine if a statistical model using a non-normal response offers a better fit for this data than a model utilizing a normal approximation. The two experiments involve fixed as well as multiple random effects. In this case study, the data from these experiments is analyzed using a linear mixed model and Generalized Linear Mixed Models (GLMM’s) with the SAS Glimmix procedure. Comparisons are made between a linear mixed model and GLMM’s using the beta and binomial responses. Since the response data is not count data a quasi-binomial approximation to the binomial is used to convert continuous proportions to the ratio of successes over total number of trials, N, for a variety of possible N values. Results from these analyses are compared on the basis of point estimates, confidence intervals and confidence interval widths, as well as p-values for tests of fixed effects. The investigation concludes that a GLMM may offer a better fit than models using a normal approximation for this data when sample sizes are small or response values are close to zero. This investigation discovers that these same instances can cause GLMM’s utilizing the beta response to behave poorly in the Glimmix procedure because lack of convergence issues prevent the obtainment of valid results. In such a case, a GLMM using a quasi-binomial response distribution with a high value of N can offer a reasonable and well behaved alternative to the beta distribution.

The increased online presence and use of technology by today’s adolescents has created new places where bullying can occur. The aim of this thesis is to specify a prediction model that can accurately predict the risk of cyberbullying victimization. The data used is from a survey conducted at five secondary schools in Pereira, Colombia. A logistic regression model with random effects is used to predict cyberbullying exposure. Predictors are selected by lasso, tuned by cross-validation. Covariates included in the study includes demographic variables, dietary habit variables, parental mediation variables, school performance variables, physical health variables, mental health variables and health risk variables such as alcohol and drug consumption. Included variables in the final model are demographic variables, mental health variables and parental mediation variables. Variables excluded in the final model includes dietary habit variables, school performance variables, physical health variables and health risk variables. The final model has an overall prediction accuracy of 88%.

Signal Detection Theory (SDT; Green & Swets, 1966) is a well-established technique to analyze accuracy data in a number of experimental paradigms in psychology, most notably memory and perception, by separating a response bias/criterion from the theoretically bias-free discriminability/sensitivity. As SDT has traditionally been applied, the researcher may be confronted with loss in statistical power and erroneous inferences. A generalized linear mixed-effects modeling (GLMM) approach is presented and advantages with regard to power and precision are demonstrated with an example analysis. Using this approach, a correlation of response bias and sensitivity was detected in the dataset, especially prevalent at the item level, though a correlation between these measures is usually not found to be reported in the memory literature. Directions for future extensions of the method as well as a brief discussion of the correlation between response bias and sensitivity are enclosed. / Graduate / 2019-03-22

We propose to extend the use of penalized likelihood based variable selection methods to hierarchical generalized linear models (HGLMs) for jointly modellingboth the mean and variance structures. We are interested in applying these newmethods on multilevel structured data, hence we assume a two-level hierarchical structure, with subjects nested within groups. We consider a generalized linearmixed model (GLMM) for the mean, with a structured dispersion in the formof a generalized linear model (GLM). In the first instance, we model the varianceof the random effects which are present in the mean model, or in otherwords the variation between groups (between-level variation). In the second scenario,we model the dispersion parameter associated with the conditional varianceof the response, which could also be thought of as the variation betweensubjects (within-level variation). To do variable selection, we use the smoothlyclipped absolute deviation (SCAD) penalty, a penalized likelihood variable selectionmethod, which shrinks the coefficients of redundant variables to 0 and at thesame time estimates the coefficients of the remaining important covariates. Ourmethods are likelihood based and so in order to estimate the fixed effects in ourmodels, we apply iterative procedures such as the Newton-Raphson method, inthe form of the LQA algorithm proposed by Fan and Li (2001). We carry out simulationstudies for both the joint models for the mean and variance of the randomeffects, as well as the joint models for the mean and dispersion of the response,to assess the performance of our new procedures against a similar process whichexcludes variable selection. The results show that our method increases both theaccuracy and efficiency of the resulting penalized MLEs and has 100% successrate in identifying the zero and non-zero components over 100 simulations. Forthe main real data analysis, we use the Health Survey for England (HSE) 2004dataset. We investigate how obesity is linked to several factors such as smoking,drinking, exercise, long-standing illness, to name a few. We also discover whetherthere is variation in obesity between individuals and between households of individuals,as well as test whether that variation depends on some of the factorsaffecting obesity itself.

No description available.

The factors affecting tree establishment in boreal forests after fire will help determine the community composition of the regenerating forest. These may have large consequences on the community dynamics for years after the fire disturbance. Factors such as burn severity and soil moisture among others have been shown to play a key role in influencing several facets of establishment. However, tree establishment after megafire in boreal forest in Europe has not yet been fully understood. Here I capitalise on a megafire in Sweden in 2014 to investigate the relative impact of different abiotic factors and preconditions on tree establishment six years after the fire. This study used a systematic survey of tree saplings (height >30cm) at 625 locations inside the nature reserve set up within the burnt area. Tested factors were: The number of dead trees lying down, slope and slope aspect, elevation, soil wetness, pre-fire standing volume, distance to fire perimeter, forest stand age, stand productivity index, previous stand dominant tree species, humus thickness after fire and depth of burn. Generalized Linear Mixed Models (GLMMs) were used to estimate the effect of these factors on specific tree species abundance. Strong influences from previous wood volume, soil wetness, elevation, and dead wood lying down had an effective influence on sapling abundance but were typically species-specific. Only elevation and wood volume had a consistent effect on all species’ abundances. Habitat context was important on a landscape scale. These results support the pattern of increasing boreal deciduousness caused by high burn severity and shorter disturbance intervals, in turn, caused by hotter, drier weather, which will have implications on the composition of boreal forests of tomorrow.

No description available.