Estimation of Parameters in Random Effect Models with Incidence Matrix Uncertainty

Random effect models have been widely applied in many fields of research. However, models with uncertain design matrices for random effects have been little investigated before. In some applications with such problems, an expectation method has been used for simplicity. This method does not include the extra information of uncertainty in the design matrix is not included. The closed solution for this problem is generally difficult to attain. We therefore propose an two-step algorithm for estimating the parameters, especially the variance components in the model. The implementation is based on Monte Carlo approximation and a Newton-Raphson-based EM algorithm. As an example, a simulated genetics dataset was analyzed. The results showed that the proportion of the total variance explained by the random effects was accurately estimated, which was highly underestimated by the expectation method. By introducing heuristic search and optimization methods, the algorithm can possibly be developed to infer the 'model-based' best design matrix and the corresponding best estimates.

Feasible estimation of generalized linear mixed models (GLMM) with weak dependency between groups

This paper presents a two-step pseudo likelihood estimation technique for generalized linear mixed models with the random effects being correlated between groups. The core idea is to deal with the intractable integrals in the likelihood function by multivariate Taylor's approximation. The accuracy of the estimation technique is assessed in a Monte-Carlo study. An application of it with a binary response variable is presented using a real data set on credit defaults from two Swedish banks. Thanks to the use of two-step estimation technique, the proposed algorithm outperforms conventional pseudo likelihood algorithms in terms of computational time.

A Microdata Analysis Approach to Transport Infrastructure Maintenance

Maintenance of transport infrastructure assets is widely advocated as the key in minimizing current and future costs of the transportation network. While effective maintenance decisions are often a result of engineering skills and practical knowledge, efficient decisions must also account for the net result over an asset's life-cycle. One essential aspect in the long term perspective of transport infrastructure maintenance is to proactively estimate maintenance needs. In dealing with immediate maintenance actions, support tools that can prioritize potential maintenance candidates are important to obtain an efficient maintenance strategy. This dissertation consists of five individual research papers presenting a microdata analysis approach to transport infrastructure maintenance. Microdata analysis is a multidisciplinary field in which large quantities of data is collected, analyzed, and interpreted to improve decision-making. Increased access to transport infrastructure data enables a deeper understanding of causal effects and a possibility to make predictions of future outcomes. The microdata analysis approach covers the complete process from data collection to actual decisions and is therefore well suited for the task of improving efficiency in transport infrastructure maintenance. Statistical modeling was the selected analysis method in this dissertation and provided solutions to the different problems presented in each of the five papers. In Paper I, a time-to-event model was used to estimate remaining road pavement lifetimes in Sweden. In Paper II, an extension of the model in Paper I assessed the impact of latent variables on road lifetimes; displaying the sections in a road network that are weaker due to e.g. subsoil conditions or undetected heavy traffic. The study in Paper III incorporated a probabilistic parametric distribution as a representation of road lifetimes into an equation for the marginal cost of road wear. Differentiated road wear marginal costs for heavy and light vehicles are an important information basis for decisions regarding vehicle miles traveled (VMT) taxation policies. In Paper IV, a distribution based clustering method was used to distinguish between road segments that are deteriorating and road segments that have a stationary road condition. Within railway networks, temporary speed restrictions are often imposed because of maintenance and must be addressed in order to keep punctuality. The study in Paper V evaluated the empirical effect on running time of speed restrictions on a Norwegian railway line using a generalized linear mixed model.

Detecting Major Genes Controlling Robustness of Chicken Body Weight Using Double Generalized Linear Models

Detecting both the majors genes that control the phenotypic mean and those controlling phenotypic variance has been raised in quantitative trait loci analysis. In order to mapping both kinds of genes, we applied the idea of the classic Haley-Knott regression to double generalized linear models. We performed both kinds of quantitative trait loci detection for a Red Jungle Fowl x White Leghorn F2 intercross using double generalized linear models. It is shown that double generalized linear model is a proper and efficient approach for localizing variance-controlling genes. We compared two models with or without fixed sex effect and prefer including the sex effect in order to reduce the residual variances. We found that different genes might take effect on the body weight at different time as the chicken grows.

Equipping Simulation Model (BIOSIM)’s Actors With Multi-agent Intelligence on Cross platforms

Thesis is to Introduce an Intelligent cross platform architecture with Multi-agent system in order to equip the simulation Models with agents, having intelligent behavior, reactive and pro-active nature and rational in decision making.

Testing linear cointegration against smooth-transition cointegration

This paper studies a smooth-transition (ST) type cointegration. The proposed ST cointegration allows for regime switching structure in a cointegrated system. It nests the linear cointegration developed by Engle and Granger (1987) and the threshold cointegration studied by Balke and Fomby (1997). We develop F-type tests to examine linear cointegration against ST cointegration in ST-type cointegrating regression models with or without time trends. The null asymptotic distributions of the tests are derived with stationary transition variables in ST cointegrating regression models. And it is shown that our tests have nonstandard limiting distributions expressed in terms of standard Brownian motion when regressors are pure random walks, while have standard asymptotic distributions when regressors contain random walks with nonzero drift. Finite-sample distributions of those tests are studied by Monto Carlo simulations. The small-sample performance of the tests states that our F-type tests have a better power when the system contains ST cointegration than when the system is linearly cointegrated. An empirical example for the purchasing power parity (PPP) data (monthly US dollar, Italy lira and dollar-lira exchange rate from 1973:01 to 1989:10) is illustrated by applying the testing procedures in this paper. It is found that there is no linear cointegration in the system, but there exits the ST-type cointegration in the PPP data.

Att tillämpa återkommande mätning av kundnöjdhet i IT-projekt : En vidareutvecklad modell baserad på modellerna American Customer Satisfaction Index (ACSI) och SERVQUAL

I dagens samhälle är det allt viktigare för företag att behålla sina existerande kunder då konkurrensen blir allt hårdare. Detta medför att företag försöker vidta åtgärder för att vårda relationer med sina kunder. Detta problem är även högst relevant inom IT-branschen. Inom IT-branschen är det vanligt att arbeta agilt i IT-projekt. Vår samarbetspartner har sett ett ökat behov av att mäta servicekvalitet på ett återkommande sätt inom IT-projekt, detta för att mäta relevanta variabler som sträcker sig utanför kravspecifikationen. För att mäta framgång gällande detta arbetssätt vill man kunna mäta Nöjd Kund Index (NKI) för att kunna jämföra IT-projekt internt i företaget. Då tidigare forskning visat avsaknad av modeller innehållande både mätning av servicekvalitet samt NKI har lämplig litteratur studerats där det framkommit att modellen SERVQUAL är vedertagen för mätning av servicekvalitet och modellen American Customer Satisfaction Index (ACSI) är vedertagen för mätning av NKI. Detta har legat till grund för arbetets problemformulering och syfte. Syftet med arbetet är att skapa en vidareutvecklad modell för mätning av NKI för att jämföra IT-projekt internt samt återkommande mätning av servicekvalitet inom IT-projekt. Framtagande av denna modell har sedan skett genom forskningsstrategin Design and Creation. Intervjuer har genomförts för kravfångst till den vidareutvecklade modellen. Resultatet av denna forskningsstrategi blev sedan en vidareutvecklad modell baserad på ovan nämnda modeller med återkommande förhållningssätt för mätning av servicekvalitet inom IT-projekt och mätning av NKI för att jämföra IT-projekt internt i företaget. Den framtagna modellen har sedan verifierats genom ytterligare intervjuer med respondenter som innehar god erfarenhet från kundsidan av IT-projekt. Från dessa intervjuer kunde sedan slutsats dras att denna modell är att anse som applicerbar i empirin gällande IT-projekt.

Hglm: A package for fitting hierarchical generalized linear models

We present the hglm package for fitting hierarchical generalized linear models. It can be used for linear mixed models and generalized linear mixed models with random effects for a variety of links and a variety of distributions for both the outcomes and the random effects. Fixed effects can also be fitted in the dispersion part of the model.

The effects of attitudes and personality traits on mode choice

We hypothesise that differences in people's attitudes and personality traits lead them to attribute varying importance to environmental considerations, safety, comfort, convenience and flexibility. Differences in personality traits call be revealed not only in the individuals' choice of transport, but also in other actions of their everyday lives-such as how much they recycle, whether they take precautions or avoid dangerous pursuits. Conditioning on a set of exogenous individual characteristics, we use indicators of attitudes and personality traits to form latent variables for inclusion in an, otherwise standard, discrete mode choice model. With a sample of Swedish commuters, we find that both attitudes towards flexibility and comfort, as well as being pro-environmentally inclined, influence the individual's choice of mode. Although modal time and cost still are important, it follows that there are other ways, apart from economic incentives, to attract individuals to the, from society's perspective, desirable public modes of transport. Our results should provide useful information to policy-makers and transportation planners developing sustainable transportation systems.

Genetic heterogeneity of residual variance : estimation of variance components using double hierarchical generalized linear models

Background: The sensitivity to microenvironmental changes varies among animals and may be under genetic control. It is essential to take this element into account when aiming at breeding robust farm animals. Here, linear mixed models with genetic effects in the residual variance part of the model can be used. Such models have previously been fitted using EM and MCMC algorithms. Results: We propose the use of double hierarchical generalized linear models (DHGLM), where the squared residuals are assumed to be gamma distributed and the residual variance is fitted using a generalized linear model. The algorithm iterates between two sets of mixed model equations, one on the level of observations and one on the level of variances. The method was validated using simulations and also by re-analyzing a data set on pig litter size that was previously analyzed using a Bayesian approach. The pig litter size data contained 10,060 records from 4,149 sows. The DHGLM was implemented using the ASReml software and the algorithm converged within three minutes on a Linux server. The estimates were similar to those previously obtained using Bayesian methodology, especially the variance components in the residual variance part of the model. Conclusions: We have shown that variance components in the residual variance part of a linear mixed model can be estimated using a DHGLM approach. The method enables analyses of animal models with large numbers of observations. An important future development of the DHGLM methodology is to include the genetic correlation between the random effects in the mean and residual variance parts of the model as a parameter of the DHGLM.

Parameter estimation of Poisson generalized linear mixed models based on three different statistical principles : a simulation study

Generalized linear mixed models are flexible tools for modeling non-normal data and are useful for accommodating overdispersion in Poisson regression models with random effects. Their main difficulty resides in the parameter estimation because there is no analytic solution for the maximization of the marginal likelihood. Many methods have been proposed for this purpose and many of them are implemented in software packages. The purpose of this study is to compare the performance of three different statistical principles - marginal likelihood, extended likelihood, Bayesian analysis-via simulation studies. Real data on contact wrestling are used for illustration.

Association of soluble tumor necrosis factor receptors 1 and 2 with nephropathy, cardiovascular events, and total mortality in type 2 diabetes

AIMS/HYPOTHESIS: Soluble tumor necrosis factor receptors 1 and 2 (sTNFR1 and sTNFR2) contribute to experimental diabetic kidney disease, a condition with substantially increased cardiovascular risk when present in patients. Therefore, we aimed to explore the levels of sTNFRs, and their association with prevalent kidney disease, incident cardiovascular disease, and risk of mortality independently of baseline kidney function and microalbuminuria in a cohort of patients with type 2 diabetes. In pre-defined secondary analyses we also investigated whether the sTNFRs predict adverse outcome in the absence of diabetic kidney disease. METHODS: The CARDIPP study, a cohort study of 607 diabetes patients [mean age 61 years, 44 % women, 45 cardiovascular events (fatal/non-fatal myocardial infarction or stroke) and 44 deaths during follow-up (mean 7.6 years)] was used. RESULTS: Higher sTNFR1 and sTNFR2 were associated with higher odds of prevalent kidney disease [odd ratio (OR) per standard deviation (SD) increase 1.60, 95 % confidence interval (CI) 1.32-1.93, p < 0.001 and OR 1.54, 95 % CI 1.21-1.97, p = 0.001, respectively]. In Cox regression models adjusting for age, sex, glomerular filtration rate and urinary albumin/creatinine ratio, higher sTNFR1 and sTNFR2 predicted incident cardiovascular events [hazard ratio (HR) per SD increase, 1.66, 95 % CI 1.29-2.174, p < 0.001 and HR 1.47, 95 % CI 1.13-1.91, p = 0.004, respectively]. Results were similar in separate models with adjustments for inflammatory markers, HbA1c, or established cardiovascular risk factors, or when participants with diabetic kidney disease at baseline were excluded (p < 0.01 for all). Both sTNFRs were associated with mortality. CONCLUSIONS/INTERPRETATIONS: Higher circulating sTNFR1 and sTNFR2 are associated with diabetic kidney disease, and predicts incident cardiovascular disease and mortality independently of microalbuminuria and kidney function, even in those without kidney disease. Our findings support the clinical utility of sTNFRs as prognostic markers in type 2 diabetes.