Multiple imputation for missing continuous and dichotomous data: The effects of patterns of missingness and variable correlations on type I error with small samples

The purpose of this study is to investigate the effects of predictor variable correlations and patterns of missingness with dichotomous and/or continuous data in small samples when missing data is multiply imputed. Missing data of predictor variables is multiply imputed under three different multivariate models: the multivariate normal model for continuous data, the multinomial model for dichotomous data and the general location model for mixed dichotomous and continuous data. Subsequent to the multiple imputation process, Type I error rates of the regression coefficients obtained with logistic regression analysis are estimated under various conditions of correlation structure, sample size, type of data and patterns of missing data. The distributional properties of average mean, variance and correlations among the predictor variables are assessed after the multiple imputation process. ^ For continuous predictor data under the multivariate normal model, Type I error rates are generally within the nominal values with samples of size n = 100. Smaller samples of size n = 50 resulted in more conservative estimates (i.e., lower than the nominal value). Correlation and variance estimates of the original data are retained after multiple imputation with less than 50% missing continuous predictor data. For dichotomous predictor data under the multinomial model, Type I error rates are generally conservative, which in part is due to the sparseness of the data. The correlation structure for the predictor variables is not well retained on multiply-imputed data from small samples with more than 50% missing data with this model. For mixed continuous and dichotomous predictor data, the results are similar to those found under the multivariate normal model for continuous data and under the multinomial model for dichotomous data. With all data types, a fully-observed variable included with variables subject to missingness in the multiple imputation process and subsequent statistical analysis provided liberal (larger than nominal values) Type I error rates under a specific pattern of missing data. It is suggested that future studies focus on the effects of multiple imputation in multivariate settings with more realistic data characteristics and a variety of multivariate analyses, assessing both Type I error and power. ^

Validation of a Spatially Continuous EDEN Water-Surface Model for the Everglades, Florida

The Everglades Depth Estimation Network (EDEN) is an integrated network of realtime water-level monitoring, ground-elevation modeling, and water-surface modeling that provides scientists and managers with current (2000-present), online water-stage and water-depth information for the entire freshwater portion of the Greater Everglades. Continuous daily spatial interpolations of the EDEN network stage data are presented on grid with 400-square-meter spacing. EDEN offers a consistent and documented dataset that can be used by scientists and managers to: (1) guide large-scale field operations, (2) integrate hydrologic and ecological responses, and (3) support biological and ecological assessments that measure ecosystem responses to the implementation of the Comprehensive Everglades Restoration Plan (CERP) (U.S. Army Corps of Engineers, 1999). The target users are biologists and ecologists examining trophic level responses to hydrodynamic changes in the Everglades. The first objective of this report is to validate the spatially continuous EDEN water-surface model for the Everglades, Florida developed by Pearlstine et al. (2007) by using an independent field-measured data-set. The second objective is to demonstrate two applications of the EDEN water-surface model: to estimate site-specific ground elevation by using the validated EDEN water-surface model and observed water depth data; and to create water-depth hydrographs for tree islands. We found that there are no statistically significant differences between model-predicted and field-observed water-stage data in both southern Water Conservation Area (WCA) 3A and WCA 3B. Tree island elevations were derived by subtracting field water-depth measurements from the predicted EDEN water-surface. Water-depth hydrographs were then computed by subtracting tree island elevations from the EDEN water stage. Overall, the model is reliable by a root mean square error (RMSE) of 3.31 cm. By region, the RMSE is 2.49 cm and 7.77 cm in WCA 3A and 3B, respectively. This new landscape-scale hydrological model has wide applications for ongoing research and management efforts that are vital to restoration of the Florida Everglades. The accurate, high-resolution hydrological data, generated over broad spatial and temporal scales by the EDEN model, provides a previously missing key to understanding the habitat requirements and linkages among native and invasive populations, including fish, wildlife, wading birds, and plants. The EDEN model is a powerful tool that could be adapted for other ecosystem-scale restoration and management programs worldwide.

A Universal Formula for Continuous Utility

A single formula assigns a continuous utility function to every representable preference relation.

Continuous Paretian Preferences

Two forms of continuity are defined for Pareto representations of preferences. They are designated continuity and coordinate continuity. Characterizations are given of those Pareto representable preferences that are continuously representable and, in dimension two, of those that are coordinate-continuously representable.

Continuous safety screens for randomized controlled clinical trials with blinded treatment information

Standard methods for testing safety data are needed to ensure the safe conduct of clinical trials. In particular, objective rules for reliably identifying unsafe treatments need to be put into place to help protect patients from unnecessary harm. DMCs are uniquely qualified to evaluate accumulating unblinded data and make recommendations about the continuing safe conduct of a trial. However, it is the trial leadership who must make the tough ethical decision about stopping a trial, and they could benefit from objective statistical rules that help them judge the strength of evidence contained in the blinded data. We design early stopping rules for harm that act as continuous safety screens for randomized controlled clinical trials with blinded treatment information, which could be used by anyone, including trial investigators (and trial leadership). A Bayesian framework, with emphasis on the likelihood function, is used to allow for continuous monitoring without adjusting for multiple comparisons. Close collaboration between the statistician and the clinical investigators will be needed in order to design safety screens with good operating characteristics. Though the math underlying this procedure may be computationally intensive, implementation of the statistical rules will be easy and the continuous screening provided will give suitably early warning when real problems were to emerge. Trial investigators and trial leadership need these safety screens to help them to effectively monitor the ongoing safe conduct of clinical trials with blinded data.^

A novel method for evaluating an interaction effect of correlated continuous covariates in a linear model

Interaction effect is an important scientific interest for many areas of research. Common approach for investigating the interaction effect of two continuous covariates on a response variable is through a cross-product term in multiple linear regression. In epidemiological studies, the two-way analysis of variance (ANOVA) type of method has also been utilized to examine the interaction effect by replacing the continuous covariates with their discretized levels. However, the implications of model assumptions of either approach have not been examined and the statistical validation has only focused on the general method, not specifically for the interaction effect.^ In this dissertation, we investigated the validity of both approaches based on the mathematical assumptions for non-skewed data. We showed that linear regression may not be an appropriate model when the interaction effect exists because it implies a highly skewed distribution for the response variable. We also showed that the normality and constant variance assumptions required by ANOVA are not satisfied in the model where the continuous covariates are replaced with their discretized levels. Therefore, naïve application of ANOVA method may lead to an incorrect conclusion. ^ Given the problems identified above, we proposed a novel method modifying from the traditional ANOVA approach to rigorously evaluate the interaction effect. The analytical expression of the interaction effect was derived based on the conditional distribution of the response variable given the discretized continuous covariates. A testing procedure that combines the p-values from each level of the discretized covariates was developed to test the overall significance of the interaction effect. According to the simulation study, the proposed method is more powerful then the least squares regression and the ANOVA method in detecting the interaction effect when data comes from a trivariate normal distribution. The proposed method was applied to a dataset from the National Institute of Neurological Disorders and Stroke (NINDS) tissue plasminogen activator (t-PA) stroke trial, and baseline age-by-weight interaction effect was found significant in predicting the change from baseline in NIHSS at Month-3 among patients received t-PA therapy.^

Mixture modeling for joint analysis of survival, discrete, and continuous data

Mixture modeling is commonly used to model categorical latent variables that represent subpopulations in which population membership is unknown but can be inferred from the data. In relatively recent years, the potential of finite mixture models has been applied in time-to-event data. However, the commonly used survival mixture model assumes that the effects of the covariates involved in failure times differ across latent classes, but the covariate distribution is homogeneous. The aim of this dissertation is to develop a method to examine time-to-event data in the presence of unobserved heterogeneity under a framework of mixture modeling. A joint model is developed to incorporate the latent survival trajectory along with the observed information for the joint analysis of a time-to-event variable, its discrete and continuous covariates, and a latent class variable. It is assumed that the effects of covariates on survival times and the distribution of covariates vary across different latent classes. The unobservable survival trajectories are identified through estimating the probability that a subject belongs to a particular class based on observed information. We applied this method to a Hodgkin lymphoma study with long-term follow-up and observed four distinct latent classes in terms of long-term survival and distributions of prognostic factors. Our results from simulation studies and from the Hodgkin lymphoma study demonstrated the superiority of our joint model compared with the conventional survival model. This flexible inference method provides more accurate estimation and accommodates unobservable heterogeneity among individuals while taking involved interactions between covariates into consideration.^

Population-level risks of physical activity: Saving bones and screening hearts

Documented risks of physical activity include reduced bone mineral density at high activity volume, and sudden cardiac death among adults and adolescents. Further illumination of these risks is needed to inform future public health guidelines. The present research seeks to 1) quantify the association between physical activity and bone mineral density (BMD) across a broad range of activity volume, 2) assess the utility of an existing pre-screening questionnaire among US adults, and 3) determine if pre-screening risk stratification by questionnaire predicts referral to physician among Texas adolescents. ^ Among 9,468 adults 20 years of age or older in the National Health and Nutrition Examination Survey (NHANES) 2007-2010, linear regression analyses revealed generally higher BMD at the lumbar spine and proximal femur with greater reported activity volume. Only lumbar BMD in women was unassociated with activity volume. Among men, BMD was similar at activity beyond four times the minimum volume recommended in the Physical Activity Guidelines. These results suggest that the range of activity reported by US adults is not associated with low BMD at either site. ^ The American Heart Association / American College of Sports Medicine Preparticipation Questionnaire (AAPQ) was applied to 6,661 adults 40 years of age or older from NHANES 2001-2004 by using NHANES responses to complete AAPQ items. Following AAPQ referral criteria, 95.5% of women and 93.5% of men would be referred to a physician before exercise initiation, suggesting little utility for the AAPQ among adults aged 40 years or older. Unnecessary referral before exercise initiation may present a barrier to exercise adoption and may strain an already stressed healthcare infrastructure. ^ Among 3181 athletes in the Texas Adolescent Athlete Heart Screening Registry, 55.2% of boys and 62.2% of girls were classified as high-risk based on questionnaire answers. Using sex-stratified contingency table analyses, risk categories were not significantly associated with referral to physician based on electrocardiogram or echocardiogram, nor were they associated with confirmed diagnoses on follow-up. Additional research is needed to identify which symptoms are most closely related to sudden cardiac death, and determine the best methods for rapid and reliable assessment. ^ In conclusion, this research suggests that the volume of activity reported by US adults is not associated with low BMD at two clinically relevant sites, casts doubts on the utility of two existing cardiac screening tools, and raises concern about barriers to activity erected through ineffective screening. These findings augment existing research in this area that may inform revisions to the Physical Activity Guidelines regarding risk mitigation.^

Longitudinal categorical data analysis: A continuous -time Markov chain approach

In this dissertation, we propose a continuous-time Markov chain model to examine the longitudinal data that have three categories in the outcome variable. The advantage of this model is that it permits a different number of measurements for each subject and the duration between two consecutive time points of measurements can be irregular. Using the maximum likelihood principle, we can estimate the transition probability between two time points. By using the information provided by the independent variables, this model can also estimate the transition probability for each subject. The Monte Carlo simulation method will be used to investigate the goodness of model fitting compared with that obtained from other models. A public health example will be used to demonstrate the application of this method. ^

Long-term Evaluation of Hybrid, Nitrogen, and Potassium Interactions in Continuous Corn

A long-term experiment was established in 2009 to study continuous corn responses to potassium (K), nitrogen (N), and hybrid rootworm resistance. Previous research suggested a need for this study. A long-term trial conducted until 2001 at the ISU Northern Research Farm showed that the maximum corn yield level and the N rate that maximized yield was higher when K was optimal or greater. In contrast, the relative yield response to N and the N rate that maximized yield were similar for soil-test phosphorus (P) levels ranging from very low to very high. Other studies have shown that rootworm resistance often increases yield compared with untreated susceptible hybrids. Also, that rootworm resistance does not consistently affect the K rate that maximizes yield, but increases K removal because of the higher yield levels. Therefore, this new study evaluates possible interactions between rootworm resistance and N and K fertilization in corn.