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. ^

FUNCTIONS OF DEADENYLATION FACTORS IN MRNA DECAY AND MRNA PROCESSING BODY FORMATION

Most newly synthesized messenger RNAs possess a 5’ cap and a 3’ poly(A) tail. The process of poly(A) tail shortening, also termed deadenylation, is important for post-transcriptional gene regulation, because deadenylation not only leads to mRNA translational inhibition but also is the first step of major mRNA degradation. Translationally inhibited mRNAs can be stored and/or degraded in dynamic cytoplasmic foci termed mRNA processing bodies, or P bodies, which are conserved in eukaryotes. To shed new light on the mechanisms of P body formation and P body functions, I focused on the link between deadenylation factors and P bodies. I found that the two major deadenylation complexes, Pan3-Pan2 and Ccr4-Caf1, can both be enriched in P bodies. The deadenylase activity of the Ccr4-Caf1 complex is prerequisite for P body formation. Pan3, but not the deadenylase Pan2, is essential for P body formation. While the C-terminal domain of Pan3 is important for interaction with Pan2, Pan3 N-terminal domain is important for Pan3 to form cytoplasmic foci colocalizing with P bodies and to promote mRNA decay. Interestingly, Pan3 N-terminal domain may be phosphorylated to regulate Pan3 localization and functions. Aside from the functions of the two deadenylation complexes in P bodies, I also studied all reported human P body proteins as a whole using bioinformatics. This effort not only has generated a comprehensive picture of the functions of and interactions among human P body proteins, but also has predicted proteins that may regulate P body formation and/or functions. In summary, my study has established a direct link between mRNA deadenylation and P body formation and has also led to new hypotheses to guide future research on how P body dynamics are controlled.

Certified nurse midwives effects on catecholamine levels and maternal anxiety during labor

Studies of nurse midwifery care in the last twenty one years have reported excellent birth outcomes (Levy, Wilkenson and Marine, 1971; Platt et al. 1985; Stone et al. 1976). These outcomes are frequently attributed to the special support offered during labor and delivery by nurse midwives. This supportive style is thought to decrease catecholamine levels by reducing maternal anxiety. This prospective observational study evaluated catecholamine levels, anxiety levels, in-hospital costs, obstetrical practices and outcomes between low risk, term, labor and delivery primigravida patients managed by obstetrical residents (n = 55) or by certified nurse-midwives CNM (n = 59). The two groups were similar with regard to obstetrical risk factors present at admission. Each group was selected over the same period of time between March 23, 1994 and November 2, 1994. Specific catecholamines evaluated were epinephrine and norepinephrine. Obstetrical and newborn characteristics were also compared. This study did not prove that there is a decreased level in stress as indicated by lower levels of epinephrine and norepinephrine in nurse-midwife patients compared to obstetrical resident patients after adjusting for the use of epidural anesthesia. There was also no difference found in the perceived anxiety levels between the two groups. This study did confirm that nurse-midwives and obstetrical residents have different practice styles. Nurse-midwife patients had fewer augmented deliveries, fewer operative deliveries, less blood loss, fewer episiotomies and fewer third and fourth degree lacerations. The physician's choice to utilize more interventions such as continuous fetal monitoring and epidural anesthesia did not improve outcomes. The hospital cost of the nurse-midwife patients in this study was 35 percent lower than the physician patients. ^

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.^