Statistics and Probability Commons^™

Selective Multiple Imputation Of Keys For Statistical Disclosure Control In Microdata, Rod Little, Fang Liu

The University of Michigan Department of Biostatistics Working Paper Series

The fundamental tension in statistical disclosure control (SDC) of microdata is the trade-off between the protection of individual respondents and the release of enough information for statistical inferences. We consider microdata that include key variables that contain identifying information and target variables that include sensitive information. Releasing the original data may expose some individuals in the sample to high risk of disclosure; deleting key variables is a common approach, but this loses information for some statistical analysis. This paper proposes selective multiple imputation of key variables (SMIKe) as an alternative SDC technique between those two extremes, and applies SMIKe to …

Normal Mixture Models For Gene Cluster Identification In Two Dimensional Microarray Data, Eric Scott Harvey

Theses and Dissertations

This dissertation focuses on methodology specific to microarray data analyses that organize the data in preliminary steps and proposes a cluster analysis method which improves the interpretability of the cluster results. Cluster analysis of microarray data allows samples with similar gene expression values to be discovered and may serve as a useful diagnostic tool. Since microarray data is inherently noisy, data preprocessing steps including smoothing and filtering are discussed. Comparing the results of different clustering methods is complicated by the arbitrariness of the cluster labels. Methods for re-labeling clusters to assess the agreement between the results of different clustering techniques …

Statistical Image Analysis Of Spotted Arrays, Filippo Posta

Theses

There is a lot of systematic and specific variability in microarray experiments, this variability affects measured gene expression levels, leading to unreliable gene profiling or an heavy load of extra experiment to statistically confirm the data observed in one experiment.

The aim of this work is to systematically analyze, using statistics, the image derived from a cDNA microarray experiment to have a better understanding of this variability and thus a better confidence over the data obtained from an experiment.

Using technologies available at the Center for Applied Genomics, Newark, New Jersey. Selected images derived from different type of microarray experiments …

An Algorithm For Estimating The Quality Of Microarrays, Ajeet S. Sodhi

Theses

Microarray technology is currently one of the most valuable gene expression tools in molecular biology allowing the experimenter to simultaneously quantify the expression of thousands of genes. It is also one of the most difficult tools to use accurately as each microarray produces a large amount of information that needs to be inspected and normalized before analysis. As the size of a microarray or number of replicates increase, the use of manual inspection becomes impractical. The aim of this thesis is to introduce an algorithm that evaluates each feature of a microarray from the scanned data file. A quality score …

Comparative Molecular Field Analysis (Comfa) Of Protonated Methylphenidate Phenyl-Substituted Analogs, Kathleen Mary Gilbert

Theses

Protonated methylphenidate (pMP) and several phenyl-substituted pMP analogs were analyzed using Comparative Molecular Field Analysis (CoMFA) to develop a pharmacophore for dopamine transporter (DAT) binding. This research is a part of an interdisciplinary study on using methylphenidate (MP) analogs to block the binding of cocaine to the DAT as a treatment for addiction.

A random search conformational analysis using key pMP torsional angles was performed to create conformer families representing possible bioactive conformations. The lowest energy pMP conformer of each family was used as a template to create phenyl-substituted pMP analogs.

Partial least squares analysis was used to determine the …

Bottom-Up Design Of Artificial Neural Network For Single-Lead Electrocardiogram Beat And Rhythm Classification, Srikanth Thiagarajan

Doctoral Dissertations

Performance improvement in computerized Electrocardiogram (ECG) classification is vital to improve reliability in this life-saving technology. The non-linearly overlapping nature of the ECG classification task prevents the statistical and the syntactic procedures from reaching the maximum performance. A new approach, a neural network-based classification scheme, has been implemented in clinical ECG problems with much success. The focus, however, has been on narrow clinical problem domains and the implementations lacked engineering precision. An optimal utilization of frequency information was missing. This dissertation attempts to improve the accuracy of neural network-based single-lead (lead-II) ECG beat and rhythm classification. A bottom-up approach defined …

The Moral Significance Of Indetectable Effects, Sven Ove Hansson

RISK: Health, Safety & Environment (1990-2002)

A reassessment of Parfit's fifth "mistake in moral mathematics."

Body Weight And Mortality Among Adults Who Never Smoked, Pramil N. Singh

Loma Linda University Electronic Theses, Dissertations & Projects

Most prospective studies identify an increased mortality risk for adults of high body mass index (> 27 kg/m²) that is commonly attributed to the effects of excess body fat, and also identify an increased mortality risk for adults of low body mass index (< 21 kg/m²), an association that, if causal among healthy adults, is without adequate pathophysiologic support.

In this dissertation, I have conducted three studies that continue the investigation of adiposity in relation to mortality among never-smoking adults of the California Seventh-day Adventist population. Among never-smoking adults of the Adventist Mortality Study (1960-1985), the relation between …

Does The Oswestry Or Sf-36 Help A Therapist To Predict Treatment Classification, Amy Crawford, Denese D. Kaufeldt-Soliz

Loma Linda University Electronic Theses, Dissertations & Projects

The purpose of this study was to determine the relationship of two disability questionnaires, the Oswestry Low Back Pain Disability Questionnaire (Oswestry) and the Medical Outcome Study Short Form-36 (SF-36), and a standardized physical examination and diagnostic classification system. The physical examination was performed by the evaluating therapists from the clinic and classification was determined by the evaluating therapists and the investigators to ensure correct subject placement into treatment Stages la, lb, or II. Data collection occurred at an outpatient physical therapy clinic in a metropolitan area health maintenance organization, where a sample of 221 subjects with low back pain …

Multiple Outcomes In Health Services Research: Hypothesis Tests And Power, Donald C. Martin, Paula Diehr, Thomas D. Koepsell, Stephan D. Fihn

UW Biostatistics Working Paper Series

Health services research often is directed towards making small improvements in a number of outcomes that reflect many aspects of the patient’s life rather than a large improvement in a single well defined outcome. A researcher might choose five scales to measure different aspects of treatment outcomes and not expect any large treatment differences on any single outcome measure. O’Brien (1984) has proposed a nonparametric statistical procedure which is particularly well suited to this type of problem and that can result in considerable increases in statistical power. This paper will briefly review O’Brien’s pooled rank method and develop power calculations. …

Pooling Community Data For Community Interventions When The Number Of Pairs Is Small, Paula Diehr, Ted Lystig, Holly Andrilla, Ziding Feng

UW Biostatistics Working Paper Series

There is considerable interest in community interventions for health promotion, where the community is the experimental unit. Because such interventions are expensive, the number of experimental units (communities) is usually very small, yielding a study with low power. We examined the ability of a process known as “pooling” or “preliminary significance testing” to improve the power of community variations. In this process, one first tests whether there is significant community variation, using type 1 error of perhaps 0.25. If there is significant variation, the usual community-level test is performed. If not, a person-level test is performed. We found through Monte …

Power Analysis For The Mixed Linear Model, Cheryl Annette Dixon

Theses and Dissertations

Power analysis is becoming standard in inference based research proposals and is used to support the proposed design and sample size. The choice of an appropriate power analysis depends on the choice of the research question, measurement procedures, design, and analysis plan. The "best" power analysis, however, will have many features of a sound data analysis. First, it addresses the study hypothesis, and second, it yields a credible answer.

Power calculations for standard statistical hypotheses based on normal theory have been defined for t-tests through the univariate and multivariate general linear models. For these statistical methods, the approaches to power …

Student Evaluations Of Teaching Effectiveness: The Interpretation Of Observational Data And The Principle Of Faute De Mieux, B. Burt Gerstman

Faculty Publications

Student opinion surveys are important but widely misunderstood tools for evaluating teaching effectiveness. In this brief review, an analogy is drawn between the use and interpretation of observational data for public health and biomedical research and the use of student opinion data in evaluating teach ing effectiveness. Sources of systematic error in the form of selection bias, information bias, and confounding are defined and illustrated. Original data concerning intermittent "quid pro quo" confounding (i.e., the effect of expected grades on student evaluations of teaching) are presented. Finally, the principle of faute de mieux ("lack of anything better") and the interpretation …

The Relationship Of Dietary And Lifestyle Factors To Bone Mineral Density Of Healthy Singaporean Chinese Women, Ampai Dana Aimsiri

Loma Linda University Electronic Theses, Dissertations & Projects

Few studies have examined the risk factors associated with reduced bone mass in Asians, but none specifically investigated Singaporean Chinese women. The subjects in this study were 16 premenopausal, 8 perimenopausal and 13 postmenopausal women who participated in a larger study which began in 1986. Bone density was measured in 1986 and 1992. Dietary and lifestyle data were collected for this study by personal interview. Association between dietary and lifestyle factors and bone density variables and change in bone density at the end of the 6 year period were assessed by univariate regression analyses.

Postmenopausal women had significantly lower baseline …

An Empirical Study Of Small-Area Variation For Icd-9 Surgical Procedures, Paula Diehr, Kevin Cain, Zhan Ye, John Loeser

UW Biostatistics Working Paper Series

Objective. Several measures of variation have been used in SAVA. One study of DRGs found that the coefficient of variation from analysis of variance (CVA) had superior performance. That work is replicated here for ICD-9 surgical procedures, and extended to age/sex-standardized rates. Results are compared with those in the literature, and recommendations are made for assessing small-area variation in future studies.

Data Sources. Data were taken from Washington State's "Episode of Illness" file of hospital discharges in the State in 1987. Up to three ICD-9 surgical procedures and a unique patient identifier were available for each discharge.

Study Design. We …

Methods For The Comparison Of Timing Behavior Applied To The Pink Salmon Fisheries Of Prince William Sound, Alaska, Louis J. Rugolo

OES Theses and Dissertations

Harvest control in salmonid fisheries was examined as a problem in the formulation of regulations which restrict time and area of fishing. An ability to rigorously define and compare the form of the progression of migration across time and between harvest areas was judged fundamental to objective harvest decisions. Identification and evaluation of statistical methods appropriate to the comparison of empirical migratory time densities was performed.

The development of the measure of central tendency (mean date) of the time density as the consistent, unbiased estimator of migratory behavior was given. Practical evidence demonstrated that the mean date was highly resistant …

The Standardized Influence Matrix And Its Applications To Generalized Linear Models, Jiandong Lu

Theses and Dissertations

The standardized influence matrix is a generalization of the standardized influence function and Cook’s approach to local influence. It provides a general and unified approach to judge the suitability of statistical inference based on parametric models. It characterizes the local influence of data deviations from parametric models on various estimators, including generalized linear models. Its use for both robustness measures and diagnostic procedures has been studied. With global robust estimators, diagnostic statistics are proposed and shown to be useful in detecting influential points for linear regression and logistic regression models. Robustness of various estimators is compared via. the standardized influence …

Breaking The Matches In A Paired T-Test For Community Interventions When The Number Of Pairs Is Small, Paula Diehr, Don C. Martin, Thomas D. Koepsell, Allen D. Cheadle

UW Biostatistics Working Paper Series

There is considerable interest in community interventions for health promotion, where the community is the experimental unit. Because such interventions are expensive, the number of experimental units (communities) is usually small. Because of the small number of communities involved, investigators often match treatment and control communities on demographic variables before randomization to minimize the possibility of a bad split. Unfortunately, matching has been shown to decrease the power of the design when the number of pairs is small, unless the matching variable is very highly correlated with the outcome variable (in this case, with change in the health behavior). We …

The Multiple Admission Factor (Maf) In Small Area Variation Analysis, Kevin Cain, Paula Diehr

UW Biostatistics Working Paper Series

Small area variation analysis are often based on area-level data such as the total number of hospital admissions within an area, rather than person-level data. Such analysis often make the assumption that the number of admissions within a small area follow a Poisson distribution. This may not be a reasonable assumption when multiple admissions per person are possible. In this case, the multiple admission factor (MAF) can be used to adjust for the extra variance introduced by multiple admissions. In this article, data from Washington State are used to estimate the multiple admission rate and the MAF for each modifed …

Condylar Angulations As Related To Submental-Vertex Radiographs, Jady L. Chiakowsky

Loma Linda University Electronic Theses, Dissertations & Projects

Pretreatment submental-vertex radiographs were obtained for 637 adolescent patients (307 males, 330 females) who had presented themselves for orthodontic treatment. The purpose of this study was to: (1) determine the relationship between condylar angulations and depth of cut with the variables: age, sex, and race, and (2) establish normative values for the categories studied. The results indicated that no significant differences existed between the condylar angulations for the variables measured. However, significant differences did exist between the depth of cut for the variables measured and there was significant interaction between age and race with respect to the depth of cut. …

Missing Data In Repeated Measurement Studies, Kejian Niu

Theses and Dissertations

Repeated measurement data or longitudinal data occur often in statistical applications. For example, in a clinical trial comparing the efficacy of a new treatment with that of a standard treatment, rather than measuring the main response variable only once on each patient, or subject, we can take several measurements over time on each subject.

A Repeated measurement study differs from a longitudinal study. The latter generally refers to any study in which one or more response variables are repeatedly measured over time. The former usually imposes some restrictions on the data. One common restriction is that each response variable must …

A Flow Cytometric Analysis Of Immunocyte Populations In Peripheral Blood And Pleural Effusions Of Patients With Cancer, Mandy L. Bohn

Loma Linda University Electronic Theses, Dissertations & Projects

Two-color flow cytometric analysis was performed on paired samples of peripheral blood (PB) and pleural effusions (PE) of patients with metastatic malignancies. The purpose of these analyses was to test the hypothesis that there are significant differences in the distribution of immunocyte populations in the PE compared to that of the PB.

The majority of the pleural fluid immunocytes were CD3+ cells. The ratio of CD4+ to CD8+ cells was higher in the PE compared to PB. Levels of CD8+, CD19+ and CD14+ cells were not significantly different in the PE compared to the levels in the PB. CD16+CD56+ cells …

Classification Of Newborns Based On Maturity Rating And Intrauterine Growth At The Medical College Of Virginia Hospitals, Lydia Holmes Sund

Theses and Dissertations

Nurses at the Medical College of Virginia Hospitals (MCVH) in Richmond, Virginia, use the Newborn Maturity Rating and Classification Tool to identify high risk infants. An estimate of gestational age is made and using this estimate, weight, length, and head circumference measurements are plotted on graphs on the tool to determine if the infant achieves intrauterine growth smaller, larger or equal to gestational age.

The data used to generate the graphs on the Newborn Maturity Rating and Classification Tool were collected in Colorado during the 1950's. Two nurses at MCVH questioned the use of these graphs. They wanted to know …

Regression Models For Bivariate Binary Responses, Juni Palmgren

UW Biostatistics Working Paper Series

We discuss maximum likelihood inference for the bivariate logistic model, specified in terms of the marginal logits and the log odds ratio. Using the exponential family nonlinear model formulation the model fitting can be done in GLIM. The procedure is illustrated by modelling survival of unilateral and bilateral total hip arthroplasties as function of patient specific and hip specific covariates. We compare maximum likelihood inference with inference obtained from solving likelihood equations under the assumption of within block independence and using robust standard errors for the estimates. Simulations indicate that the latter procedure is effcient for block specific covariates but …

Effect Of Photoperiod On Developmental Morphology And Enolase Isoenzyme Immunohistochemistry In Rat And Djungarian Hamster Superficial Pineal Glands, Chalmer D. Mcclure

Loma Linda University Electronic Theses, Dissertations & Projects

The best understood functional activity of the pineal gland is its diurnal production of melatonin in response to environmental lighting cues. Several enzymes of the melatonin pathway respond to daily photoperiod changes, for example hydroxyindole-O-methyltransferase (HIOMT) and serotonin N-acetyltransferase (SNAT). Increased levels of the glycolytic enzyme neuron-specific enolase (NSE) are thought to reflect increased physiological demands placed on neurons and neuroendocrine tissues. Homodimer non-neuronal enolase isoenzyme (NNE) is immunolocalized to cells, and the hybrid enolase (consisting of subunits from NSE and NNE) has been seen in cerebellar stellate and basket cells. Although not rate limiting, concentrations of both NSE and …

Mathematical Models Of Prevascular Tumor Growth By Diffusion, Sophia A. Maggelakis

Mathematics & Statistics Theses & Dissertations

A study of several complementary mathematical models that describe the early, prevascular stages of solid tumor growth by diffusion under various simplifying assumptions is presented. The advantage of these models is that their degree of complexity is relatively low, which ensures fairly straightforward comparisons with experimental or clinical data (as it becomes available), yet they are mathematically sophisticated enough to capture the main biological phenomena of interest.

The tumor growth and cell proliferation rate are assumed to depend on the local concentrations of nutrients and inhibitory factors. The effects of geometry and spatially non-uniform inhibitor production and non-uniform nutrient consumption …

Decreased Triiodothyronine Binding To The Hepatic Nuclear Thyroid Hormone Receptor In The Diabetic Mouse, Thomas J. Dewind

Loma Linda University Electronic Theses, Dissertations & Projects

The diabetic C57BL/KsJ-db m mouse has abnormal thyroid hormone levels and indications of thyroid hormone resistance. To investigate the basis of these abnormalities, the hepatic nuclear thyroid hormone receptor was extracted with 0.4 M KCl, 1.1 mM MgCl₂, 20 mM Tris/HCl, pH 7.9 from hepatocyte nuclei of normal C57BL/KsJ, heterozygous C57BL/KsJ-db m (db/m), and diabetic C57BL/KsJ-db m (db/db) mice. Normal and heterozygous mice were grouped together as the controls. Triiodothyronine (T₃) binding studies at 4°C using nitrocellulose filtration to separate free T₃ from receptor bound T₃ demonstrated an …

Time Delayed Protein Complementation, Diana L. Lakusta

Loma Linda University Electronic Theses, Dissertations & Projects

The time delayed complementation of plant proteins was tested in weanling Sprague-Dawley male rats by measuring growth rates as well as plasma and tissue free amino acids. Diets of pinto beans with rice, corn or wheat were pair-fed in combination or alternating 4 times a day at 6 and 11 am, and 4 and 9 pm for 4 weeks. Plasma, liver and muscle samples were obtained 2 hours postprandial, a time determined most suitable for sacrifice, and analyzed for free amino acids via ion-exchange chromatography. There were no significant differences in growth of rats fed combination or alternating diets.during week …

False Positive Rates Encountered In The Detection Of Changes In Periodontal Attachment Level, John C. Gunsolley

Theses and Dissertations

This thesis demonstrates that the assumption of normality used by Goodson results in the underestimation of the type I error rate of the tolerance method by a factor of 10. This underestimation is due to the positive kurtosis demonstrated in the distribution of replicate differences. Therefore, the assumption of normality does not seem warranted. It is shown here that a resampling technique more accurately estimates the type I error rate.

The estimates of false positive rates have important implications in the field of periodontics. When diagnostic decisions are based on single measurements, false positive rates are high. Even when thresholds …

The Effect Of Dietary Fat Level On Tumor Development And Immunity In Balb/C Mice Fed Casein Of Wheat Gluten As Protein And Challenged With Herpes Type 2-Transformed Cells, Helen Drakou

Loma Linda University Electronic Theses, Dissertations & Projects

A high percentage of fat in the diet has been implicated through epidemiological studies in several human cancers. Studies in experimental animals have produced evidence that increasing the fat in the diet decreases the animal’s ability to restrict tumor development and growth. In previous work done in this laboratory with BALB/c mice injected with herpes simplex Type 2-transformed mouse cells (H238), the effects of a diet which greatly enhanced tumor growth was compared with one which restricted tumor growth. The latter, a low (5%) fat, low protein diet, in which the protein was casein, was also found to produce a …