Browsing by Subject "Multivariate analysis"

Now showing 1 - 9 of 9
  • Thumbnail Image
    Item
    Combining Multivariate Statistical Methods and Spatial Analysis to Characterize Water Quality Conditions in the White River Basin, Indiana, U.S.A.
    (2011-02-25) Gamble, Andrew Stephan; Babbar-Sebens, Meghna; Tedesco, Lenore P.; Peng, Hanxiang
    This research performs a comparative study of techniques for combining spatial data and multivariate statistical methods for characterizing water quality conditions in a river basin. The study has been performed on the White River basin in central Indiana, and uses sixteen physical and chemical water quality parameters collected from 44 different monitoring sites, along with various spatial data related to land use – land cover, soil characteristics, terrain characteristics, eco-regions, etc. Various parameters related to the spatial data were analyzed using ArcHydro tools and were included in the multivariate analysis methods for the purpose of creating classification equations that relate spatial and spatio-temporal attributes of the watershed to water quality data at monitoring stations. The study compares the use of various statistical estimates (mean, geometric mean, trimmed mean, and median) of monitored water quality variables to represent annual and seasonal water quality conditions. The relationship between these estimates and the spatial data is then modeled via linear and non-linear multivariate methods. The linear statistical multivariate method uses a combination of principal component analysis, cluster analysis, and discriminant analysis, whereas the non-linear multivariate method uses a combination of Kohonen Self-Organizing Maps, Cluster Analysis, and Support Vector Machines. The final models were tested with recent and independent data collected from stations in the Eagle Creek watershed, within the White River basin. In 6 out of 20 models the Support Vector Machine more accurately classified the Eagle Creek stations, and in 2 out of 20 models the Linear Discriminant Analysis model achieved better results. Neither the linear or non-linear models had an apparent advantage for the remaining 12 models. This research provides an insight into the variability and uncertainty in the interpretation of the various statistical estimates and statistical models, when water quality monitoring data is combined with spatial data for characterizing general spatial and spatio-temporal trends.
  • Thumbnail Image
    Item
    Computational Analysis of Flow Cytometry Data
    (2013-07-12) Irvine, Allison W.; Dundar, Murat; Tuceryan, Mihran; Mukhopadhyay, Snehasis; Fang, Shiaofen
    The objective of this thesis is to compare automated methods for performing analysis of flow cytometry data. Flow cytometry is an important and efficient tool for analyzing the characteristics of cells. It is used in several fields, including immunology, pathology, marine biology, and molecular biology. Flow cytometry measures light scatter from cells and fluorescent emission from dyes which are attached to cells. There are two main tasks that must be performed. The first is the adjustment of measured fluorescence from the cells to correct for the overlap of the spectra of the fluorescent markers used to characterize a cell’s chemical characteristics. The second is to use the amount of markers present in each cell to identify its phenotype. Several methods are compared to perform these tasks. The Unconstrained Least Squares, Orthogonal Subspace Projection, Fully Constrained Least Squares and Fully Constrained One Norm methods are used to perform compensation and compared. The fully constrained least squares method of compensation gives the overall best results in terms of accuracy and running time. Spectral Clustering, Gaussian Mixture Modeling, Naive Bayes classification, Support Vector Machine and Expectation Maximization using a gaussian mixture model are used to classify cells based on the amounts of dyes present in each cell. The generative models created by the Naive Bayes and Gaussian mixture modeling methods performed classification of cells most accurately. These supervised methods may be the most useful when online classification is necessary, such as in cell sorting applications of flow cytometers. Unsupervised methods may be used to completely replace manual analysis when no training data is given. Expectation Maximization combined with a cluster merging post-processing step gives the best results of the unsupervised methods considered.
  • Thumbnail Image
    Item
    Donor Utilization in the Recent Era: Effect of Sex, Drugs, and Increased Risk
    (American Heart Association, 2022) Baran, David A.; Long, Ashleigh; Lansinger, Justin; Copeland, Jack G.; Copeland, Hannah; Surgery, School of Medicine
    Background: Heart transplantation volumes have increased in recent years, yet less than a third of donors are typically accepted for transplantation. Whether donor sex, donor drug use, or perception of increased risk affects utilization for transplantation is unclear. Methods: The United Network for Organ Sharing database was queried for donors from January 1, 2007, to December 31, 2017. Donor toxicology was collected when available. Multivariate analysis was conducted to examine correlations with donor utilization. Results: Between January 1, 2007, and December 31, 2017, there were 87 816 heart donors aged ≥15 years. The mean age was 42.7±15.8 years, and 24 831 donors (28.3%) were utilized for heart transplantation. Subsequent analyses focused on donors between 15 and 39 years old. The strongest associations with donor acceptance were for male donor sex, blood type, hepatitis C antibody, donor age, left ventricular hypertrophy, and history of donor drug use. After removing hepatitis C, Public Health Service Increased Risk was identified as a strong negative predictor. Most positive drug toxicology results were associated with donor nonuse except for donors between 15 and 19 years of age. Exceptions included alcohol, marijuana, and cocaine. Opiates were associated with less utilization at all donor ages. The Public Health Service Increased Risk status was associated with significantly less utilization in all age groups except 15- to 19-year-old donors. Conclusions: While male donors were preferentially utilized, donors with drug use or those deemed Public Health Service Increased Risk were significantly less utilized for heart transplantation. Further consideration of such donors would be appropriate particularly as the demand for transplantation continues to increase.
  • Thumbnail Image
    Item
    An evaluation of the moving horizon estimation algorithm for online estimation of battery state of charge and state of health
    (2014) Bibin Nataraja, Pattel; Anwar, Sohel
    Moving Horizon Estimation (MHE) is a powerful estimation technique for tackling the estimation problems of the state of dynamic systems in the presence of constraints, nonlinearities and disturbances and measurement noises. In this work, the Moving Horizon Estimation approach is applied in estimating the State of Charge (SOC) and State of Health (SOH) of a battery and the results are compared against those for the traditional estimation method of Extended Kalman Filter (EKF). The comparison of the results show that MHE provides improvement in performance over EKF in terms of different state initial conditions, convergence time, and process and sensor noise variations. An equivalent circuit battery model is used to capture the dynamics of the battery states, experimental data is used to identify the parameters of the battery model. MHE based state estimation technique is applied to estimates the states of the battery model, subjected to various estimated initial conditions, process and measurement noises and the results are compared against the traditional EKF based estimation method. Both experimental data and simulations are used to evaluate the performance of the MHE. The results shows that MHE performs better than EKF estimation even with unknown initial state of the estimator, MHE converges faster to the actual states,and also MHE is found to be robust to measurement and process noises.
  • Thumbnail Image
    Item
    Increased epigenetic age in normal breast tissue from luminal breast cancer patients
    (Biomed Central, 2018-08-29) Hofstatter, Erin W.; Horvath, Steve; Dalela, Disha; Gupta, Piyush; Chagpar, Anees B.; Wali, Vikram B.; Bossuyt, Veerle; Storniolo, Anna Maria; Hatzis, Christos; Patwardhan, Gauri; Von Wahlde, Marie-Kristin; Butler, Meghan; Epstein, Lianne; Stavris, Karen; Sturrock, Tracy; Au, Alexander; Kwei, Stephanie; Pusztai, Lajos; Medicine, School of Medicine
    BACKGROUND: Age is one of the most important risk factors for developing breast cancer. However, age-related changes in normal breast tissue that potentially lead to breast cancer are incompletely understood. Quantifying tissue-level DNA methylation can contribute to understanding these processes. We hypothesized that occurrence of breast cancer should be associated with an acceleration of epigenetic aging in normal breast tissue. RESULTS: Ninety-six normal breast tissue samples were obtained from 88 subjects (breast cancer = 35 subjects/40 samples, unaffected = 53 subjects/53 samples). Normal tissue samples from breast cancer patients were obtained from distant non-tumor sites of primary mastectomy specimens, while samples from unaffected women were obtained from the Komen Tissue Bank (n = 25) and from non-cancer-related breast surgery specimens (n = 28). Patients were further stratified into four cohorts: age < 50 years with and without breast cancer and age ≥ 50 with and without breast cancer. The Illumina HumanMethylation450k BeadChip microarray was used to generate methylation profiles from extracted DNA samples. Data was analyzed using the "Epigenetic Clock," a published biomarker of aging based on a defined set of 353 CpGs in the human genome. The resulting age estimate, DNA methylation age, was related to chronological age and to breast cancer status. The DNAmAge of normal breast tissue was strongly correlated with chronological age (r = 0.712, p < 0.001). Compared to unaffected peers, breast cancer patients exhibited significant age acceleration in their normal breast tissue (p = 0.002). Multivariate analysis revealed that epigenetic age acceleration in the normal breast tissue of subjects with cancer remained significant after adjusting for clinical and demographic variables. Additionally, smoking was found to be positively correlated with epigenetic aging in normal breast tissue (p = 0.012). CONCLUSIONS: Women with luminal breast cancer exhibit significant epigenetic age acceleration in normal adjacent breast tissue, which is consistent with an analogous finding in malignant breast tissue. Smoking is also associated with epigenetic age acceleration in normal breast tissue. Further studies are needed to determine whether epigenetic age acceleration in normal breast tissue is predictive of incident breast cancer and whether this mediates the risk of chronological age on breast cancer risk.
  • Thumbnail Image
    Item
    Multivariate Statistical Methods Applied to the Analysis of Trace Evidence
    (2013-08-22) Szkudlarek, Cheryl Ann; Goodpaster, John V. (John Vincent); Picard, Christine; Siegel, Jay A.; Minto, Robert
    The aim of this study was to use multivariate statistical techniques to: (1) determine the reproducibility of fiber evidence analyzed by MSP, (2) determine whether XRF is an appropriate technique for forensic tape analysis, and (3) determine if DART/MS is an appropriate technique for forensic tape analysis. This was achieved by employing several multivariate statistical techniques including agglomerative hierarchical clustering, principal component analysis, discriminant analysis, and analysis of variance. First, twelve dyed textile fibers were analyzed by UV-Visible MSP. This analysis included an inter-laboratory study, external validations, differing preprocessing techniques, and color coordinates. The inter-laboratory study showed no statistically significant difference between the different instruments. The external validations had overall acceptable results. Using first derivatives as a preprocessing technique and color coordinates to define color did not result in any additional information. Next, the tape backings of thirty-three brands were analyzed by XRF. After chemometric analysis it was concluded that the 3M tapes with black adhesive can be classified by brand except for Super 33+ (Cold Weather) and Super 88. The colorless adhesive tapes were separated into two large groups which were correlated with the presence of aluminosilicate filler. Overall, no additional discrimination was seen by using XRF compared to the traditional instrumentation for tape analysis previously published. Lastly, the backings of eighty-nine brands of tape were analyzed by DART/MS. The analysis of the black adhesive tapes showed that again discrimination between brands is possible except for Super 33+ and Super 88. However, now Tartan and Temflex have become indistinguishable. The colorless adhesive tapes again were more or less indistinguishable from one another with the exception of Tuff Hand Tool, Qualpack, and a roll of 3M Tartan, which were found to be unique. It cannot be determined if additional discrimination was achieved with DART/MS because the multivariate statistical techniques have not been applied to the other instrumental techniques used during tape analysis.
  • Thumbnail Image
    Item
    A Psychometric Evaluation of Script Concordance Tests for Measuring Clinical Reasoning
    (2013-06) Wilson, Adam Benjamin; Pike, Gary R. (Gary Robert), 1952-; Humbert, Aloysius J.; Brokaw, James J.; Seifert, Mark F.
    Purpose: Script concordance tests (SCTs) are assessments purported to measure clinical data interpretation. The aims of this research were to (1) test the psychometric properties of SCT items, (2) directly examine the construct validity of SCTs, and (3) explore the concurrent validity of six SCT scoring methods while also considering validity at the item difficulty and item type levels. Methods: SCT scores from a problem solving SCT (SCT-PS; n=522) and emergency medicine SCT (SCT-EM; n=1040) were used to investigate the aims of this research. An item analysis was conducted to optimize the SCT datasets, to categorize items into levels of difficulty and type, and to test for gender biases. A confirmatory factor analysis tested whether SCT scores conformed to a theorized unidimensional factor structure. Exploratory factor analyses examined the effects of six SCT scoring methods on construct validity. The concurrent validity of each scoring method was also tested via a one-way multivariate analysis of variance (MANOVA) and Pearson’s product moment correlations. Repeated measures analysis of variance (ANOVA) and one-way ANOVA tested the discriminatory power of the SCTs according to item difficulty and type. Results: Item analysis identified no gender biases. A combination of moderate model-fit indices and poor factor loadings from the confirmatory factor analysis suggested that the SCTs under investigation did not conform to a unidimensional factor structure. Exploratory factor analyses of six different scoring methods repeatedly revealed weak factor loadings, and extracted factors consistently explained only a small portion of the total variance. Results of the concurrent validity study showed that all six scoring methods discriminated between medical training levels in spite of lower reliability coefficients on 3-point scoring methods. In addition, examinees as MS4s significantly (p<0.001) outperformed their MS2 SCT scores in all difficulty categories. Cross-sectional analysis of SCT-EM data reported significant differences (p<0.001) between experienced EM physicians, EM residents, and MS4s at each level of difficulty. When considering item type, diagnostic and therapeutic items differentiated between all three training levels, while investigational items could not readily distinguish between MS4s and EM residents. Conclusions: The results of this research contest the assertion that SCTs measure a single common construct. These findings raise questions about the latent constructs measured by SCTs and challenge the overall utility of SCT scores. The outcomes of the concurrent validity study provide evidence that multiple scoring methods reasonably differentiate between medical training levels. Concurrent validity was also observed when considering item difficulty and item type.
  • Thumbnail Image
    Item
    Single-index regression models
    (2015-05) Wu, Jingwei; Tu, Wanzhu
    Useful medical indices pose important roles in predicting medical outcomes. Medical indices, such as the well-known Body Mass Index (BMI), Charleson Comorbidity Index, etc., have been used extensively in research and clinical practice, for the quantification of risks in individual patients. However, the development of these indices is challenged; and primarily based on heuristic arguments. Statistically, most medical indices can be expressed as a function of a linear combination of individual variables and fitted by single-index model. Single-index model represents a way to retain latent nonlinear features of the data without the usual complications that come with increased dimensionality. In my dissertation, I propose a single-index model approach to analytically derive indices from observed data; the resulted index inherently correlates with specific health outcomes of interest. The first part of this dissertation discusses the derivation of an index function for the prediction of one outcome using longitudinal data. A cubic-spline estimation scheme for partially linear single-index mixed effect model is proposed to incorporate the within-subject correlations among outcome measures contributed by the same subject. A recursive algorithm based on the optimization of penalized least square estimation equation is derived and is shown to work well in both simulated data and derivation of a new body mass measure for the assessment of hypertension risk in children. The second part of this dissertation extends the single-index model to a multivariate setting. Specifically, a multivariate version of single-index model for longitudinal data is presented. An important feature of the proposed model is the accommodation of both correlations among multivariate outcomes and among the repeated measurements from the same subject via random effects that link the outcomes in a unified modeling structure. A new body mass index measure that simultaneously predicts systolic and diastolic blood pressure in children is illustrated. The final part of this dissertation shows existence, root-n strong consistency and asymptotic normality of the estimators in multivariate single-index model under suitable conditions. These asymptotic results are assessed in finite sample simulation and permit joint inference for all parameters.
  • Thumbnail Image
    Item
    Using Evidence Based Practice: The Relationship Between Work Environment, Nursing Leadership and Nurses at the Bedside
    (2013-01-30) Pryse, Yvette M.; Schafer, John; McDaniel, Anna M.; Swenson, Melinda M.; Duffy, Joanne R.; Cook, Cynthia A., 1945-
    Evidence based practice (EBP) is essential to the practice of nursing for purposes of promoting optimal patient outcomes. Research suggests that the implementation of EBP by staff nurses is problematic and influenced by beliefs, nursing leadership and the work environment. The purpose of this descriptive study was to examine variables that describe the relationship among beliefs about EBP, the work environment and nursing leadership on the EBP implementation activities of the staff nurse. The variables of interest were 1) individual staff nurse characteristics, 2) beliefs about EBP, 3) the EBP work environment and 4) nursing leadership for EBP. A descriptive, quantitative method was used. A sample of 422 Registered Nurses from two urban hospitals (one Magnet and one non-Magnet) completed an online 58 item survey that included questions related to individual belief’s about EBP, the EBP work environment and nursing leadership for EBP as well as EBP implementation activities. Education, tenure and Magnet status were not significantly related to EBP implementation activities in either the univariate or multivariate analysis. EBP beliefs had a significantly positive relationship with EBP implementation activities in both the univariate and multivariate analyses. Work environment and nursing leadership support for EBP had significant positive relationships with self-reported implementation activities in only the univariate analysis. The most surprising finding was that there were no differences between Magnet and non-Magnet work environments for EBP implementation scores, yet the Magnet hospitals reported higher means on the EBP Beliefs Scale than the non-Magnet hospital. The results of this have implications for identifying and testing strategies to influence EBP implementation activities through development of nursing leadership skills for EBP and creating a more EBP friendly work environment.