- Title
- Factor analysis for dtetermination of metabolic syndrome components of anthropometric data from Kinshasa hiterland of the Democractic Republic of Congo
- Creator
- Nasila, John Sungwacha
- Subject
- Factor analysis Multivariate analysis
- Date Issued
- 2017
- Date
- 2017
- Type
- Thesis
- Type
- Doctoral
- Type
- PhD
- Identifier
- http://hdl.handle.net/10353/14032
- Identifier
- vital:39799
- Description
- Factor analysis is a multivariate statistical approach commonly used in psychology, education, and more recently in the health-related professions. This thesis will attempt to provide novice and experienced researchers an application of two factor analysis methods which are; exploratory factor analysis (EFA) and Confirmatory Factor Analysis (CFA) to medical data. As Biostatistics knowledge continues to grow, it is timely that this thesis contributes immensely; firstly to the discipline of Biostatistics and secondly to Medicine both nationally and internationally. Factor analysis is an important tool that can be used in the development, refinement, and evaluation of tests, scales, and measures that can be used in education and in health-related professions such as medicine. This thesis is focused on applying Factor Analysis on medical data, specifically on data obtained from patients that suffer from Metabolic Syndrome and patients who don’t suffer from Metabolic Syndrome. Metabolic Syndrome (MS) is a constellation of components (factors) such as obesity, lipid-lipoprotein (fats) disorders, increase in glucose (sugar), hypertension (blood pressure), and inflammation/ hypercoagulability (clotting). MS and other risk factors; (smoking, physical inactivity, excessive alcohol intake, and inappropriate diet) determine high morbidity and mortality for the cardiovascular disease (CVD=heart attack, brain attack, peripheral vascular disease) or cardio-metabolic risk (CMR=type 2 diabetes, kidney disease, retinopathy). Obesity, CVD, and CMR are emerging as epidemic conditions worldwide. However, Africa is not paying priority to early detection, treatment, prevention and control of atherosclerotic diseases (MS, CMR) from valid and reliable data. The aim of this thesis was to examine anthropometry, glucose and blood pressure (non-lipid components of MS) as most valid, reliable, less time-consuming, less complex and less expensive procedure of identifying people at high risks of CVD and CMR. A further contribution of this thesis was its understanding of the economic implications of the burden of Metabolic Syndrome. Other burden factors have been identified and also discussed. The study has revealed that the presence of metabolic syndrome has contributed to an enormous economic burden by about 20percent of the total economic loss experienced by many countries. The prevalence has risen recently and elevated patients’ use of more health care resources, and face higher morbidity and mortality, resulting in an enormous economic burden. Some studies have shown healthcare costs to be as much as 20percent higher than those accrued by patients without the risk factors. Patients with the Metabolic Syndrome have been shown to have greater drug expenditures, more frequent hospitalizations, and higher utilization of outpatient and physician services. When considered alone, the individual risk factor components account for a substantial economic burden to patients, health plans, and society as a whole. Overall, this has had serious economic impacts on many countries. The diagnosis of Metabolic Syndrome as a condition may encourage appropriate management and thus help prevent disease progression and reduce the considerable economic impact. This study was a cross-sectional, comparative, and correlational survey conducted between January and April 2005, in Kinshasa Hinterland, DRC. Participants were black Bantu Africans. In this study, the researcher attempted to determine latent factors that could explain the variability in a large set of data collected on many individuals of mixed health statuses. The original population consisted of 9770 people of whom, only 977 (10percent) participated. Factor analysis and interpretation of the results were based on anthropometric parameters (body mass index or BMI and waist circumference or WC), blood pressure (BP), lipid (triglycerides)-lipoprotein (HDL-C) and glucose with different numbers and cutoffs of components of Metabolic Syndrome. A number of different statistical procedural methods have been employed to clearly scrutinize and bring out the information which is concealed in a variety of variables observed/collected on many human participants. A large portion of these approaches was based on multivariate statistical methods. The approach, in this case, was the application of Principal Component Analysis (PCA); a multivariate statistical approach used under Factor Analysis to reduce many variables into a few latent variables which are seen as capable of explaining the variability. The approach was effected under both conditions of presence and absence of metabolic risk. Other data settings were: within males, within females, in the rural and in urban communities.
- Format
- 266 leaves
- Format
- Publisher
- University of Fort Hare
- Publisher
- Faculty of Science and Agriculture
- Language
- English
- Rights
- University of Fort Hare
- Hits: 466
- Visitors: 419
- Downloads: 61
Collections
UFH Department of Statistics
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | SOURCE1 | PhD (Biostatistics) NASILA.pdf | 3 MB | Adobe Acrobat PDF | View Details Download |