A descriptive risk model for risk factors of stroke using least absolute shrinkage and selection operator

Loading...
Thumbnail Image
Date
October 9, 2016
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
We selected most informative risk factors of stroke as well as established the association with stroke and derived a risk score of stroke using statistically acceptable modi cations. Secondary data on the aging population of Ghana was used with a sample size of 5119. The LASSO Logistic Regression was implemented through \R"statistical software for windows version.3.1.1 using the penalised package. A key risk factor identi ed was hypertension. A person who exercises regularly had a low risk of developing stroke as compared to one who did not exercise. Data about stroke discovered angina and arthritis as emerging risk factors of stroke in addition to hypertension, physical activities, age and diabetes. We hypothesise that hypertension, diabetes and lack of physical activities re ect the trend of stroke cases in Ghana. There must be public consciousness about the signi cance of managing hypertension in Ghana.
Description
A thesis submitted to the Department of Mathematics, Kwame Nkrumah University of Science and Technology In partial fulfillment of the requirement for the Degree of M.Phil in Mathematical Statistics,
Keywords
Citation