Health Status Analysis of the Erythrocyte Sedimentation Rate (ESR) of Patients Using Logistic Regression Method

Abstract

In this study, a logistic the Institute of Medical Research, Kuala Lumpur, Malaysia which contained 32 observations and 3 variables( Three logistic regression models were constructed namely: the null model (model with only the constant), model with the two predictors and model with the best predictor.Backward selection procedure was used in this study variable that contributes to the outcome of the erythrocyte sedimentation rate (ESR). The logistic regression models were constructed for the data with their corresponding accuracy and precision at 95% confidence level.Various tests were validate the models obtained.The result shows that only significantly to the outcome of the erythrocyte sedimentation rate (ESR) while Globulins do not really contributed. It is indeed possible to predict whether a patient is healthy or not based on the values of individual. Also it was discovered that the in predicting whether a patient is healthy or not.The best model was the model with the two predictors with 87.5

Keywords: Logistic regression, maximum likelihood, prediction, akaike information criteria, deviance, modelling

1.0 Introduction Logistic regression model is a mathematical model that describe the relationship of several independent variabless to a binar (dichtomous) dependent variable.Logistic regression model was developed primarily by Cox in 1958 and Walker and Duncan in 1967 [1- 4].Logistic regression can be seen as a special case of regression. The model of logistic regression, however, is based on quite different assumptions (about the relationship between dependent and independent variables) from those of linear regression [5]. In particular the key differences of these two models can be seen in the following two features of logistic regression. First, the conditional distribution is a Bernoulli variable is binary. Second, the predicted values are probabilities and are therefore restri distribution function because logistic regression predicts the Logistic regression is an alternative to Fisher's 1936 classification method, linear discriminant analysis hold, application of linear discriminant assumptions are true, logistic regression assumptions must hold. The converse is not true, so the logisti model has fewer assumptions than discriminant analys variables [8-9]. All the analysis were carried out using Statistical Package for Social Sciences [10 1.1 The Erythrocytes Sedimentation Rate The erythrocyte sedimentation rate (ESR), al cells sediment in a period of one hour. It is a common The erythrocyte sedimentation rate (ESR) is the

Corresponding author: Aye P.O, E-mail: ayepatricko@gmail.com, Tel.:

Journal of the Nigerian Association of Mathematical Physics 163 Journal of the Nigerian Association of Mathematical Physics Volume 37, (November, 201

Health Status Analysis of the Erythrocyte Sedimentation Rate (ESR) of Patients Using Logistic Regression Method

Aye P.O, 2Ologbonyo J.J and 3Azuaba E.

Department of Mathematical Sciences, Adekunle Ajasin University, Akungba Ondo State, Nigeria Department of Mathematics, Federal University of Technology, Minna, Nigeria

Abstract In this study, a logistic regression model was fitted using a secondary data from the Institute of Medical Research, Kuala Lumpur, Malaysia which contained 32 observations and 3 variables(Fibrinogen ( ), γ-Globulins ( ) and Health Status). Three logistic regression models were constructed namely: the null model (model with only the constant), model with the two predictors and model with the best predictor.Backward selection procedure was used in this study to select the best variable that contributes to the outcome of the erythrocyte sedimentation rate (ESR). The logistic regression models were constructed for the data with their corresponding accuracy and precision at 95% confidence level.Various tests were carried out to validate the models obtained.The result shows that only Fibrinogen contributed significantly to the outcome of the erythrocyte sedimentation rate (ESR) while γ do not really contributed. It is indeed possible to predict whether a patient is healthy or not based on the values of Fibrinogen ( ) and γ-Globulins ( ) of an t was discovered that the Fibrinogen ( ) is the best predictor to use in predicting whether a patient is healthy or not.The best model was the model with the two predictors with 87.5% accuracy.