Demographic Variables & Nutritional Risk: The Predictive Power Using Binary Logit Model

Suraj Kushe Shekhar; Rehin K.R; Dr. P.T Raveendran

Volume : III, Issue : XI, November - 2013

Demographic Variables & Nutritional Risk: The Predictive Power Using Binary Logit Model

Suraj Kushe Shekhar, Rehin K. R, Dr. P. T Raveendran

Abstract :

Nutrition is the provision, to living organisms, of the materials necessary (in the form of food) to support life. Many common health problems can be prevented or alleviated with a healthy nutritious diet. This paper uses a binary logistic regression to predict the nutritional risk of 100 consumers using ‘age’ and ‘sex’ as the predictors. A full model test against a constant only model indicted that the result was statistically significant, with the predictors as a group clearly distinguishing between nutritional risk groups and nutritional unrisk groups. Nagelkerke’s R2 of .943 indicated that there existed a strong relationship between the prediction and the grouping. The overall prediction success rate was 98% with over 98.7% for nutritional risk respondents and 95.2% for nutritional unrisk respondents. The Wald statistics revealed that age of the respondent contributed significantly to the prediction (p=.012)