Multiple Regression Analysis of Basal Metabolic Rate Using Dataset of 50 Adults at Federal Medical Center, Otuoke Outreach
Sylva Ligeiaziba
Department of Statistics, Bayelsa Medical University, Yenagoa, Nigeria.
Kubugha Wilcox Bunonyo *
Department of Mathematics and Statistics, Federal University Otuoke, Yenagoa, Nigeria.
Jason Biobaragha Goldie
Department of Biochemistry, Bayelsa State Polytechnic, Yenagoa, Nigeria.
*Author to whom correspondence should be addressed.
Abstract
This data analysis aimed at investigating Basal Metabolic Rate (BMR) of patients around Otuoke region, in Ogbia Local Government Area, and the data were collated at Federal Medical Centre, Otuoke Outreach. The data collated involving 50 patients, of which, 25 are males and 25 female volunteers of different ages. The variables involved in this analysis include age, gender and basal metabolic index, using SPSS version 25. Descriptive analysis was carried out to summarize the data in terms of mean and standard deviation of the gender and age. Biserial correlation was carried out on gender, age and BMR, and Cohen standard was done to investigate the strength of the relationship between the variables. The results of the analysis showed a negative correlation between gender and BMR with a correlation coefficient of -0.70, indicating a large effect size. In addition, it is seen that the linear regression model is significant, F(2,47) = 25.09, p<0.001, and Rsq = 0.52, indicating 52% variance in BMR. The result goes further to reveal that a unit increase in age doesn’t cause an effect on BMR. However, the female category can significantly predict BMR, B = -267.10, t(47) = -7.06, p<0.001. Based on this sample, this suggests that moving from the Male to Female category of Gender will decrease the mean value of BMR by 267.10 units on average.
Keywords: Basal metabolic rate, multiple regressions, age, gender.