Introduction and Review of literature:
Recent lifestyles have made people less active resulting into obesity. Long sittings, lack of exercise and junk eating are a few of the causes of obesity. Isolated systolic hypertension is a silent killer among modern day community usually following obesity. In this disorder once the systolic blood pressure crosses 140 mark on the scale, the disease happens. In addition to obesity certain physiological conditions such as artery stiffness, heart disorders or overactive thyroids may also be considered the culprits of the disease.
Understanding the gradual changes that occur in our life styles which ultimately is reflected in our physical fitness we can predict the risk of developing systolic hypertension. In this study, an econometric analysis has been used to correlate the body mass index to predict the probability of disease occurrence.
Studies have been conducted in these respects where it a strong correlation among BMI and hypertension has been reported . Similarly, Resnicow et al. have studies the same relationships in school going childern and found that obesity and higher BMI contribute towards high systolic blood pressure in them. Increasing BMI with age has been reported to have strong trend in causing sever hypertension in both males and females . Concluding from these findings this study has been proposed to find out any significant relationship among local population. This will help us design social motivation compeigns for healt fitness of local population and to eleviate increasing incidences of this maniace.
Study Descriptions:
For these studies we selected a locality, populated approximately 70 thousand people between the age group of 40 years and above. We surveyed 10 different hospitals and other health facilities including psychological therapy centres in the area and collected data. Information regarding age, gender, weight, height and systolic blood pressure readings were collected and tabulatecd for further econometric analysis.
These data on general health indicatives including age, height and weight and systolic blood pressure of subject population are presented in Table 1. For econometric analysis, we selected 30 random patients of mixed ages and was subjected to multivariate regressional models.
Analysis of the data:
Before analysis, in order to calculate Body Mass Index (BMI) of the patients was calculated using the following formula:
BMI= Weight kg x 703Height (inches)^2
Data on general health indicatives of random patients in a local hospital
The data was subjected to multivariable corelation analysis using Gretl Software. Systolic blood pressure has been considered as fixed variable while age, weight and height and BMI were used as dynamic variables.
Summary statistics of the data
An other model had been tried but the results were insignificant hence not explained here (please refer to appendix A1).
Results:
In order to check the data reliability and general statistics standard statistical summary was generated. General summary statistics of the data is presented in Table 2. It mentions that mean blood pressure of the sample population was 141.47 ± 13.913, ranging from 123 to 168 mm of Hg on the scale (Table 2). BMI ranged from 18 to 32 with a mean value of 24.28 ± 3.17 (Table 2).
The data has been tested for normality and a Q-Q plot is presented in Figure 1. The data has been found normal as it lies along the normal curve in Q-Q plot (Figure 1).
Figure 1 Q-Q Plot showing data normality
The outcome from regression analysis is presented in Table 3. The results have represented that BMI is significantly correlated with high systolic blood pressure (F1, 28 = 10.85, p = 0.002) (Table 3). The high value for slope (85.019) depicts that a minor increase in BMI of the patient increases the chances of hypertension, exponentially.
Figure 2 presents a chart with actual and fitted values for blood pressure plotted against BMI of the sample population.
Model 7: OLS, using observations 1-30
Dependent variable: BP
Figure 2: Actual and fitted values of blood pressure against BMI
Conclusion
The findings in our study has clearly demonstrated that BMI of patients above 40 years of the age are very sensitive towards developing sever hypertension and anxiety. Due to their life styles if their weight increase resulting a slight rise in their BMI will put them on high risk of disease incidence. Therefore, as a next step we will be conducting a social motivation campaign to elaborate the importance of healthy life style among the local population and controlling general fitness, especially body weight.
Non-Technical Conclusion:
This exercise has serious applicability in the process of learning research methodologies especially understanding econometric assessments. The exercise has enabled me to find out underlying relationships of major issues using proper statistical models of econometrics. I can correlate various factors and variables to predict future events. I have tried using different regression models and techniques to find out exact relationship among independent and dependent variables. After comparison, I have been able to select the appropriate technique for this study.
Works Cited
F Tesfaye, NG Nawi, H Van Minh, P Byass, Y Berhane, R Bonita and S Wall. "Association between body mass index and blood pressure across three populations in Africa and Asia." Journal of Human Hypertension (2007): 28-37.
Humayun, A, A.S. Shah and R Sultana. "Relation of hypertension with body mass index and age in male and female population of Peshawar, Pakistan." Journal of Ayub Medical College, Abbottabad (2009): 63-65.
Resnicow K, Futterman R, Vaughan RD. "Body mass index as a predictor of systolic blood pressure in a multiracial sample of US schoolchildren." Ethinicity and Disease (1993): 351-361.
Appendix 1
Model 7: TSLS, using observations 1-30
Dependent variable: BP
Instrumented: BMI
Instruments: const Age
Coefficient std. error z p-value
Const 141.408 698.754 0.2024 0.8396
BMI 0.00242718 28.7946 8.429e-05 0.9999
Mean dependent var 141.4667 S.D. dependent var 13.91287
Sum squared resid 5610.195 S.E. of regression 14.15500
R-squared 0.279405 Adjusted R-squared 0.253669
F(1, 28) 7.11e-09 P-value(F) 0.999933
Log-likelihood −237.1708 Akaike criterion 478.3416
Schwarz criterion 481.1440 Hannan-Quinn 479.2381
Hausman test -
Null hypothesis: OLS estimates are consistent
Asymptotic test statistic: Chi-square(1) = 0.00968855
with p-value = 0.921591
Weak instrument test -
First-stage F-statistic (1, 28) = 0.0233625
Critical values for desired TSLS maximal size, when running
tests at a nominal 5% significance level:
size 10% 15% 20% 25%
value 16.38 8.96 6.66 5.53
Maximal size may exceed 25%
