Statistical Analysis of Group Differences: Testing Normality and Associations in BMI and Glucose Level Data
Overview
This paper examines statistical methods for identifying differences between groups using the Framingham study dataset and SPSS analysis. The author tests assumptions of normal distribution across BMI categories and performs linear regression analysis to evaluate associations between age, BMI, and coronary heart disease prevalence.
What this coursework covers
- Testing for the Assumption of Normal Distribution - Shapiro-Wilk and Kolmogorov-Smirnov tests applied to baseline glucose levels across four BMI categories
- Analysis of Normality Results - Interpretation of significance values indicating normal and non-normal distributions by BMI group
- Performing Statistical Tests - Linear regression analysis examining association between age and prevalent coronary heart disease in normal BMI group
Preview
Testing to Find Differences Between Groups
Helena Lynch
MPH5509
Dr. Cash
Unit 4 Assignment
The t-test and NOVA materials provided helped in examining how to select a statistical test. Therefore, the SPSS and Framingham study data set was used to perform and interpret the statistical tests that provide answers to the following research questions.
Testing for The Assumption of Normal Distribution
The following is a test of nominal distribution of the data.
- BMI (Underweight<18.5)
Case Processing Summarya | ||||||
Cases | ||||||
Valid | Missing | Total | ||||
N | Percent | N | Percent | N | Percent | |
Baseline glucose level | 2 | 100.0% | 0 | 0.0% | 2 | 100.0% |
a. Body Max Index = Underweight <18.5 | ||||||
Tests of Normalitya | |||
Kolmogorov-Smirnovb | |||
Statistic | df | Sig. | |
Baseline glucose level | .260 | 2 | . |
a. Body Max Index = Underweight <18.5 | |||
b. Lilliefors Significance Correction | |||
- BMI ( Normal 18.5 -25))
Case Processing Summarya | ||||||
Cases | ||||||
Valid | Missing | Total | ||||
N | Percent | N | Percent | N | Percent | |
Baseline glucose level | 3 | 100.0% | 0 | 0.0% | 3 | 100.0% |
a. Body Max Index = Normal 18.5>25 | ||||||
Tests of Normalitya | ||||||
Kolmogorov-Smirnovb | Shapiro-Wilk | |||||
Statistic | df | Sig. | Statistic | df | Sig. | |
Baseline glucose level | .247 | 3 | . | .969 | 3 | .663 |
a. Body Max Index = Normal 18.5>25 | ||||||
b. Lilliefors Significance Correction | ||||||
- BMI Overweight 25-30)
Case Processing Summarya | ||||||
Cases | ||||||
Valid | Missing | Total | ||||
N | Percent | N | Percent | N | Percent | |
Baseline glucose level | 2 | 100.0% | 0 | 0.0% | 2 | 100.0% |
a. Body Max Index = Overweight 25-30 | ||||||
Tests of Normalitya | |||
Kolmogorov-Smirnovb | |||
Statistic | df | Sig. | |
Baseline glucose level | .260 | 2 | . |
a. Body Max Index = Overweight 25-30 | |||
b. Lilliefors Significance Correction | |||
- BMI Obese >30
Case Processing Summarya | ||||||
Cases | ||||||
Valid | Missing | Total | ||||
N | Percent | N | Percent | N | Percent | |
Baseline glucose level | 1 | 100.0% | 0 | 0.0% | 1 | 100.0% |
a. Body Max Index = Obese>30 | ||||||
From the data above, the Shapiro-wilk test is used to test the normal of the four sets of people categorized according to their BMI> therefore, for the underweight people with a BMI< 18.5, the sig.