Biostats Research Poster

pdf

School

University of New Hampshire *

*We aren’t endorsed by this school

Course

528

Subject

Statistics

Date

Feb 20, 2024

Type

pdf

Pages

1

Uploaded by DukeNeutronSheep47

Report
Question: Is there a significant difference between glucose level and BMI in diabetics of certain ages? Results: In figure 1, you can see the means of the glucose levels and the means of the BMI in all three age categories. The graph supports that there is a difference between the levels, even if it is a small difference. Linear Regression- p value= 0.325 f stat= 11.626 f crit= 0.182 The p value is greater than 0.05 and the f stat value is greater than the f crit value. This supports that there is a difference in levels between the three ages. Factorial anova- (We used the interaction values because we are testing the correlation.) p value= 0.014 f stat= 15.233 f crit= 1.257 The p value is not greater than 0.05, however, the f stat value is greater than the f crit value. This still supports there being a difference in levels between the three ages. Hypothesis: There is a significant difference. Methods: Formed the research question that we could test. Stated our hypothesis. Put the data into an excel spreadsheet. Conducted two hypothesis tests, a factorial anova test, and a linear regression test. Used a histogram plot and a scatter plot to compare the mean data results. Found the mean, p value and f statistic to determine if our hypothesis was correct. Discussion: This study is relevant because with this data, we can predict whether people have diabetes or not when these specific parameters are observed. This could allow doctors to begin treatment before diagnosis. Introduction: This dataset is originally from the National Institute of Diabetes and Digestive and Kidney Diseases. This research was originally to predict based on diagnostic measurements whether a patient has diabetes. Several constraints were placed on the selection of these instances from a larger database. In particular, all patients here are females at least 21 years old of Pima Indian heritage. With this data, my group decided to take some of the parameters and statistically test the correlation between two parameters we found the most influential. Conclusion: In conclusion, with both the histogram and the scatter plot along with the two hypothesis tests, factorial anova and linear regression, we have proved our hypothesis correct. Yes, there is a significant difference between glucose levels and BMI levels in women of certain ages. Additionally, further research is needed to monitor these levels to see if the mean glucose and BMI levels of each age groups either gets larger or smaller over time. References: https://data.world/data-society/pima-indians-diabetes-database (Smith et al., 1998) https://medium.com/@SafakSS/pima-indians-diabetes-classification-project-ce4f234bafdf Diabetes In Pima Indian Women Caitlin Barton, Daryna Serediuk Fig 1 Fig 2 Teen Young Adult Adult
Discover more documents: Sign up today!
Unlock a world of knowledge! Explore tailored content for a richer learning experience. Here's what you'll get:
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help