This exercise demonstrates statistical analysis of a sample of 130 human temperature readings to explore and explain normality and distribution of temperature values as relating to the generally accepted average of 98.6 degrees.
130 records of human temperatures and genders is given in CSV format.
Using SciPy and Seaborn, statistical inferences are drawn from the data. Cumulative Distribution Functions and Probability Distribution Functions are used to evaluate conformity to normal distribution, and subsamples by gender. T and Z testing provides p values that are used to evaluate hypotheses about the data. Seaborn is used to explore the data and supply occasional visual aids.
The techniques in this exercise are the foundation of basic statistical analysis and will no doubt continue to serve me as a Data Scientist. Previously when I explored the data visually in my first capstone project, I wondered if my charts and graphs were relevant. Now I'm excited to bring statistical relevance to my exploration. My only disappointment is with Springboard's lack of material on this subject. Beyond the DataCamp resources, I would recommend the following to anyone interested in learning this material: