Month: September 2023

Week 3 – Friday

I went through what a T test is. Essentially, it is a measure of how two different samples differ from each other when it comes to the mean and when the source is common. Now if that is the case, I can also implement T test to use Alaska as the main source and then compare obesity percentage and inactivity percentage and possibly create a hypothesis. Still in the works…

Week 3 – Wednesday

Coming to p – values, it is a measure of how likely it is that the observed data would have occurred by random chance. And since it is intimately related to hypothesis testing, it could also be an indicator of a null hypothesis. Returning to diabetes data, I believe starting with an assumption regarding diabetes and a specific state or county could point to something significant. More to follow…

Week 3 – Monday

So far, I have had an overview of regression analysis and its three kinds – linear, multiple linear and non linear regression, the difference between both being the number of independent variables. Also found a little bit of clarity regarding heteroskedasticity. Since it describes the amount of residuals in a model, it would be interesting to observe once the diabetes data is analysed…..

Week 1

So far I have had a look through statistics fundamentals such as distributions, sampling, estimations, hypothesis testing etc. I found out that when there are extreme values or outliers in any data, a statistician/mathematician may need to use different statistical methods that can take deviations into account. Also had a brief overview of the Breusch-Pagan test.