Question

1. For the following scenario, please identify the most appropriate statistical method to use. Describe why it is the most appropriate.

A population-based case-control study was performed to assess the association between diabetes mellitus history and breast cancer in Hispanic women.  Breast cancer cases were identified through state cancer registries. Age- and ethnicity-matched controls were selected from commercial mailing lists and driver’s license and Social Security records.  The goal of the statistical analysis was to determine whether there was a statistically significant association between diabetes and breast cancer, after adjustment for age, body mass index at age 15 years, and parity.

Answer 1

Statistical tests to use: T-test, Chi-square test, logistic regression

Why and How :

1. We need to understand the factors causing cancer and diabetes are the same, so for this, we have data of cancer patients and we need to asses if various factors responsible for this cancer are different among patients who have diabetics and not having diabetics. This can be done using t-test and chi-square test. As these tests tell us if two groups are significantly different or not.

2. For assessing the association between cancer and diabetics ods need to be calculated and this can be done by logistic regression