General Information
| Student: |
Jacqueline Zawada |
| Office: |
CoRE 450 |
| School: |
University of Notre Dame |
| E-mail: |
jzawada@nd.edu |
| Project: |
Statistical Inference |
Project Description
In quantitative sciences p-values are largely used to determine statistical significance. Ron Wasserstein, the ASA’s executive director said, “Well-reasoned statistical arguments contain much more than the value of a single number and whether that number exceeds an arbitrary threshold. The ASA statement is intended to steer research into a ‘post p-value era’” Operating off this claim, the goal of this project is to understand the effectiveness of p-values. To do this we will survey recent clinical results to compare reproducibility of results given by p-values as compared with other statistical summaries.
Weekly Log
- Week 1:
- I arrived on Tuesday night to campus and settled into the apartment and met my room mates. On Wednesday morning we had breakfast as a group, which was the first time we were able to meet everyone, and then we went through an orientation. On Wednesday afternoon I was able to meet with my mentor, Dr. Kolassa, to begin discussing our work. From my discussion with him and some supplemental readings he gave me I got an overview of what we would be working on over the summer. For the first few weeks I am going to gather data from clinical trials including things like the p-value, confidence interval, trial details, and many more statistics. I enjoyed getting to know the other members in the DIMACS REU program as well as getting to become more familiar with my project.
Week 2:
I have been meeting with Dr. Kolassa for about 20 minutes every day to refine our research question and go over some of the more specific questions I had. He introduced me to the FDA websites that contain all of the clinical trial information that we will use to gather the statistics we will need to answer our research question. We discussed the different options I had for ways to organize the data as I go over all the clinical trials. We opted to collect data in the order they were approved from newest to oldest rather than gathering a random sample. We did this because drug labeling changes overtime, thus it would not be relevant to compare labels that were approved decades apart. We are using clinical trials that are randomized, controlled, and have a pair of studies. I am collecting all the data in an excel spreadsheet, separating them between study one and study two. To be sure that it will be as useful as possible in our analysis of the data I am making notes of what the primary or co-primary endpoints for the study were and how it was measured. I mainly spent this week getting more familiar with how to read and comprehend the clinical trial information and getting the spreadsheet set up.
Week 3:
describe week 3
Week 4:
describe week 4
Week 5:
describe week 5
Week 6:
describe week 6
Week 7:
describe week 7
Week 8:
describe week 8
Week 9:
describe week 9
References
insert any References
Presentations
Additional Information
