We aim to serve all faculty, fellows, residents, and students with research support needs in order to improve the quality and long-term success of scientific research. This page is meant to provide the epidemiology and biostatistics background to better prepare researchers to plan and conduct their own research studies as well as better prepare them for their collaborative work with our RISE team.
Biostatistics Training and Practice
Biostatistics information
This GraphPad guide examines general principles of statistical analyses, looks at how to conduct those analyses using the GraphPad statistical program Prism, and how to interpret results. See the Principles of Statistics page to review some important issues in statistics, and Guided Examples of Statistical Analyses page for examples of some common statistical analyses using Prism, including descriptive statistics, comparing two groups, and diagnostic tests.
Calculations/analysis practice
GraphPad Prism offers GraphPad Quick Calcs which can be used to view and become comfortable with the way in which data needs to be entered depending upon the statistical test. There are many other software options available, some of which are free for use. While using GraphPad Quick Calcs, choose the type of data and analysis you have or would like to run and follow the prompts for entering data and conducting your analysis.
Epidemiology and Study Design Info
Principles in Epidemiology
The CDC’s Principles of Epidemiology in Public Health Practice is a great resource to look through for a reminder of different types of research studies (observational, retrospective, quasi-experimental, intervention, prospective, etc.) as well as some of the calculations and biostatistics involved in determining and assessing descriptive statistics.
Public Health 101
The CDC also created a course series to review the sciences essential to public health practice, which includes introductions to public health, epidemiology, and public health informatics, among others. The information is available in several formats including video, PDF, PowerPoint, etc.
Clinical Trials
If you’d like to review or plan on becoming involved in clinical trials, please see clinicaltrials.gov. This site provides the current status of privately and publicly funded clinical studies. Further, many devices, biologics, etc. are required by law to be registered via clinical trials.gov.
Freely Available Datasets
Below are links to a few of the many publicly available datasets available online. These datasets are great to use as practice for becoming familiar with different types of data, cleaning data and conducting analyses, and can also be used to conduct secondary data analysis and present findings at conferences and/or submit manuscripts for publication. As these datasets are publicly available, it is very important to review the existing literature to ensure that your research is new and has not yet already been studied and published.
- The PhysioNet is a platform that includes many databases, including several large clinical data sets. You can use the search page to filter for the type of data you are looking for, e.g., by diagnosis, procedure, date, etc. Of note, data is available at different levels of access such as open, restricted, and credentialed. There are no fees associated with these levels however CITI training and Data Use Agreements may need to be submitted depending on the data and level of access being requested.
- The eICU Collaborative Research Database includes data from patients admitted to critical care units in 2014 and 2015. This database was prepared by MIT and the Philips Healthcare system. To access data, complete the required training course and submit a request for data access.
- The Medicare COVID-19 Vaccine PUF is a public use file that demonstrates how Medicare was utilized and the spending involved with the administration of the COVID-19 vaccine. This data covers all vaccinations that occurred between December 11, 2020 to December 31, 2022 and is updated regularly. There is also a geographic table available that contains demographic, spending, utilization and quality indicators for the Medicare fee-for-service population. Two versions of this data are available, one being state and county level while the other was at the hospital referral region level.
Research Bootcamp 2022
Below are recordings from our Spring 2022 Research Bootcamp: