On this page:
Overview
The Boonshoft School of Medicine Strategic Plan includes the following Research Goal: “Advance the school's reputation for nationally recognized research.” The first Strategy for achieving this goal is to “Increase and advance our research portfolio.” One of the Planned Tactics for this Strategy is to “Increase faculty success in research grant processes.”
The Boonshoft School of Medicine Analytical Resources web page exists for the purpose of facilitating this tactic through “improving faculty skills in mixed methods research, epidemiology, and biostatistics.”
On this webpage, medical school researchers can find links to online tutorials and resources for analytical concepts and methods. This page exists to help faculty know what these areas are, why they are important, what the basic issues are and where to go for help.
Biostatistics
“Biostatistics is the branch of statistics responsible for the proper interpretation of scientific data generated in the biology, public health and other health sciences (i.e., the biomedical sciences). In these sciences, subjects (patients, mice, cells, etc.) exhibit considerable variation in their response to stimuli. This variation may be due to different treatments or it may be due to chance, measurement error, or other characteristics of the individual subjects.
“Biostatistics is particularly concerned with disentangling these different sources of variation. It seeks to distinguish between correlation and causation, and to make valid inferences from known samples about the populations from which they were drawn. (For example, do the results of treating patients with two therapies justify the conclusion that one treatment is better than the other?)”
(Source: Vanderbilt University School of Medicine Department of Biostatistics, accessed 11/12/14)
Topics
- Basic Statistics For Clinicians (a series of four free articles in CMAJ, 1995)
- Basic statistics for clinicians: 1. Hypothesis testing
- Basic statistics for clinicians: 2. Interpreting study results: confidence intervals
- Basic statistics for clinicians: 3. Assessing the effects of treatment: measures of association
- Basic statistics for clinicians: 4. Correlation and regression
- Sample size determination / Power
- Sample Size Estimation in Clinical Trial (introductory explanation)
- Java applets for power and sample size (Russel Lenth)
- OpenEpi: Free software
- PASS: Commercial software
- Clinical Trials
- Understanding Clinical Trial Design: A Tutorial for Research Advocates
- Sensitivity Analyses (how robust is a study to the assumptions and methods used?)
- CONSORT (Consolidated Standards of Reporting Trials)
- Survival Analysis in Clinical Trials: Past Developments and Future Directions (Fleming TR and DY Lin, Biometrics, 2000, 56(4):971-983)
- Questionnaire design
- Questionnaires in clinical trials: guidelines for optimal design and administration
- Questionnaire design (Cathy A. Jenkins, M.S., Vanderbilt University)
- Questionnaire design (Theresa A. Scott, M.S., Vanderbilt University)
- Randomization
- Definition of a randomized trial
- An Overview of Randomization and Minimization Programs for Randomized Clinical Trials (includes links to online randomizers)
- Response-Adaptive Randomization (RAR) in Clinical Trials (Feifang Hu)
- Minimization (a method of assigning subjects that minimizes differences between groups)
Online Resources
- Clinical Trials.gov
- Handbook of Biological Statistics
- Randomization
- Directory of randomisation software and services (by Martin Bland)
- Great list of online tools
- GraphPad QuickCalcs (Easy to use, but limited to assigning N subjects to 2-10 groups)
- Directory of randomisation software and services (by Martin Bland)
- CONSORT (Consolidated Standards of Reporting Trials)
Wright State University Resources
- Wright State University Statistical Consulting Center (SCC) (consulting, data management, data analysis, questionnaire design, etc.)
- Wright State University and Premier Health Clinical Trials Research Alliance (CTRA)
Books
- Clinical Trials
- Principles and Practice of Clinical Research, Third Edition (John I. Gallin and Frederick P Ognibene, editors)
- Fundamentals of Clinical Trials (Lawrence M. Friedman, Curt D. Furberg, and David L. DeMets)
- Clinical Trials: A Methodologic Perspective (Steven Piantadosi)
- Randomised Response-Adaptive Designs in Clinical Trials (Anthony C. Atkinson, Atanu Biswas)
- Introductory Applied Biostatistics (Ralph D'Agostino, Sr., Lisa Sullivan, and Alexa Beiser)
- Intuitive Biostatistics: A Nonmathematical Guide to Statistical Thinking (Harvey Motulsky)
- Modern Statistics for the Life Sciences (Alan Grafen and Rosie Hails)
- Experimental Design and Data Analysis for Biologists (Gerry P. Quinn and Michael J. Keough)
- Experimental Design for the Life Sciences (Graeme Ruxton and Nick Colegrave)
Statistical Software
- SAS, SPSS, STATA
- Learning SAS
- SAS Training & Books
- The Little SAS Book: A Primer (Lora Delwiche and Susan Slaughter)
- Learning SPSS
- Learning STATA
- Learning SAS
- R
- Freely available at http://www.r-project.org/
- Command line interface, not menu driven, so steeper learning curve
- Learning R
- Free online tutorial e-book
- Includes sample code for many tasks
- Elementary statistics with R (Chi Yau)
- RStudio: A nicer GUI for running R
- Other tutorials (some are more basic than others…)
- http://cran.r-project.org/doc/manuals/r-release/R-intro.html
- http://ww2.coastal.edu/kingw/statistics/R-tutorials/
- http://www.statmethods.net/
- http://heather.cs.ucdavis.edu/~matloff/r.html
- http://tryr.codeschool.com/
- http://www.cyclismo.org/tutorial/R/
- https://www.datacamp.com/courses/introduction-to-r
- Free online tutorial e-book
- Minitab: Easy to use
- JMP: Based on SAS, but much more user-friendly
- Mplus: Powerful for any kind of latent variable methods (factor analysis, SEM, mixture models, growth models, longitudinal data analysis, etc.)
- Web training and short-course materials available on their website
- PASS: Specifically for power and sample size calculations
- Free Statistical Software links
- Directory of randomisation software and services (by Martin Bland)
- Matlab: Has a “Statistics and Machine Learning Toolbox™”
- Java applets for power and sample size (Russel Lenth)
- Statistical Software Links (Free and reduced price) for faculty/staff by OnTheHub – SPSS, JMP, NCSS, StatSoft, Minitab
Epidemiology
“Epidemiology is the study of the distribution and determinants of health-related states or events (including disease), and the application of this study to the control of diseases and other health problems. Various methods can be used to carry out epidemiological investigations: surveillance and descriptive studies can be used to study distribution; analytical studies are used to study determinants.” (Source: World Health Organization, accessed 11/12/14)
Resources
- CDC Wonder
- “Wide-ranging Online Data for Epidemiologic Research -- an easy-to-use, menu-driven system that makes the information resources of the Centers for Disease Control and Prevention (CDC) available to public health professionals and the public at large. It provides access to a wide array of public health information.”
- Epiville
- Case studies
- World Health Organization
- STROBE (Strengthening the Reporting of Observational Trials in Epidemiology) website
- Similar to CONSORT, but for observations studies instead of clinical trials
- SEER
- Statistics and epidemiology online self-paced tutorials
- HealthData.gov
- A compilation of publicly available data
Books
Software
- Much of the biostatistics software [LINK] can be used for epidemiology
- OpenEpi
- “OpenEpi is free and open source software for epidemiologic statistics. It can be run from a web server or downloaded and run without a web connection.”
- Can run on a smartphone browser
Mixed Methods Research
Mixed methods research is “a research approach or methodology:
- focusing on research questions that call for real-life contextual understandings, multi-level perspectives, and cultural influences;
- employing rigorous quantitative research assessing magnitude and frequency of constructs and rigorous qualitative research exploring the meaning and understanding of constructs;
- utilizing multiple methods (e.g., intervention trials and in-depth interviews);
- intentionally integrating or combining these methods to draw on the strengths of each; and
- framing the investigation within philosophical and theoretical positions.”
(Source: National Institutes of Health, accessed 11/12/14)
Resources
- Linking Qualitative and Quantitative Methods: Integrating Cultural Factors into Public Health
- Carey JW, Qual Health Res 1993 3:298-318, DOI: 10.1177/104973239300300303
- Barriers to Integrating Quantitative and Qualitative Research
- Bryman A, Journal of Mixed Methods Research 2007 1(1):8-22, DOI: 10.1177/1558689806290531.
- Simultaneous and Sequential Qualitative Mixed Method Designs
- Morse JM, Qualitative Inquiry 2010 16(6) 483–491, DOI: 10.1177/1077800410364741
Software
- Includes both qualitative and quantitative analyses
- QDA Miner
- Contains statistical (SimStat) and text analysis (WordStat) software packages
- QDA Miner
- Qualitative data analysis
- NVivo
- For relatively small qualitative projects, NVivo is good (and cheaper than QDA); if you have more data and want easier integration with statistical method, QDA works better
- Atlas.ti
- Ethnograph
- MAXQDA
- QDAP
- Free, open-source
- NVivo
- Other software for analyzing data on cultural domains
- Anthropac
- Good for consensus analysis
- Anthropac