Category: Writing research papers. These pages discuss some of the issues that you need to consider when writing about a scientific or medical topic. Articles are arranged by date with the most recent entries at the top. You can find the theme and closely related categories and other resources at the bottom of this page.

Stats: Calculating statistics on whole numbers (April 4, 2008). Dear Professor Mean, I have some data that has a resolution of 1, meaning that these are whole numbers only and no decimals. When I calculate the mean and standard deviation, should I report the actual value or should I round it?

Stats: Presenting unadjusted and adjusted estimates side by side (March 24, 2008). Someone on the Medstats discussion group asked about reporting the analysis of a model without adjustment for covariates along with the analysis adjusted for covariates. What is the purpose of reporting the unadjusted analysis?

Stats: Open-access (OA) journals and their impact on research and the practice of medicine. This talk will cover the following topics: What is open-access (OA)? What are the historical antecedents to OA? What are the costs and benefits of OA? How you can help promote OA?

Stats: Open Access Journals, part 2 (October 14, 2007). I'm giving a talk at the Grand Rounds for CMH on Thursday, October 18. I'm using PowerPoint for this talk, and I have a version in web format that skips the images but provides more content. Here are some resources I probably will not use in my talk.

Stats: Seminar on Open Access Journals (October 5, 2007). I was inspired by a talk by Jim Pitman, President of the IMS, at the Joint Statistical Meetings in August, "Open Access to Professional Information" so when an opportunity arose for me to give a talk at our local Grand Rounds, I suggested a similar talk with the title "Open Access Publication and its impact on research and the practice of medicine."

Stats: Seven different formulas for the odds ratio (June 14, 2007). I received an interesting email recently. Someone was studying the relationship between firearm suicides and veterans to answer the question: "Are veterans more likely to commit suicide with a firearm than non-veterans?" Then this person proceeded to find seven different formulas for the odds ratio and tried all of them. How I wish more people were this adventurous! Here are the results.

Stats: Another open site closes (May 23, 2005). I often link to interesting resources on the web, and it is always distressing to find that content which had been available freely is now available only through subscription or through membership in a professional society. This breaks all the links I have on my web pages and there is no way to fix these links. When you are providing educational examples to a broad audience, you cannot assume that most of your readers belong to a particular scientific or medical society or that they subscribe to a particular journal or magazine.

Stats: Public access to publications from NIH-funded research (February 15, 2005). The NIH is now requesting publication in PubMed Central of research publications that is supported in whole or in part by NIH grants. The authors can designate a time delay between the appearance of the publication in the journal itself and when the PubMed Central article is available.

Stats: Free Full Text on the Web (August 24, 2004). As I mention at the top of the weblog, I preferentially try to cite medical literature where there is free full text available on the web. There are several journals who make their full text freely available.

Stats: Data is/are (November 26, 2003). Dear Professor Mean, Should I write "data is" or "data are"?

Stats: Displaying tables of percentages (November 6, 2002). Dear Professor Mean, My colleagues and I argue over the most appropriate way for displaying tables of percentages. Must the row or column always add to 100%? Also, in cases where it is difficult to know which variable is dependent, how does one decide the best way to present the results? -- Garrulous Gail

Stats: E notation (September 3, 1999). Dear Professor Mean: In my regression output, I saw that following value: -2.384E-03. What does this E notation mean?

Theme and closely related categories:

• Theme: Disseminating research results
• Category: Grant writing
• Category: Post hoc power
• Category: Scientific presentations and publications

Other resources:

• 10 Big Myths about copyright explained Excerpt: Note that this is an essay about copyright myths. It assumes you know at least what copyright is -- basically the legal exclusive right of the author of a creative work to control the copying of that work.
• Data inconsistencies in abstracts of articles in Clinical Chemistry. Description: A review of 87 articles published in Clinical Chemistry from January to June 2000 noted that 20 articles (23%) contained data in the abstract that were inconsistent with the main article or entirely missing from the main article. Some discrepancies were minor, but many were not.
• The effect of Web 2.0 on the future of medical practice and education. Description: Recent changes on the web that make it more interactive (collectively referred to as Web 2.0) have a potentially large impact on medicine. This article summarizes developments like Really Simple Syndication, blogs, wikis, and podcasts and their impact on heath care practice and education.
• Journal Info. Description: If you are looking for a journal in a specific area, perhaps to publish in, then this site is for you. It lists over 18,000 journals divided into broad classes such as History, Law, and Medicine. The Medicine category is further divided into areas like Dentistry, Hematology, and Oncology. This website was last verified on 2007-07-09. URL: jinfo.lub.lu.se/
• Reporting Non Significant Results: Summary. Description: Dr. Kornbrot discusses the research papers which present negative results. Adequate documentation including a power calculation and confidence interval are important. This website was last verified on 2007-11-29. URL: web.mac.com/kornbrot/iweb/KornbrotNonSignificantSummary.htm
• CONSORT for Reporting Randomized Controlled Trials in Journal and Conference Abstracts: Explanation and Elaboration Description: This article describes the type of information that any abstract describing a randomized clinical trial should contain.
• Scientific Papers and Presentations (PDF) Excerpt: "Scientific communication is essential for helping us to use and take care of this earth. Researchers who discover the wonders of science must tell someone about their findings in clear, complete, and concise terms. To add to the pool of scientific knowledge, scientists must synthesize available information with what they discover. If a scientist garbles words or leaves out important points, messages become unclear, and the progress of science suffers."

[Return to full topic list] [Read current weblog entries]

This webpage was written by Steve Simon on 2007-06-14, edited by Steve Simon, and was last modified on 2008-07-14. Send feedback to ssimon at cmh dot edu or click on the email link at the top of the page.