« Music for Public Relations Measurement: The types of bias in your research. | Main | You Want to Write Better? Go Out and Have Some Fun! »

May 11, 2010


Feed You can follow this conversation by subscribing to the comment feed for this post.


"Very little if any research is accurate. Even the most mathematically precise research usually has a 10 per cent error rate or more."

Where does the 10% number come from?

Jim Macnamara

Quantitative researchers aim for 90 per cent probability as an accepted level of reliability in quant work. 95% is possible, but requires large samples. In content analysis, for example, intercoder reliability scores of 0.8 are considered very good (80% consistency). The point is that - even with rigorous methodology - there is deviation and error rates in research. Without rigorous methodology, well ...

John Ledingham

While I nderstand the purpose of this article, I nonetheless found it to be somewhat unsettling. The literary device of setting up a 'straw man" and then tearing it down is a time-honored way of attracting readers, but how does that justify comments like: “Two common misconceptions are that research is all about statistics and that research is accurate. Very little if any research is accurate.”

To whom do these "common misconceptions" refer? Certainly not those in leading agencies charged with providing insight and evaluation. I don't know anyone who shares this view ("research is all statistics"). In fact, I've more often enclountered the view that qualitative research by itself is sufficient for campaign planning, implementation and evaluation, also not true, obviously.

And, in response to a write-in..."Without rigorous methodology..." Point is, research is accurate when done properly, using appropriate qualitative and quantitative methods, and appropriate sample sizes.

With all appropriate apologies, I think a better approach would have been to point out what needs to be done to ensure accuracy and reliability.

I do respect the effort to make certain that research -- to be accurate -- must be conducted properly but the fact that it sometimes or even often isn't is not the fault of the research but of the person conducting the research.

Thank you for providing a mechanism for feedback.

John Ledinghgam, Ph.D.
School of Communication
Capital university
Columbus, Ohio

The comments to this entry are closed.

Get us every month as a free email newsletter:

  • Just type your address here and click GO
    For Email Marketing you can trust

New Every Morning at 7:30 am...

  • The Measurement Standard Daily Digest is an automatically compiled collection of public relations measurement-related posts from around the Web.

Great Minds on Measurement

  • Lawrence M. Krauss“I cannot stress often enough that what science is all about is not proving things to be true but proving them to be false.” --Lawrence M. Krauss

Become a Fan

Recent Blog Posts on Measurement