A Series on Statistics and Science
Take a few minutes to answer the following science question:
Two scientists want to know if a certain drug is effective against high blood pressure. The first scientist wants to give the drug to 1,000 people with high blood pressure and see how many of them get better. The second scientist wants to give the drug to 500 people with high blood pressure and a placebo to another 500 people with the same condition to see how many in both groups improve. Which researcher is the better scientist?
The correct answer is the scientist that gave 500 people a placebo. Unfortunately, out of 1,864 participants surveyed, only 42 percent gave the correct answer. Even more troubling is that only 25 percent of the participants were able to adequately describe the meaning of the term “scientific study.” According to the National Science Foundation, "understanding how ideas are investigated and analyzed can be valuable for staying abreast of important issues, participating in the political process, and assessing the validity of other types of information" (visit the NSF website
for more information).
Members of SAF's Forest Science and Technology Board (FSTB) are confident that answers from well trained foresters will exceed the percentages reported above for the general public. Even so, the FSTB is concerned that training and knowledge of statistics is declining. As foresters, we sometimes make decisions that are based more on tradition than on results that have been analyzed statistically. In many cases, the research to support a management technique simply does not exist. Foresters know that bad decisions (based on inadequate information or faulty analysis) can be costly with unusually long-lasting consequences. For this reason, when new findings are reported, it is important to understand if the statistics reported were used properly.
The following essays comprise a series of essays on statistics and the scientific method. Hopefully, these essays will (1) improve the general understanding of statistics, and (2) improve the overall ability of foresters to assess the validity of new information.
Note: the opinions of the author in this and future essays may not necessarily represent the views of either SAF or the FSTB.
1.) Are My Seedlings Stunted?
2.) Four Types of Probabilities
3.) No Replication
4.) Computer Packages and Statistical Analyses
5.) Pseudoreplication - part 1
6.) Two Favorite Statistical References
7.) Means and Variation
8.) Confidence Intervals: The Average is Just Along for the Ride
9). The Pitfalls of False Positives
10) Hypothesis Testing