While onsite, the Litigation Insights team collects data that gives our clients an idea of how each juror is leaning, etc. For instance, at key junctures in the presentations, jurors complete short questionnaires designed to track their individual case leanings over the course of the day. At each juncture, we calculate the average case leaning along with the mode, median and standard deviation. Most people will recall the definition of “average” from middle school math. Some will also recognize mode, the most frequently occurring value in a set of numbers, and median, the middle value of a particular set of numbers. However, standard deviation tends to be a less familiar value.
Standard deviation is a measure of dispersion illustrating the extent to which all leanings vary from the average or, in other words, how spread out the jurors’ individual leanings are. A low standard deviation indicates that jurors’ leanings tend to be very close to the average; a high standard deviation indicates that jurors’ leanings are spread out over a large range of values.
Calculating the standard deviation of a set of numbers is a somewhat complicated process that is beyond the scope of this article, but it can be an informative statistic. In our research exercises, jurors’ leanings are generally gathered with a seven-point scale in which 1.00 = strongly favor the defense and 7.00 = strongly favor the plaintiff. Knowing that the average leaning at a particular juncture is, say 2.13 is informative, but it tells you nothing about the distribution of those leanings (how spread out they might be along the seven-point scale). In theory, it is mathematically possible for two groups to have the same average leaning even though the extent to which the leanings are spread out within each group is drastically different. In one group, all jurors might have generally agreed in their stated leaning; in the other, a few very strong plaintiff-leaning jurors might have skewed the average.
In this example, and most other cases, knowing the standard deviation offers a richer understanding of the data and helps to gauge the persuasiveness of arguments by understanding the spread of jurors’ leanings.
By: John Wilinski, M.A. – Consultant