Using Mahalanobis Distance to Evaluate Recovery in Acute Stroke.

Objective: In the weeks immediately following a stroke, impairments across multiple cognitive domains are pervasive yet there is little literature that explores cognitive recovery during this period. This paper evaluates the use of Mahalanobis distance as a means of statistically evaluating cognitive change at the individual level.

Method: A small battery of standardized neuropsychological tests was administered on five or six occasions across a 2-week period to the participants recovering from a stroke and a non-stroke control group.

Discrepancy analysis and Australian norms for the Trail Making Test.

Objective: Discrepancy analyses refer to comparison methods that evaluate the relationship or differences between two measures in the same individual. A common type of discrepancy analysis involves the comparison of two trials within a measure, such as, Trails A and B of the Trail Making Test (TMT). The TMT is well-suited to this role as the two measures are highly correlated, assess similar underlying constructs, and most importantly demonstrate differential vulnerability to the impact of pathology.

How Small Is Big: Sample Size and Skewness.

Sample sizes of 50 have been cited as sufficient to obtain stable means and standard deviations in normative test data. The influence of skewness on this minimum number, however, has not been evaluated. Normative test data with varying levels of skewness were compiled for 12 measures from 7 tests collected as part of ongoing normative studies in Brisbane, Australia.