ERIC Number: ED191855
Record Type: RIE
Publication Date: 1980-Apr
Reference Count: 0
Nonparametric Discrimination Based Upon Inverse Normal Scores and Rank Transformations.
Koffler, Stephen L.; Penfield, Douglas A.
Two nonparametric statistical methods, the inverse normal scores method and the rank order transformation, are compared for use in discriminant function analysis. The methods are compared for both normal and non-normal distributions. When the distributions are normal, the rank and inverse normal scores methods are effective substitutes for the linear discriminant function (LDF) and the quadratic discriminant function (QDF). When the populations are non-normal, the LDF methods based on the ranks or the inverse normal scores are more effective than the LDF or QDF methods based on the raw data. Finally, when the criterion sample sizes are unequal, the inverse normal scores approach is more desirable than the rank approach. When the criterion sample sizes are equal, either of the two procedures can be used. (Author/JKS)
Publication Type: Speeches/Meeting Papers; Reports - Research
Education Level: N/A
Authoring Institution: N/A
Identifiers: Inverse Normal Scores; Rank Order Transformation
Note: Paper presented at the Annual Meeting of the American Educational Research Association (64th, Boston, MA, April 7-11, 1980).