NotesFAQContact Us
Collection
Advanced
Search Tips
ERIC Number: ED174338
Record Type: RIE
Publication Date: 1979-Apr
Pages: 14
Abstractor: N/A
Reference Count: 0
ISBN: N/A
ISSN: N/A
Issues in the Analysis of Data in Developmental Interventions.
Lieberman, Marcus
This paper illustrates the relevance and utility of non-parametric statistical tests, such as the Kolmogorov-Smirnov two sample test, for analysis of developmental phenomena. This statistic tests the null hypothesis that two samples have been drawn from the same population by comparing their whole distributions, rather than specific parameters and makes no assumptions about their shapes. This comparison allows one to test the assumption that the groups are similar on the pretest. The same test may be performed on post-test scores, or on the relative amount of change in each group's scores. Tables are provided which illustrate: (1) a comparison of a traditional analysis and a distribution analysis of change scores in an intervention study; (2) frequency distributions of changes in stage scores for social-cognitive measures by Loevinger, Kohlberg, and Selman; (3) an analysis of subjects who advance or regress over the length of a program; and (4) an analysis of change defined as showing reasoning characteristic of the next highest stage, not previously elicited. (Author/SS)
Publication Type: Reports - Research; Speeches/Meeting Papers
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Identifiers: Kolmogorov Smirnov Two Sample Test
Note: Paper presented at the Annual Meeting of the American Educational Research Association (San Francisco, California, April, 1979)