To Transform or Not Transform Skewed Data for Psychometric Analysis
- 1 January 2004
- journal article
- review article
- Published by Ovid Technologies (Wolters Kluwer Health) in Nursing Research
- Vol. 53 (1), 67-71
- https://doi.org/10.1097/00006199-200401000-00011
Abstract
Although data transformation is generally recommended, its benefits of have not been widely studied. This report reviews evidence regarding the costs and benefits of transforming skewed data with respect to two statistics commonly used in psychometric analyses: the Cronbach alpha and the Pearson product-moment correlation. Data describing 758 immigrants from the former Soviet Union who completed a Russian language version of the Symptom Checklist-90-Revised (SCL-90-R) were used to demonstrate the effects of transformation. More than half (55%) of the SCL-90-R items had a problematic skew. The Cronbach alpha and the Pearson product-moment correlation were calculated for original item responses as well as for square root and log transformations of these responses. Sample size (full, 30%, 20%), transformation type (square root or log transformation), and transformation method (sum items first and then transform, transform items first and then sum) were manipulated to evaluate the relevance of these factors to transformation. Regardless of sample size, neither the Cronbach alpha nor the Pearson product-moment correlation showed a difference between original and transformed data, with one exception. When items were transformed first before being summed in the calculation of the Pearson product-moment correlation, inconsistently higher (+.05) or slightly lower values (-.01) were observed relative to those created with the nontransformed data across the different sample sizes. These findings suggest that data transformation is not always needed or advisable when the Cronbach alpha or Pearson product-moment correlation is calculated for instruments with skewed item responses.Keywords
This publication has 14 references indexed in Scilit:
- Infant Sleep Problems and Postnatal Depression: A Community-Based StudyPEDIATRICS, 2001
- Heterogeneity of variance in clinical data.Journal of Consulting and Clinical Psychology, 2000
- The Effects of Heterogeneous Item Distributions on ReliabilityApplied Measurement in Education, 1999
- Predicting Psychological Distress Among Former Soviet ImmigrantsInternational Journal of Social Psychiatry, 1998
- Development and psychometric evaluation of the Demands of Immigration Scale.Journal of Nursing Measurement, 1998
- The Effect of Skew on the Magnitude of Product-Moment CorrelationsThe Journal of General Psychology, 1995
- Focus on psychometrics. An Overview of Data TransformationResearch in Nursing & Health, 1994
- Skew reduces test-retest reliability.Journal of Applied Psychology, 1994
- Power of the F test with skewed data: Should one transform or not?Psychological Bulletin, 1982
- Robustness?British Journal of Mathematical and Statistical Psychology, 1978