A Review on the Use of Effect Size in Nursing Research

PURPOSE: The purpose of this study was to introduce the main concepts of statistical testing and effect size and to provide researchers in nursing science with guidance on how to calculate the effect size for the statistical analysis methods mainly used in nursing. METHODS: For t-test, analysis of variance, correlation analysis, regression analysis which are used frequently in nursing research, the generally accepted definitions of the effect size were explained. RESULTS: Some formulae for calculating the effect size are described with several examples in nursing research. Furthermore, the authors present the required minimum sample size for each example utilizing G*Power 3 software that is the most widely used program for calculating sample size. CONCLUSION: It is noted that statistical significance testing and effect size measurement serve different purposes, and the reliance on only one side may be misleading. Some practical guidelines are recommended for combining statistical significance testing and effect size measure in order to make more balanced decisions in quantitative analyses.

Development of Global Deterioration Scale Staging Algorithm

BACKGROUND: The Global Deterioration Scale (GDS) is a useful tool for staging dementia; each stage is described by specific characteristics. However, one should not rely on the presence or absence of a single symptom in determining the stage. There is a need for a systematic computerized program to enable untrained doctors to easily assess dementia. This study aimed to generate an algorithm to help stage dementia. METHODS: Items were drawn from each stage and sorted out into questions adequate for the caregiver and questions adequate for the patient. Subjects recruited were 50 years or older and had visited the neurologic and/or psychiatric clinic at any of the university affiliated hospitals with symptoms of memory impairment. Structured questionnaires with 20 questions were administered to the subject-informant dyads. Psychometricians or well-trained nurses then assessed the remaining 10 items and decided the overall stage. Classification tree analysis was accomplished by using SPSS Answer Tree 3.0 software. RESULTS: 182 subject-informant dyads were included in the analysis. The mean age was 74.5 years; 112 (61.5%) were female. Among the 30 predictors, the item 'get lost when travelling' was the most important predictor of GDS score (chi2=96.6, p=0.0000). The classification tree algorithm begins with the item 'get lost when travelling' and includes 13 predicting variables. The most probable GDS predicted scores are presented in the final nodes of the algorithm. Risk estimate, probability of misclassification in the developed model, was 35.2%. CONCLUSION: A classification tree algorithm for GDS staging was developed to narrow down the range of choices when staging cognitive impairment. The algorithm is yet to undergo validity and reliability tests.