Understanding Sample Size Determination in Nursing Research

被引:11
作者
Hayat, Matthew J. [1 ]
机构
[1] Rutgers State Univ, Coll Nursing, Newark, NJ 07102 USA
关键词
hypothesis testing; precision estimation; power analysis; sample size; STATISTICAL POWER; GUIDELINES; PRECISION; ETHICS; NEED;
D O I
10.1177/0193945913482052
中图分类号
R47 [护理学];
学科分类号
1011 ;
摘要
Sample size determination is a natural consideration in the planning stages of most research studies. The purpose of this work is to provide an overview of modern methods of sample size determination and describe some of the challenges to be aware of and pitfalls to avoid in applying these various methods. Although sample size can be determined in many ways, the most commonly used approach has relied on classical hypothesis-based methods of power analysis. Several challenges often arise with traditional power analysis. For example, the statistical methods used in a power analysis may not adequately address the complexities of the data collected in a research study. The American Psychological Association currently accepts and endorses the use of two methods, power analysis and precision estimation, for sample size determination. Precision estimation is a viable alternative to the traditional power analysis approach. Recommendations for deciding on an approach are provided.
引用
收藏
页码:943 / 956
页数:14
相关论文
共 40 条
[1]  
American Psychological Association, 2010, Publication manual of the American Psychological Association, V6th
[2]  
[Anonymous], JALT TESTING EVALUAT
[3]  
Bacchetti P, 2005, AM J EPIDEMIOL, V161, P105, DOI 10.1093/aje/kwi014
[4]   Current sample size conventions: Flaws, harms, and alternatives [J].
Bacchetti, Peter .
BMC MEDICINE, 2010, 8
[5]   Effect size estimation: Methods and examples [J].
Berben, Lut ;
Sereika, Susan M. ;
Engberg, Sandra .
INTERNATIONAL JOURNAL OF NURSING STUDIES, 2012, 49 (08) :1039-1047
[6]   Writing a grant proposal - Part 2 - Research methods - Part 2 [J].
Bliss, DZ ;
Savik, K .
JOURNAL OF WOUND OSTOMY AND CONTINENCE NURSING, 2005, 32 (04) :226-229
[7]   Sample size requirements for estimating Pearson, Kendall and Spearman correlations [J].
Bonett, DG ;
Wright, TA .
PSYCHOMETRIKA, 2000, 65 (01) :23-28
[8]  
COBB EB, 1985, NURS RES, V34, P386
[10]  
Cohen J., 1988, Statistical power analysis for the behavioral sciences, VSecond