Selecting a sample size for studies with repeated measures

BMC Medical Research Methodology

Keith E Muller²  Deborah H Glueck³  Henrietta L Logan¹  Yi Guo² 

[1] Department of Community Dentistry and Behavioral Science, College of Dentistry, University of Florida, Gainesville, FL, USA;Southeast Center for Research to Reduce Disparities in Oral Health, University of Florida, Gainesville, FL, USA;Department of Biostatistics and Informatics, Colorado School of Public Health, University of Colorado Denver, Aurora, CO, USA

关键词: Interaction;    Repeated measures;    Sample size selection;   

Others  :  1092106
DOI  :  10.1186/1471-2288-13-100

 received in 2013-04-04, accepted in 2013-07-29,  发布年份 2013

【 摘 要 】

Many researchers favor repeated measures designs because they allow the detection of within-person change over time and typically have higher statistical power than cross-sectional designs. However, the plethora of inputs needed for repeated measures designs can make sample size selection, a critical step in designing a successful study, difficult. Using a dental pain study as a driving example, we provide guidance for selecting an appropriate sample size for testing a time by treatment interaction for studies with repeated measures. We describe how to (1) gather the required inputs for the sample size calculation, (2) choose appropriate software to perform the calculation, and (3) address practical considerations such as missing data, multiple aims, and continuous covariates.

【 授权许可】

   
2013 Guo et al.; licensee BioMed Central Ltd.

【 图 表 】

Figure 1.

Figure 2.

Figure 3.

【 参考文献 】

• [1]Muller KE, Lavange LM, Ramey SL, Ramey CT: Power Calculations for General Linear Multivariate Models Including Repeated Measures Applications. J Am Stat Assoc 1992, 87(420):1209-1226.
• [2]Muller K, Stewart P: Sample size for linear mixed models. In Linear model theory: Univariate, multivariate and mixed models. New York, NY: Wiley; 2006:385-386.
• [3]Gurka MJ, Edwards LJ, Muller KE: Avoiding bias in mixed model inference for fixed effects. Stat Med 2011, 30(22):2696-2707.
• [4]Cheng J, Edwards LJ, Maldonado-Molina MM, Komro KA, Muller KE: Real longitudinal data analysis for real people: Building a good enough mixed model. Stat Med 2010, 29(4):504-520.
• [5]Muller KE, Edwards LJ, Simpson SL, Taylor DJ: Statistical tests with accurate size and power for balanced linear mixed models. Stat Med 2007, 26(19):3639-3660.
• [6]Johnson JL, Muller KE, Slaughter JC, Gurka MJ, Gribbin MJ, Simpson SL: POWERLIB: SAS/IML Software for Computing Power in Multivariate Linear Models. J Stat Softw 2009, 30(5):1-27.
• [7]Liu G, Liang KY: Sample size calculations for studies with correlated observations. Biometrics 1997, 53(3):937-947.
• [8]Simpson SL, Edwards LJ, Muller KE, Sen PK, Styner MA: A linear exponent AR(1) family of correlation structures. Stat Med 2010, 29(17):1825-1838.
• [9]Lenth RV: Some Practical Guidelines for Effective Sample Size Determination. Am Stat 2001, 55(3):187-193.
• [10]Raudenbush SW, Liu X: Statistical power and optimal design for multisite randomized trials. Psychol Methods 2000, 5(2):199-213.
• [11]Sampson AR: A tale of two regressions. J Am Stat Assoc 1974, 69(347):682-689.
• [12]Gatsonis C, Sampson AR: Multiple Correlation - Exact Power and Sample-Size Calculations. Psychol Bull 1989, 106(3):516-524.
• [13]Glueck DH, Muller KE: Adjusting power for a baseline covariate in linear models. Stat Med 2003, 22(16):2535-2551.
• [14]Logan H, Baron RS, Kohout F: Sensory focus as therapeutic treatments for acute pain. Psych Med 1995, 57(5):475-484.
• [15]Gedney JJ, Logan H: Memory for stress-associated acute pain. J Pain 2004, 5(2):83-91.
• [16]Logan HL, Gedney JJ: Sex differences in the long-term stability of forehead cold pressor pain. J Pain 2004, 5(7):406-412.
• [17]Logan HL, Gedney JJ, Sheffield D, Xiang YW, Starrenburg E: Stress influences the level of negative affectivity after forehead cold pressor pain. J Pain 2003, 4(9):520-529.
• [18]Gedney JJ, Logan H, Baron RS: Predictors of short-term and long-term memory of sensory and affective dimensions of pain. J Pain 2003, 4(2):47-55.
• [19]Logan HL, Baron RS, Keeley K, Law A, Stein S: Desired control and felt control as mediators of stress in a dental setting. Health Psychol 1991, 10(5):352-359.
• [20]Lu K, Luo X, Chen PY: Sample size estimation for repeated measures analysis in randomized clinical trials with missing data. Int J Biostat 2008, 4(1):Article 9.