Skip to main content

Table 2 Sample size requirements for power levels of 0.8 and 0.9 based on prior studies of Cooking with Kids

From: Fuel for Fun: a cluster-randomized controlled study of cooking skills, eating behaviors, and physical activity of 4th graders and their families

Measure Clinically relevant change Minimum sample size/groupa
1 - β = 0.8 1 - β = 0.9
Student attitude 2 50 66
Student self-efficacy 2 108 144
Student FV preference 3 127 170
Parent modeling 2 64 86
Parent self-efficacy 4 110 146
Parent FV availability 2 15 20
Parent eating competence 3 105 140
  1. aBased on repeated pre/post measures using standard deviations from previous research. For example, a total of 100 participants are needed in this two-treatment parallel-design study. The probability is 80 % that the study will detect a treatment difference in student attitude at a two-sided 0.05 significance level, if the true difference between treatments is 2 units. This is based on the assumption that the standard deviation of the response variable is 3.5
  2. website: http://hedwig.mgh.harvard.edu/sample_size/js/js_parallel_quant.html