Considerations in determining sample size for pilot studies

College of Nursing, University of Nebraska Medical Center, Lincoln Division, 1230 O Street, Suite 131, P.O. Box 880220, Lincoln, NE 68588-0220, USA.
Research in Nursing & Health (Impact Factor: 1.27). 04/2008; 31(2):180-91. DOI: 10.1002/nur.20247
Source: PubMed


There is little published guidance concerning how large a pilot study should be. General guidelines, for example using 10% of the sample required for a full study, may be inadequate for aims such as assessment of the adequacy of instrumentation or providing statistical estimates for a larger study. This article illustrates how confidence intervals constructed around a desired or anticipated value can help determine the sample size needed. Samples ranging in size from 10 to 40 per group are evaluated for their adequacy in providing estimates precise enough to meet a variety of possible aims. General sample size guidelines by type of aim are offered.

727 Reads
    • "Based on Cohen's recommendation [21], a total of 128 participants will be required for a full scale RCT of medium-sized effect with power = 0.8 and p = 0.05. For a feasibility study, using an upper bound of 40%, a total of 52 participants will be required [22]. As the intervention program for this study would be carried out over a period of three months and involve twice-weekly participation, attrition was expected. "
    [Show abstract] [Hide abstract]
    ABSTRACT: To determine the feasibility of a salutogenesis-based self-care program on quality of life, sense of coherence, activation and resilience among older community dwellers. This is a feasibility randomized controlled trial. Sixty-four older community-dwellers were recruited from a Singapore senior activity center and randomly assigned to intervention and control groups. The intervention group attended a 12-week Resource Enhancement and Activation Program. The outcomes were assessed with the Chinese versions of World Health Organization Quality of Life Scale, Sense of Coherence, Patient Activation Measure, and Connor-Davidson Resilience Scale. Process evaluation was conducted using focus groups with the intervention group. At the end of the program, the intervention group showed significant improvement in the Sense of Coherence scale and the psychological subscale of the WHO Quality of Life scale compared with the control group. Three themes emerged from the process evaluation: participation in the program, reflection on the experience, and improving the experience. A salutogenic self-care approach could be a potential health promotion strategy for older people. With improved sense of coherence and psychological aspect of quality of life, older people's self-care ability may improve, leading to better health and better quality of life. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.
    Patient Education and Counseling 08/2015; DOI:10.1016/j.pec.2015.08.003 · 2.20 Impact Factor
    • "The total sample consisted of 212 nursing students, 17 biology students, 44 sociology students, 47 law students, 84 business administration students, 28 engineering students, 23 shipping students, and 25 students enrolled in multimedia. The relatively large sample engaged in this study was additionally supported in the relevant literature of the current field in which it is recommended to incorporate large and diverse samples to minimize potential limitations , especially within the psychometric tests and retests of behavioral trend measures (Hertzog, 2008; Johanson & Brooks, 2010) and in particular of the LSI (Kayes, 2005). All participants were recruited from three big public universities in Greece and Cyprus. "
    [Show abstract] [Hide abstract]
    ABSTRACT: The nursing research on learning differences is currently expanding, suggesting the need for trustful measurements. This study aimed to adapt and cross-culturally validate the Learning Style Inventory. The first phase involved symmetrical translation and adaptation to the Greek target language. The second phase concerned the psychometric testing. Internal reliability showed satisfactory alpha values. Kappa coefficients supported the test-retest reliability, and paired t test correlations justified the stability. Factor analysis yielded 2 constructs fitted with theory. The internal validity was also evidenced. The nursing students' learning style profile was discussed within their educational field and cultural background. The inventory presented content and construct equivalence to original scales. Certain implications were drawn for nursing supporting the utility of learning styles' measurements.
    Journal of Nursing Measurement 08/2015; 23(2):88-111. DOI:10.1891/1061-3749.23.2.E88
  • Source
    • "A convenience sample of 40 individuals with HIV/ AIDS was enrolled. This sample size allowed for assessment of the methodology, acceptability of the intervention, and identifying problems with logistics and data-collection strategies (Hertzog, 2008). The sample size also ensured that at least 10 individuals in each cohort group (n = 20) would complete the feasibility study, even with an attrition rate of 50% (Gucciardi, DeMelo, Offenheim, Grace, & Steward, 2007). "

    07/2015; 2(3). DOI:10.1177/2373665815597231
Show more


727 Reads