Sample size calculation in epidemiological studies（流行病学研究的样本量计算）.pdfVIP

Gerontologija 2006; 7(4): 225–231 GERONTOLOGIJA Theory and practice Sample size calculation in epidemiological studies 1 1 2 V. Kasiulevičius , V. Šapoka , R. Filipavičiūtė 1 Vilnius University 2 Institute of Experimental and Clinical Medicine at Vilnius University Summary sample sizes, making the interpretation of negative results Sample-size determination is often an important difficult. Conducting a study with an inadequate sample step in planning an epidemiological study. There are size is not only futile, it is also unethical. Exposing pa- several approaches to determining sample size. It depends on tients to the risks inherent in a research is justifiable on- the type of the study. Descriptive, observational and randomized ly if there is a realistic possibility that the results will be- controlled studies have different formulas to calculate sample nefit those subjects, future subjects, or lead to substantial size. In this article, we discuss the formulas that can help to scientific progress. estimate sample size in an epidemiological trial. We present a How many individuals will I need to study? This ques- few examples from clinical practice, which may contribute to tion is commonly asked by a clinical investigator and ex- the understanding of this problem. poses one of many issues that are best to be settled before Keywords: sample size determination actually carrying out a study. Consultation with a statisti-