Statistical estimation using confidence intervals（统计使用置信区间估计）.pdfVIP

0894PP_ch06 15/3/02 11:02 am Page 135 6 Statistical estimation using confidence intervals In Chapter 2, the concept of the central nature and variability of data and the methods by which these two phenomena may be mathematically determined were described. As previously explained, one of the main purposes for calculating the central nature (e.g. the mean) and the vari- ability (e.g. the standard deviation) of a set of sample data is to gain an understanding of the corresponding population statistics. In other words, the mean (XK ) and standard deviation (s) of sample data are employed to estimate the true (population) mean and true (population) standard deviation. However, it is reasonable to ask, how reliable are the sample data at representing the population data? Is the sample data a good estimation of the population data? 6.1 The concept of confidence intervals After calculating the mean and standard deviation of a sample, as is the normal approach in the pharmaceutical and related sciences, we need to provide an indication of the reliability of the data. For example, in a clinical trial (N # 20 patients) the volume of urine produced after the administration of a new diuretic drug has been calculated as 5.2 1.9 L. In light of the small sample size, it is unreasonable to predict that the population mean and standard deviation will be identical to these observed sample values, as each sample will produce different mean and standard deviation values. Therefore, when reporting the mean of sample data it is good practice to pr