Data, central tendency, and variation

Having reviewed the concepts of study design we now turn our attention to data. We are interested in various questions relating to data, such as What are data How might we classify different types of data How are data used to answer questions arising during clinical trials This last question is, perhaps, the most important one for this book. We start to answer it first in conceptual terms before turning our attention to more specific points. 

---

Statistical process control methods may be used to demonstrate that a process had been validated (i.e., is in a state of control). The control chart method of analysis and presentation of data may for instance be used to document the variations that occur in the central tendency and dispersion of a set of observations relating to a specific quality characteristic. 

The data we collect are characterized by their central tendency (where the values are clustered), and their spread (the variation of individual values around the central value). Central tendency is reported by stating the mean or median. The range, standard deviation, or variance may be used to report the data s spread. Data also are characterized by their errors, which include determinate errors... 

However, using the actual time measurements (Exhibit 37.2), we can identify where the central tendency of the data lies (as measured by the mean or median), how much variation is present in the data (range or standard deviation), and the shape of the data distribution (bellshaped with most data in the center ). With these parameters, we can better describe the data and predict the impact of longterm shifts. 

Summary statistics are of particular importance when it comes to describing quantitative data. Four features of the data can be described, namely central tendency, variation, symmetry and shape. These will now be considered in turn. 

---