TABLE OF CONTENTS Comparative studies are carried out routinely in the analytical laboratory in method development, in troubleshooting and as part of method validation exercises. They are initiated in response to questions like 'would the assay be more stable or would the recovery rate be better if the HPLC column temperature were controlled?' A comparative study might involve several measurements of a test material with and without column temperature control, followed by a statistical comparison of the test results. Other examples might involve comparison of the results produced by two analysts, two instruments, or two laboratories, for the same analysis.
In this chapter the issues involved in the design and analysis of simple comparative studies, i.e., ones designed to investigate the impact of changing a single system parameter, will be discussed in some detail. Studies involving changes to many system parameters will be considered in Chapters 5 and 7. The analysis of the resulting data typically involves formal comparison of the means and standard deviations of the two sets of test results, using statistical significance tests and confidence intervals. Design aspects, such as sample size determination, pairing, randomization 'of the study sequence and ensuring that the replication scheme is appropriate to the study objectives, will also be discussed in this chapter.
One stage in a HPLC method development programme involved a study of the effect of mobile phase composition on the percentage recovery of the nominal level of the active ingredients of pharmaceutical products. Two...
