Statistics efficacy data

Phase III Dmg samples are made available to select clinicians for use on large numbers of patients to obtain statistically significant data for safety and efficacy. 

JMP. An introduction to JMP teaches reviewers how to use JMP to review electronic data. Users learn how to use a variety of JMP functions to analyze electronic data, with a specific focus on adverse event, laboratory, exposure, and efficacy data. Basic functions of summary tables, graphs, statistical tests, and the formula calculator are covered. The course is taught in the computer lab with hands-on instruction. Prior completion of the NEDAT course or familiarity with electronic data sets or both are recommended. Although primarily geared toward the clinical reviewer, the course provides useful instruction for reviewers of all disciplines. 

The previous chapter discussed the (currently) relatively loosely defined statistical approaches to safety data collected in clinical trials. In contrast, there are widely accepted statistical methods for demonstrating efficacy in clinical trials. As has been noted several times in this book, if the study design and methodology have been appropriate and have led to the collection of optimum quality data, the statistical analysis and interpretation of efficacy data are relatively straightforward. The clinical (biological) interpretation of efficacy data is typically not quite as clear-cut, but there are widely accepted methodologies that are very useful in this realm too. Of particular importance here is the expert judgment of the clinicians who will review the statistical results with the statisticians and the rest of the study team. 

Two common statistical techniques that are typically used to analyze efficacy data in superiority trials are f-tests and ANOVA. In parallel group trials, the independent groups Mest and the independent groups ANOVA discussed in Chapter 7 would be used. Another important aspect of the statistical methodology employed in superiority trials, the use of CIs (confidence intervals) to estimate the clinical significance of a treatment effect, was discussed in Chapter 8. These discussions are not repeated here. Instead, some additional aspects of statistical methodology that are relevant to superiority trials are discussed. 

The clinical data section is probably the most important and most complicated section of an NDA. It is the part that provides the safety and efficacy data on the drug for its intended use. In the Guidelines for the Format and Content of the Clinical and Statistical Sections of an Application, FDA has outlined how it would like to see this section of the NDA organized. This outline is provided below. 

Efficacy data on patients from studies that are not adequate and well controlled need not be tabulated. Applicants should resist the temptation of combining uncontrolled with controlled trials because it strengthens the statistics of the data. Studies should be grouped by design, not outcome. 

Chapters 8-11 discuss clinical trials that are conducted later during the clinical development program. These chapters address both safety data and efficacy data. Throughout these chapters, each new statistical analysis taught is addressed in the following way ... 

Of ultimate importance are the full reports of the clinical studies in humans and their results. These data will be treated statistically for their validity. The number of studies for a specific compound or combination of compounds will vary with the type of drug being tested, as will the number of tests needed to appraise relative or absolute safety and to clearly demonstrate efficacy. The basic requirement is the proof of safety and efficacy of the product being submitted under the NDA system. A drug that does not contribute to therapy, such as a new antihistamine that does not demonstrate greater safety or efficacy, or both, compared with drugs already on the market, will have a difficult or impossible time achieving approval. 

Studies aimed at gathering feasibility and toxicity data on new treatments are usually referred to as phase I trials. Phase II trials are relatively small studies (typically with sample size less than or about 100 subjects) with the purpose of detecting preliminary evidence of efficacy and safety. Phase III trials are larger studies with enough statistical power to test in a conclusive way specific hypotheses about treatment effects. The term clinical trials is often broadly used to designate phase III trials. 

---