The role of statistics and statisticians

The fall of 1983 also saw the North Atlantic Treaty Organization host an Advanced Studies Institute in Cosenza, Italy, entitled Chemometrics Mathematics and Statistics in Chemistry. One hundred scientists—a most unusual collection of chemists, engineers, and statisticians from academia, industry, and government—representing a dozen countries assembled to discuss the role of sophisticated multivariate statistics in the daily routine of an analytical chemistry laboratory. 

This chapter will attempt to elucidate the roles of statisticians and how these roles affect the overall teamwork needed to guide a new drug successfully through investigational work and to market. This chapter is not intended to provide instruction on basic or evolving statistical methods or concepts. For this kind of background information, the reader will find sources referenced in the bibliography at the end of the chapter (1,2,4). 

SAS has always had and will maintain a central role in the data management, analysis, and reporting of clinical trial data. Because of the strong suite of SAS statistical procedures and the power of Base SAS programming, SAS remains a favorite of statisticians for the analysis of clinical trial data. Several companies have built their clinical trial data management and statistical analysis systems entirely with SAS software. More recently, SAS has offered SAS Drug Development as an industry solution that provides a comprehensive clinical trial analysis and reporting environment compliant with 21 CRF-Part 11. 

The statistician s role is to determine whether a disease rate of 1 in 50 is truly distinguishable from a disease rate of 0 in 50. The statistician will point out that there is only a very small chance (and chance, or probability, is what the statistician calculates) that this observed difference between the two groups of animals is actually due to the presence of the chemical in the diet of one of the groups, and its absence in the other. In fact, the statistician will state that not until the difference in disease rate is 0/50 versus 5/50 is there reasonable probability that the observed difference is actually due to the chemical. In other words, a difference in disease rate of at least 10% (0/50 versus 5/50) is necessary to achieve what is called a statistically significant effect. The difference necessary to achieve statistical significance will... 

With greater sophistication of methods of data acquisition, intuition can play a less important role, and a bayesian philosophical approach becomes more important. In contrast to the classical approach to statistics, which is concerned with the distribution of possible measured values about a unique true value, the bayesian approach is concerned with the distribution of possible true values about the measured value at hand—a concept often greeted with hostility by traditional statisticians. 

The topics are intended to be provocative, but there is no intent to criticize the profession or those individuals who diligently play a critical role in the industry today. As statisticians take up the challenges we face today, an expanded role for statisticians can evolve. This should lead to the ability to take full advantage of the statistical perspective, one that has already helped lead to important advancements in public health and can address the challenges of the future. 

Collection. Once the data factors have been defined, statisticians must collect them from the population being studied. Experimental design also plays a role in this step. Statistical data collection must be thorough and must follow the rules of the study. For example, if a survey is mailed to one thousand high school graduates and only three respond, more data must be collected before the survey s findings can be considered valid. Statisticians also must ensure that collected data are accurate by finding a way to check the reliability of answers. 

---