In a recent article, Professor Marvin Zelen (1983) finds it "difficult to make a strong case to classify biostatistics as a discipline." He proposes the term biostatistical science and refers to it as "the applications of statistics, probability and computing and mathematics to the life sciences ... ." While Professor Zelen is correct in his description of biostatistical science, I do not share his difficulty in classifying biostatistics as a discipline. Admittedly, there is nothing sacred in the word discipline; we can all work contentedly in biostatistics whether or not it is classified as such. What surprises me is the extent of the difference that seems to exist between what is described in Professor Zelen's article and what I understand to be biostatistics. According to the article, all a biostatistician does is application. He relies on statisticians to develop statistical theory and methods, on probabilists for probabilistic concepts, and on mathematicians for mathematics. A biostatistician need only look up appropriate formulas and ask the computer to do the computations. If this were true, then I could understand Professor Zelen's difficulty. What is biostatistics? As I understand it, biostatistics is a discipline that is concerned with the development and application of statistical theory and methods for the study of phenomena arising in the life sciences. Biostatistics as a discipline. Whether biostatistics is or is not a discipline depends on the amount and quality of knowledge that has been developed and accumulated in the field. I would not consider biostatistics a discipline prior to the end of World War II. But biostatistics has experienced a drastic change during the last 30 years. Prior to 1950, biostatistics was synonymous with health statistics, almost entirely descriptive in nature. Since then graduates with strong backgrounds in mathematical statistics and mathematics have entered the field and treated biostatistical topics with a different attitude. Research emphasis shifted from descriptive statistics to the development of a sound theoretical basis for the field. Conventional topics in biostatistics were completely readdressed and restructured and new methods of analysis have been continually introduced. As a result, biostatistics today contains a respectable body of knowledge both in quality and quantity and is built on a solid theoretical foundation. In the words of Professor Bernard G. Greenberg (1983), this body of knowledge "is transmissible by teaching, and is subject to change resulting from research."