There is universal acceptance of statistics as an essential tool for all types of research. That acceptance and ever-proliferating areas of research specialization have led to corresponding increases in the number and diversity of available statistical procedures. In agricultural research, for example, there are different statistical techniques for crop and animal research, for laboratory and field experiments, for genevic and physiological research, and so on. Although this diversit" indicates the aailability of appropriate statistical techniques for most research problems, il.also indicates the difficulty of matching the best technique to a specific expe, 2ment. Obviously, this difficulty increases as more procedures develop. This is a second edition of an International Rice Research Institute publication with a similar title and we made extensive revisions to ail but three of the original chapters. We added four new chapters.