Laws of Experimentation: 1. If reproducibility may be a problem, conduct the test only once. 2. If a straight line fit is required, obtain only two data points. 3. Under the most rigorously controlled conditions of pressure, temperature, volume, humidity, and other variables, the organism will do as it pleases. 4. If at first you don't succeed, transform your data set.

source: Anonymous tags: Humor, Science, Trust