ENVS 1100 Chapter Notes - Chapter All: Design Of Experiments, Statistical Unit, Measuring Instrument
Document Summary
Chapter 1: why you should care about design. Experiments need to be designed properly in order to prevent mistakes in data. Myth 1: it does not matter how you collect your data, there will always be a statistical. X" that will allow you to analyze it. Random variation: quali es the the extent to which individuals differ from each other. Myth 2: if you collect lots of data something interesting will come out, and you"ll be able to detect even very subtle effects. Costs of poor design: time and money effectively designed experiment must be possible to analyze or else money is wasted, ethical issues some experiments may be harmful to the subjects, to avoid this one must design around that. Indirect measure: measuring one variable as a surrogate for another: generally provide unclear results, should always try and measure the thing that we are actually interested in.