Biology 2244A/B Chapter Notes - Chapter 8: Repeated Measures Design, Blind Experiment, Migraine Treatment
Document Summary
Biology 2244a topic 1 sampling and study design. The practice of statistics in the life sciences. Individuals/units called subjects when they are people, called experimental units otherwise. Experiment needs to have control to eliminate or reduce lurking variables. Placebo: control treatment that is fake but otherwise indistinguishable from treatment in experimental group. Eliminates confounding variable of psychological impact of undergoing treatment. Randomization of which subjects are assigned to which treatment reduces bias. Use enough subjects to reduce chance variation. Statistical significance: observed effect that is so large that it would rarely occur by chance. Statistically significant data from well-designed experiment imply causation. Note not necessary to assign the same number if individual to each treatment. Block: group of individuals that are known before the experiment to be similar in some way that is expected to affect response to treatments form of control, based on most important unavoidable sources of variability.