5.1 Assumption of Independent Observations

The primary assumption of most standard statistical procedures is that observations are independent of each other. That is, the value of one observation does not change or affect another observation. However, there are many examples where measurements are made on subjects before and after a certain exposure or treatment (pre-post), or an experiment to compare two cell phone packages might use pairs of subjects that are the same age, sex and income level. One subject would be randomly assigned to the first phone package, the other in the pair would get the second phone package. This chapter only deals with non-correlated analyses, leaving that topic for a later chapter.