Statistical Sciences 1024A/B Lecture Notes - Lecture 26: Central Limit Theorem, Randomized Experiment, Standard Deviation
24 Nov 2018
School
Department
Professor
Document Summary
Then, the same test is signi cant at the a level of signi cance. When using statistical inference, you are acting as though your data is a probability sample or some from randomized experiment. Statistical con dence intervals and tests cannot remedy basic aws in producing the data, such as voluntary response samples or uncontrolled experiments. Caution about z procedures (requirements: the data must be an srs (simple random sample) of the population. More complex sampling needs from complex inference methods: the sampling distribution must be approximately normal, we must know standard deviation (o) > can be unrealistic requirement. You cannot use the z procedure if the population is not normally distributed and the sample size is too small. The sampling distribution of the mean will not be approximately normal. This violates the assumptions of the central limit theorem. Poorly designed studies often produce useless results nothing can overcome a poor design.
