ECON 2500 Lecture Notes - Statistical Inference

• School: York University
• Department: Economics
• Course: ECON 2500
• Professor: all

Document Summary

Econ 2500 winter 2011 xianghong li. Chapter 7 inference for distributions mar 29. Matched pair studies: subjects are matched in pairs and the outcomes are compared within each matched pair. Two measures, e. g. before and after some treatment, from the same subjects. Draw inferences based on differences exactly the same as one-sample t procedures. Assumption: the population of differences has a normal distribution. A statistical inference procedure is called robust if the probability calculations required are insensitive to violations of the assumptions made. T procedure assumption: the underlying population follows normal distribution. N 15: using t procedures if the data are close to normal (normal quantile plot). N 15: t procedures can be used except in the presence of outliers and strong skewness.