BUEC 232 Chapter 7-8: BUEC232 - Ch.07,08 Notes

• School: Simon Fraser University
• Department: Business Economics
• Course: BUEC 232
• Professor: George Zhang

Document Summary

Inference for the mean of a population: t distributions. Where n = sample size: standard error. When the standard deviation of a statistic is estimated form the data, the result is called the standard error of the statistic ( se x. When we substitute the standard error (s/ n ) for the standard deviation ( / n ) to calculate z statistics, it becomes an one-sample t statistic t = Has a t distribution (instead of a normal distribution) with n-1 degrees of freedom. Where t* is the value for the t(n-1) density curve with area c between t* and t* If the population is normal, the confidence interval is exact. If the population is not normal, the confidence interval is approximately correct for a large sample size, n (central limit theorem) Choosing the sample size: to obtain a desired margin of error (m) with a predetermined level of confidence (t*), set: Thus, required sample size (n) is: (t*) s.