STAT 8010 Lecture Notes - Lecture 7: Null Hypothesis, Confidence Interval, Test Statistic
Document Summary
Formula used to determine sample size when is known: Formula used to determine sample size when is not known: o: this follows a t distribution with n-1 degrees of freedom, there are an infinite number of t distributions. As the degrees of freedom increases, the hump in the middle of the t density graph gets higher (density increases. ) A 100(1- )% confidence interval for the mean is: ybar t /2(n-1) () If you know , then use the z critical value. I you do not know , then use the t critical value. Failure to reject the null hypothesis is not the same as accepting the null hypothesis. You can set either or at 0, but it will increase the probability of the one that is not set at 0. The distribution of the sample mean if the null hypothesis is true is: ybar ~ n( 0, 2/n)