2. Interval estimate Although x is the single"best guess of the true population mean, the interval, say, from 8 to 14, most likely includes the true u? This is interval estimation Sampling or probability distribution:X N(L, (X- N(21) P(tn1≤t≤tn1)=1-a S/vn P(X ≤Hx≤x+ critical t values:±t n-1 confidence interval X X (lower limit-upper limit confidence coefficient: 1-a level of significance/the prob of committing type I error: a2. Interval estimate Although is the single “best” guess of the true population mean, the interval, say, from 8 to 14, most likely includes the true μχ ? This is interval estimation. Sampling or probability distribution: • • P(-t n-1 ≤t≤t n-1 )=1－α critical t values:±t n-1 confidence interval: (lower limit-upper limit) confidence coefficient: 1－α level of significance/the prob. of committing type I error: α X ~ ( , ) 2 n X N x   ~ (0,1) / ( ) N n X Z X  −  = ~ ( 1) / − − = n X t S n X t  1 α n t S μ X n t S P(X n 1 X n 1 −   + = − − − n t S X n t S X n X n−1 −1 −    +