Subsection 9.6 Choice of Procedures for Analyzing One Mean
| Study design | One quantitative variable from large population or process |
| Parameter | \(\mu\) = population mean or process mean (or use sign test or bootstrapping) |
| Null Hypothesis | \(H_0: \mu = \mu_0\) |
| Simulation | Random sample from finite population or bootstrapping |
| Can use \(t\) procedures if |
|
| Standardized (test) statistic | \(t_0 = \frac{\bar{x} - \mu_0}{s/\sqrt{n}}\) |
| Confidence interval | \(\bar{x} \pm t_{n-1}^* \frac{s}{\sqrt{n}}\) |
| Prediction interval | \(\bar{x} \pm t_{n-1}^* s\sqrt{1+\frac{1}{n}}\) (with normally distributed population) |
| R Commands |
raw data in “x”
t.test(x, alternative="two.sided", mu=0, conf.level = 0.95)
summary statistics
iscamonesamplet
|
| JMP | Analyze > Distribution with a quantitative variable Input variable column or summary statistics (Prediction interval) |
| TBI Applet | One mean |
You have attempted of activities on this page.
