Timeline for Show the shortest confidence interval of a normal distribution
Current License: CC BY-SA 3.0
9 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Jan 26, 2017 at 20:29 | history | edited | amoeba |
edited tags
|
|
Dec 19, 2014 at 6:01 | vote | accept | the_deuce | ||
Dec 10, 2014 at 20:49 | comment | added | whuber♦ | It's still not quite right. When $\alpha\lt 1/2$ and $0\lt k \lt 1$, both $Z_{k\alpha}$ and $Z_{(1-k)\alpha}$ are negative and therefore the interval you have written is empty! The meaning of your question is evident only from the intended conclusion, which implies the optimal interval is given by $[\bar{X}+Z_{\alpha/2} \sigma/\sqrt{n}, \bar{X}+Z_{1-\alpha/2} \sigma/\sqrt{n}]$. (There are many other ways to write this interval, since $Z_\beta = -Z_{1-\beta}$ for all $0\lt \beta \lt 1$, but your expression is not among the correct ones.) | |
Dec 10, 2014 at 20:37 | history | edited | the_deuce | CC BY-SA 3.0 |
edited body
|
Dec 10, 2014 at 18:38 | answer | added | whuber♦ | timeline score: 6 | |
Dec 10, 2014 at 17:52 | comment | added | whuber♦ | You probably meant to write "...$Z_{(1-k)\alpha}$...". The signs in front of the $Z_{*}$ are also problematic. | |
Dec 10, 2014 at 7:51 | history | edited | gung - Reinstate Monica | CC BY-SA 3.0 |
added tag; formatted
|
Dec 10, 2014 at 7:45 | review | First posts | |||
Dec 10, 2014 at 7:51 | |||||
Dec 10, 2014 at 7:41 | history | asked | the_deuce | CC BY-SA 3.0 |