Distribution-Free and Other Prediction Intervals (Q3753298)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 3990645
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Distribution-Free and Other Prediction Intervals |
scientific article; zbMATH DE number 3990645 |
Statements
Distribution-Free and Other Prediction Intervals (English)
0 references
1987
0 references
Chebyshev inequality
0 references
distribution-free prediction interval
0 references
triple range
0 references
table
0 references
0.804356575012207
0 references
0.7977347373962402
0 references
0.7834118604660034
0 references
0.7796206474304199
0 references
0.7749969363212585
0 references
\textit{J. G. Saw}, \textit{M.C. K. Yang} and \textit{T. C. Mo} [Chebyshev inequality with estimated mean and variance. ibid. 38, 130-132 (1984)] gave a distribution-free prediction interval for X based on \(X_ 1,...,X_ n\) of the form \([\bar X-A,\bar X+A]\) with \(A^ 2=\lambda^ 2(1+1/n)S^ 2\). As compared with the range \([X_{(1)},X_{(2)}]\), which has length R (say) and size (minimum coverage probability) \((n- 1)/(n+1)\), their intervals can have size as high as \(n/(n+1)\), a value that is attained when \(\lambda^ 2=n+1\). For \(n=2\), this interval (with \(\lambda^ 2=3)\) becomes the ''triple range'' \([X_{(1)}-R,X_{(2)}+R]\) and has size 2/3; it coincides with the ''normal interval'' for \(n=2\) with coverage probability 2/3 under normality. For all \(n>2\), the size of their interval (with \(\lambda^ 2=n+1)\) equals approximately the coverage probability of the normal interval based on three observations only. A table is given for the value of \(\lambda\) required to guarantee a size of at least h' for the distribution-free interval for selected values of h' and for all \(n\leq 100\). It may also be used when applying a Chebyshev-type inequality for simple random sampling from a finite population.
0 references