Difference between revisions of "Dist reshape"

Revision as of 23:27, 27 January 2016

Dist_reshape(x, newdist)

Reshapes the probability distribution of uncertain quantity «x» so that it has the same marginal probability distribution (i.e, same set of sample values) as «newdist», but retains the same ranks as «x». Thus:

Rank(Sample(x), Run) =

Rank(Sample(Reshape_dist(x, y)), Run)

In a Mid context, it simply returns the mid value of «newdist», with any indexes of «x».

The result retains any rank correlations that «x» may have with other predecessor variables. So, the rank-order correlation between a third variable z and «x» will be the same as the rank-order correlation between z and a reshaped version of «x», i.e.

RankCorrel(x, z) =

RankCorrel(Dist_Reshape(x, y), z)

The operation may optionally be applied along an index other than Run.

Library

Multivariate Distributions.ana

@@ Line 2: / Line 2: @@
 [[Category:Doc Status C]] <!-- For Lumina use, do not change -->
-= Dist_reshape(x,newdist) =
+== Dist_reshape(x, newdist) ==
+Reshapes the probability distribution of uncertain quantity «x» so that it has the same marginal probability distribution (i.e, same set of sample values) as «newdist», but retains the same ranks as «x».  Thus:
+:<code>Rank(Sample(x), Run) =</code>
+:<code>Rank(Sample(Reshape_dist(x, y)), Run)</code>
-Reshapes the probability distribution of uncertain quantity x so that it has the same marginal probability distribution (i.e, same set of sample values) as newdist, but retains the same ranks as x.  Thus:
+In a [[Mid]] context, it simply returns the mid value of «newdist», with any indexes of «x».
-     Rank(Sample(x), Run)
-           = Rank(Sample(Reshape_dist(x, y)), Run)
-In a Mid context, it simply returns the mid value of newdist, with any indexes of x.
-The result retains any rank correlations that x may have with other predecessor variables.  So, the rank-order correlation between a third variable z and x will be the same as the rank-order correlation between z and a reshaped version of x, i.e.
+The result retains any rank correlations that «x» may have with other predecessor variables.  So, the rank-order correlation between a third variable ''z'' and «x» will be the same as the rank-order correlation between ''z'' and a reshaped version of «x», i.e.
-     RankCorrel(x, z) = RankCorrel(Reshape_Dist(x, y), z)
+:<code>RankCorrel(x, z) =</code>
+:<code>RankCorrel(Dist_Reshape(x, y), z)</code>
-The operation may optionally be applied along an index other than Run.
+The operation may optionally be applied along an index other than [[Run]].
-= Library =
+== Library ==
 Multivariate Distributions.ana
-= See Also =
+== See Also ==
+* [[Rank]]
+* [[RankCorrel]]
 * [[Correlate_With]]
+* [[Multivariate distributions]]
+* [[Distribution Densities Library]]