Verify distribution uniformity/Naive: Difference between revisions
Content added Content deleted
m (Adjust categorization) |
(Remove chi-squared stuff to another task, add cross-link) |
||
| Line 14: | Line 14: | ||
Show the distribution checker working when the produced distribution is flat enough and when it is not. (Use a generator from [[Seven-dice from Five-dice]]). |
Show the distribution checker working when the produced distribution is flat enough and when it is not. (Use a generator from [[Seven-dice from Five-dice]]). |
||
'''See also:''' |
|||
*[[Verify Distribution Uniformity with Chi-Squared Test]] |
|||
=={{header|Python}}== |
=={{header|Python}}== |
||
| Line 64: | Line 67: | ||
0 10003 1 9851 2 10058 3 10193 4 10126 5 10002 6 9852 7 9964 8 9957 9 9994 |
0 10003 1 9851 2 10058 3 10193 4 10126 5 10002 6 9852 7 9964 8 9957 9 9994 |
||
<span style="color:red">distribution potentially skewed for 0: expected around 50000, got 94873</span> |
<span style="color:red">distribution potentially skewed for 0: expected around 50000, got 94873</span> |
||
An alternative is to use the [[wp:Pearson's chi-square test|<math>\chi^2</math> test]] to see whether the hypothesis that the data is uniformly distributed is satisfied. |
|||
{{works with|Tcl|8.5}} |
|||
{{libheader|tcllib}} |
|||
<lang tcl>package require math |
|||
interp alias {} tcl::mathfunc::lnGamma {} math::ln_Gamma |
|||
proc tcl::mathfunc::chi2 {k x} { |
|||
set k2 [expr {$k / 2.0}] |
|||
expr {exp(log(0.5)*$k2 + log($x) * ($k2 - 1) - $x/2.0 - lnGamma($k2))} |
|||
} |
|||
proc isUniform {distribution {significance 0.05}} { |
|||
set count [tcl::mathop::+ {*}[dict values $distribution]] |
|||
set expected [expr {double($count) / [dict size $distribution]}] |
|||
set X2 0.0 |
|||
foreach value [dict values $distribution] { |
|||
set X2 [expr {$X2 + ($value - $expected)**2 / $expected}] |
|||
} |
|||
set freedom [expr {[dict size $distribution] - 1}] |
|||
expr {chi2($freedom, $X2) > $significance} |
|||
}</lang> |
|||
The computing of the distribution to check is trivial (and part of the <code>distcheck</code>) and so is omitted here for clarity. |
|||