Re: Superimposing Normal on a Histogram of data
- To: mathgroup at smc.vnet.net
- Subject: [mg91595] Re: Superimposing Normal on a Histogram of data
- From: Bob Hanlon <hanlonr at cox.net>
- Date: Thu, 28 Aug 2008 07:39:16 -0400 (EDT)
- Reply-to: hanlonr at cox.net
Needs["Histograms`"];
Options[Histogram]
One option shown is HistogramScale -> Automatic
?HistogramScale
"HistogramScale is an option of histogram functions that specifies the way =
in which the bar heights are to be scaled. >>"
Click the "more" link ( >> ) to go to
Histograms/ref/HistogramScale
Under EXAMPLES / Basic Examples
"Use HistogramScale -> 1 to get a probability density:"
Bob Hanlon
---- axel <axel.kilian at hs-merseburg.de> wrote:
=============
On 28 Aug., 09:27, Bob Hanlon <hanl... at cox.net> wrote:
> Needs["Histograms`"];
>
> data = RandomReal[NormalDistribution[5, 2], {100}];
>
> {mu, sigma} = {Mean[data], StandardDeviation[data]}
>
> {5.21122,1.84401}
>
> Show[{Histogram[data, HistogramScale -> 1],
> =C2 Plot[PDF[NormalDistribution[mu, sigma], x],
> =C2 =C2 {x, mu - 3 sigma, mu + 3 sigma},
> =C2 =C2 PlotStyle -> Red]},
> =C2 PlotRange -> All]
>
> Bob Hanlon
>
> ---- ouadad <desmier... at forces.gc.ca> wrote:
>
> =============
> Can someone point me to an algorithm that allows me to plot a normal curv=
e over a histogram of residuals? =C2 I just want to show how close my res=
idual distribution approximates a normal distribution.
Hi Bob,
very elegant solution. Where did you find the option HistogramScale?
It's not in my manual.
regards
Axel Kilian