File:Standard symmetric pdfs logscale.svg
Summary
Description |
English: Logscale plot of several symmetric unimodal probability densities with unit variance. From highest to lowest peak:
red, kurtosis 3,
orange, kurtosis 2,
green, kurtosis 1.2,
black, kurtosis 0,
cyan, kurtosis
blue, kurtosis −1.2, (U)niform distribution. magenta, kurtosis |
||||||
Date | |||||||
Source | MarkSweep | ||||||
Author |
Vector: Category:Vectorizations |
||||||
Permission (Reusing this file) |
I, the copyright holder of this work, hereby publish it under the following license:
|
||||||
Other versions |
File:Standard symmetric pdfs.svg File:Standard symmetric pdfs.png File:Standard symmetric pdfs logscale.png |
||||||
SVG development | |||||||
Source code |
# Laplace double exponential distribution, kurtosis 3
laplace(x) = exp(-abs(x)*sqrt(2)) * sqrt(0.5)
# sech distribution, kurtosis 2
sech(x) = 2.0 / (exp(x) + exp(-x))
sech_pdf(x) = 0.5 * sech(0.5*pi*x)
# logistic distribution, kurtosis 1.2
slogist = sqrt(3) / pi
logist(x) = exp(-x/slogist) / slogist / (1 + exp(-x/slogist))**2
# normal distribution, kurtosis 0
n(x) = exp(-0.5*x*x) / sqrt(2*pi)
# raised cosine distribution, kurtosis -0.59376
scos = 1.0 / sqrt(1/3.0 - 2/pi**2)
cosine(x) = abs(x)>scos? 0 : (1+cos(x*pi/scos))*0.5/scos
# Wigner semicircle distribution, kurtosis -1
wigner(x) = abs(x)>2? 0 : sqrt(4-x*x)*0.5/pi
# uniform distribution, kurtosis -1.2
uniform(x) = abs(x)>sqrt(3)? 0 : 0.5/sqrt(3)
set samples 6001
set grid
set xrange [-10.4:10.4]
set logscale y
set yrange [1e-24:5]
set ytics 1e3
set key right bottom font ",8" enhanced
set terminal svg size 400,300 enhanced fname 'DejaVu Sans' fsize 10 butt solid
set output 'Standard symmetric pdfs logscale.svg'
plot \
laplace(x) lt 1 lw 2 title "D, 3", \
sech_pdf(x) lt 8 lw 2 title "S, 2", \
logist(x) lt 2 lw 2 title "L, 1.2", \
n(x) lt 7 lw 2 title "N, 0", \
cosine(x) lt 5 lw 2 title "C, -0.59376", \
wigner(x) lt 3 lw 2 title "W, -1", \
uniform(x) lt 4 lw 2 title "U, -1.2"
|