File:Correlation range dependence.svg
Summary
| Description |
English: Plot depicting how various measures of association are affected when the range of a quantitative variable is limited. |
| Date | |
| Source | Own work |
| Author | Skbkekas |
| SVG development | |
| Source code | Python codeimport numpy as np
import matplotlib.pyplot as plt
r = 0.9
X = np.random.normal(size=100)
Y = r*X + np.sqrt(1-r**2)*np.random.normal(size=100)
ii = np.flatnonzero( (X>0) * (X<1) )
XR = np.argsort(np.argsort(X))
YR = np.argsort(np.argsort(Y))
def pearson(X,Y):
cc = np.cov(X,Y)
return cc[0,1]/np.sqrt(cc[0,0]*cc[1,1])
r1 = pearson(X, Y)
r2 = pearson(X[ii], Y[ii])
s1 = pearson(XR, YR)
s2 = pearson(XR[ii], YR[ii])
plt.clf()
plt.hold(True)
plt.figure(figsize=(5,4))
plt.axes([0.13,0.13,0.8,0.8])
plt.fill((0,1,1,0,0), (-3,-3,3,3,-3), 'lightgrey', ec='lightgrey')
a = plt.plot(X, Y, 'o', color='orange')
b = plt.plot(X[ii], Y[ii], 'o', color='lightblue')
plt.xlim(-3,3)
plt.ylim(-3,3)
plt.xlabel("X", size=18)
plt.ylabel("Y", size=18)
bx = plt.legend((a,b), ["%.2f/%.2f" % (r1,s1), "%.2f/%.2f" % (r2,s2)],\
'upper left', numpoints=1, handletextpad=0.00001)
bx.draw_frame(False)
plt.savefig("correlation_range_dependence.pdf")
plt.savefig("correlation_range_dependence.svg")
|
Licensing
I, the copyright holder of this work, hereby publish it under the following license:
This file is licensed under the Creative Commons Attribution 3.0 Unported license.
- You are free:
- to share – to copy, distribute and transmit the work
- to remix – to adapt the work
- Under the following conditions:
- attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
