Data sets shared by StatCrunch members
Showing 1 to 12 of 12 data sets matching coefficient
Data Set/Description 
Owner 
Last edited 
Size 
Views 
anscombe.txt
Anscombe's 4 data sets for regression. They are very different, yet have the same correlation and regression coefficients.  butler  May 31, 2011  360B  773 
10 highest peaks in Rockies and Appalachians
Is there more variation in the heights of the highest peaks in the Rockies (newer) or in the Appalachians (older)? Use coefficient of variation to find out!  anderson_instructor  Aug 18, 2018  174B  153  Validity Continuous DataClass Example
Validity data for class example. Compute correlation, coefficient of determination, standard error of prediction, regression equation, predicted value for X = 70, and 95% confidence interval for X = 70  mld  May 21, 2014  120B  217  Economic Freedom Index (2018)
This set contains data from:
The Heritage Foundation's "Economic Freedom Index", measuring total economic freedom, property rights, government integrity, tax burden, business freedom, and investment freedom.
The World Bank Group's GDP per capita, Net National Income per capita, and GDP percentage growth
The UN's Human Development Index, total and inequality adjusted
The Gini coefficient measures for several countries from 2013 to 2017
Reporters Without Borders' "Press Freedom Index"  williamharrison  Sep 10, 2018  17KB  135  Inspecting Anscombe's quartet_Scaringelli_A
1) X1 and y1 correlation coefficient: 0.81642052
X2 and y2 correlation coefficient: 0.81623651
X3 and y3 correlation coefficient: 0.81628674
X4 and y4 correlation coefficient: 0.81652144
This means that the strength of each relation is about the same for all four, although x4 & y4 have the highest correlation coefficient and x2 & y2 have the lowest correlation coefficient.
2) The four calculations lead you to conclude that the strength of the linear association between the two quantitative variables of each x and y. With all of the four correlations around 0.816 we can conclude that there is a moderately strong linear association between each x and y variable and this holds throughout all four sets of variables.
3) See posted scatterplots
4) X1 y1
The direction of this association is positive. The form is linear but the strength of the scatter is weak.
X2 y2
The direction of this association starts out positive and then switches to negative around an x value of 11. This is because the form of the association is curved; however the strength of the association is strong.
X3 y3
The direction of this association is positive. The form is linear and the strength of the association is strong except for one outlier that stands away from the overall pattern of the scatterplot at x=13 and y=12.74.
X4 y4
The direction of this association is positive. The form is linear and the strength of the association is a very strong straight vertical line at x=8 except for one outlier that stands away from the overall pattern of the scatterplot at x=19 and y=12.5.
 ajs5633  Jul 8, 2014  391B  58  McGuire and Sosa
Correlation of Coefficient between the home runs of Sosa and McGuire.  emprogboy  Dec 9, 2013  4KB  31  Anscombe's Data
Anscombe's data that illustrates how the correlation coefficient can be similar for very different nonlinear associations.  sirelfman  Feb 29, 2012  348B  26  Turbine Coefficients  statmanone  Nov 13, 2008  154B  209  Investigating the Coefficient of Determination  cassity  Sep 25, 2018  279B  74  Critical Values for Correlation Coefficient  chenle  Oct 9, 2015  307B  58  Problem 4.50
Prediciton Coefficients  ds14483%sc  Aug 11, 2008  187B  30  Investigating the Coefficient of Determination activity  cthomas8247  Feb 12, 2018  282B  11 
