Data Coefficients Flashcards
Line of Best Fit
Shows how strong a correlation is between variables
Pearson’s Correlation Coefficient
Calculate how close a correlation is between two variables
Pearson’s Correlation Coefficient Formula
(nΣxy) - (ΣxΣy)
r = ————————————–
√(nΣx² - (Σx)²)(nΣy² - (Σy)²)
x = variable 1 y = variable 2 Σ = sum of n = number of data entries of each variable r = the correlation coefficient
Understanding the Correlation Coefficient
r = 1: correlation is perfectly positive - all points are on the line of best fit, sloping up from left to right
r = -1: perfectly negative - all points are on the line of best fit, sloping down from left to right
r = 0: no correlation - points are all over with no line of best fit
Correlation coeff can only be between 1 & -1
Coefficient of Determination
Calculates the proportion to which a change in Y is determined by a change in X
Understanding the Coefficient of Determination
1 = perfect correlation - change in Y value is solely down to the change in X value
0 = no correlation - change of X value had nothing to do with the change in Y value
Coefficient of Determination Formula
r²
r = the correlation coefficient
Spearman’s Rank Correlation Coefficient
Determines the correlation, if any, between the rankings of two distributions. The closer to 1, the closer the correlation
Spearman’s Rank Correlation Coefficient Formula
6Σd²
Rs = 1 - ——————
n(n² - 1)
Rs = Spearman's Rank n = the number of points in the data d = the difference between rankings Σ = sum of
Spurious Connection
Where two unrelated variables have the same trend pattern. Always verify the connection - how likely is it that the variables would influence each other?
Extrapolating
Making assumptions about results outside the data set