14 Correlation(1)

14 Correlation(1) - Biol 214 Statistics for Biology Majors...

Info iconThis preview shows pages 1–12. Sign up to view the full content.

View Full Document Right Arrow Icon
Biol 214 Statistics for Biology Majors Correlation November 29, 2011 1 John J. Kopecky, Ph.D. Fall 2011
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Correlation What have we done so far? 1) Compared “categorical” variable and “continuous” variable using t-tests. For example, height and sex, or concentration of dopamine and disease 2) Compared “categorical” variable and “categorical” variable: contingency tables. For example, disease and risk of dying. What are we going to do now? 1) Compare a “continuous” variable with another continuous variable. 2) There are several different ways of doing this. The first is correlation. 2
Background image of page 2
Correlation Correlation. A) Simply, we have two continuous variables, neither of which we consider a “predictor” or “independent”. We just want to figure out, for example, if one variable goes up, does the other go up? down? not change? 3
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Correlation 4 Scatter Plot
Background image of page 4
Correlation 1. Graphical description: 5
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Correlation 2) Problem - just describing the graphs is subjective, so we describe the correlation using what is called a correlation coefficient . 3) The correlation coefficient is designated by the Greek letter “rho”, and is estimated by “r”. In other words: r -> 6
Background image of page 6
Correlation B)Calculation of “r” 1) Here's the formula: 1 22 11 ( )( ) ( ) ( ) n ii i nn x x y y r x x y y    7
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Correlation Correlation Coefficient: 8
Background image of page 8
Correlation 2) How does it work? For the numerator: a) first notice that the coordinates for and are somewhere inside our points on the graph b) if x i < , and y i < , that implies that the point is below and to the left of ( , ), and for that value of i, the numerator is positive (you’re multiplying two negative numbers) y y x x x y 9 1 22 11 ( )( ) ( ) ( ) n ii i nn x x y y r x x y y   
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Correlation c) similarly, if x i > , and y i > , the point is above and to the right, and the numerator is positive. - so if all the points pair up below and to the left and above and to the right, r will be positive (you’re adding up a bunch of positive numbers. 10 x y
Background image of page 10
Correlation d) now what happens if x i < and y i > ? The point is now above and to the left of ( , ), and the numerator is negative (you’re multiplying a (-) and (+) number). e) similarly, if x i > and y i < , the point is below and to the right, and again the numerator is negative - if all the points are above to the left and below to the right of ( , ), r will be negative. Also, - if you have a mix of points, then it depends on where most of the points are, and how far away from ( , ) they are.
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 12
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 37

14 Correlation(1) - Biol 214 Statistics for Biology Majors...

This preview shows document pages 1 - 12. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online