Stat 7-14

Stat 7-14 - hapter 8 (Linear Regression) P(A or B) = P(A) +...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
hapter 8 (Linear Regression) P(A or B) = P(A) + P(B) Stat 201 Exam 2 Topics List – Spring 2009 Chapter 7 (Correlation) o Know which type of variables we use to create a scatter plot Scatterplots show relationship between two quantitative variables measured on the same cases o Interpret a scatter plot Direction (distinguish positive vs. negative relationship) Positive- as one variable increases, the other increases Negative- as one variable increases, the other decreases Form (distinguish linear vs. curvy relationship) Linear- swarm of data stretched out in generally consistent straight line Strength (distinguish strong vs. weak relationship) Strong association- represented by tight clustered single stream Weak association- represented by vague cloud Unusual Features (be able to spot an outlier) Look for: Outliers- a point that does not fit the overall pattern seen in scatterplot Subgroups- clusters that stand away from rest of data Parts of plot that show trend in a different direction o Know the difference between explanatory and response variables Explanatory variable- predictor, independent, x-variable Response variable- dependent, y-variable o Fully understand correlation Know the bounds for r r must be greater than or equal to -1 and less than or equal to 1 Be able to match r to example scatter plots .5-1- strong, positive correlation -.5—1 strong, negative correlation Know the 3 necessary conditions for correlation analysis 1. Quantitative Variables Condition- correlation only applies to quantitative variables 2. Straight Enough Condition- correlation measures the strength of linear association 3. Outlier Condition- outliers can distort correlation; report correlation with and without the outlier(s) Describe what it means for a correlation to be 1, 0, and 1 r = -1 implies a perfect negative linear correlation r = 0 implies no linear correlation at all r = 1 implies a perfect positive linear correlation Understand the difference between correlation and causation Correlation does not determine causation Have a general understanding of what lurking variables are Lurking variable- a variable not explicitly part of a model but that affects the way the variables in the model appear to be related
Background image of page 1

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

View Full DocumentRight Arrow Icon
o Know the 3 conditions for regression 1. Quantitative Variables Condition- correlation only applies to quantitative variables 2. Straight Enough Condition- correlation measures the strength of linear association 3. Outlier Condition- outliers can distort correlation; report correlation with and without the outlier(s) o Know what is special about the regression line compared to any other line drawn through the data (“least squares”) The least squares line is the line of best fit- line for which the sum of the squared residuals is the smallest o Spot regression components in JMP output o Given JMP output, write out the regression model with actual variable names o Interpret regression coefficients (b0 and b1)
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This document was uploaded on 06/28/2011.

Page1 / 6

Stat 7-14 - hapter 8 (Linear Regression) P(A or B) = P(A) +...

This preview shows document pages 1 - 3. Sign up to view the full document.

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