MATH 251, Probability and Statistics I, Fall 2001, Sept. 19, Day 9

The correlation coefficient r is a numerical measure for how strongly linear (and in what direction) the relationship is.  Doesn't substitute  for a scatterplot.

1. Measures relationship--same whichever variable is on the x-axis
2. "Correlation" --only for 2 quantitative variables
3. "Unitless"--original measurment units are "standardized out"
4. Sign of correlation coefficient matches direction of relationship
5. Between -1 and +1.  0: no linear relationship, + or -1: perfect straight line.
6. Does NOT give info about curved relationships.
7. NOT resistant to outliers--quite sensitive.

Visual aids:
In Mac 101, Class Material\Math 151\Regression Demos
Text website,  http://www.whfreeman.com/ips, scroll down to Select a Category,  ClickNetscape toolbars to minimize them.
        choose "Statistical Applets",  Regression.  Play with data points, observing r;  try drawing the best fit line and then see how well you did.
 

Hand in:  Correlation 2.2  SPSS for all p. 131, 2.19a,b,c,d  Selection variable:Sex =M. then F.  2.22 speed/fuel again.  and 2.27 (Transform/compute will make your new variables. SPSS manual pp. 52-53).  p. 124 2.14 (Use Transform/compute, function LG10(variable)) and p. 134 2.28 (tree seeds) Regression 2.3 , to about p. 143   (Use SPSS on any raw data, unless otherwise noted.)  p. 148 2.37 pH line--draw, predict, interpret slope 2.111 lamb's quarters 2.40 degree days, plot&slope       Save your data & output files for next time.  2.49 metabolism again. For c, changing variables,       do the work by hand, from the numbers you got       from SPSS for part b, and 2.2.lb = 1 kg.

Read, discuss  Correlation 2.2  2.20 dates' heights.  r = .565 2.32 blunders

Optional        Straight line practice  (if needed)  2.33, 34, 35, 36