Math 151 , Spring 2005, Day 11 Wed. Feb. 23 Hit reload...After class

--Exam 1  Next time: Friday Feb 25, Day 12, in class, closed book.   Bring a simple calculator. I will give you copies of the Normal table.  If you will need extra time, make arrangements with me today, please.
Covers through  Part I:through p.112.  You will need to read SPSS output, but not tell how to produce any. You will need to calculate "by hand" a standard deviation for four numbers. (As well as medians, quartiles, etc.)   Problems like HW + some true-false or multiple choice types.
 Sample exam was given out, solutions outside my door, & on reserve.
I will be in my office this afternoon, and  tomorrow (Thursday) 12-12:30, 1:45-2:15.
HW Day11 (Wed. Feb. 23):
Reading   D&V Ch7 Scatterplots, first thru 117 (AS7-1&2), then Correlation, the rest. (AS7-3&4) You do not have to be able to calculate r by hand.  You should be able to guess roughly at an r for a swarm of data.
Hand in Monday: Do Activstats 7-1&2, Hand in the SPSS scatterplot of cars made in the last activity on 7-2.
Hand in Monday (?).Wednesday (From D&V unless otherwise noted)
Scatterplots: (copied from day 10)
p. 130, 5,6 describing simple plots
 1,4 what relationship ALSO sketch an appropriate scatterplot for each.
  8 Derby (This is actually a timeplot)ALSO, how does the variability  change over the decades?
 9 Pottery For a, dotplot is ok instead of histo.  ALSO, is Batch # really Quantitative, or Ordinal? 

SPSS Handout: Repeat the work of page 1, and do problems 1-5 on p. 3.  Keep this work and hand it all in when all problems have been assigned. 

HW in Activstats:  Go to Chapter 7, use the menu button with the House icon.  Scroll thru the problem list to find the ones given.  In each problem involving data, a button will allow you to launch SPSS and open the correct file.  Then save the file for yourself, do the analysis.
MRA-81-4 (SPSS) Metabolic Rates, M/F
MRA-83-8 (SPSS) Ed. Spending vs. Teacher Salaries 
MRA-80-2 (SPSS)  Speed vs. Fuel Consumption (describe)
TRE-58-26 (SPSS)  Bear neck/weight  ALSO Make a plot with the M&F bears marked differently.  What if any sex differences do you see here?

MRA-95-13 (SPSS, and pencil) Corn plants.  This is a first introduction to the idea of predicting or estimating a "typical" y for a given x value.  Ch. 8 will do an important special case of that. 
- - - - - - - - - - - - - - - - - 
Correlation (beginning): 
SPSS Handout: Do problem 6, p. 3.  Keep this with the previous work.
p. 130 #11, 12  Match # to scatter.  (Use handout of typical ones, AS7-3 Activity 2)
ActivStats: MRA-89-4 (SPSS) Speed vs. Fuel Consumption (cf. MRA-80-2) r~0, why?

 Read, 
 to discuss 		 Optional 
 
Questions for Exam??
Start here Monday:
Relationships:(D&V Ch 7 thru p.117, AS7-1&2  ) Day 10
Handout on SPSS Scatterplots etc. (D&V Ch. 7-10, AS 7,8,9)
govsal_vs_pay.sav  is the file used for most of the handout. (In SPSS for Class 05 folder)

Correlation (D&V Ch.7 pp118ff, AS7-3&4) Handout, "some correlations"

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.
Use if data is:  2 quantitative variables, & "nice":
   && One cluster/cloud/band.
   "Straight enough."
   Outlier(s)? Do with/without & be cautious.

Using SPSS (p.4, Scatterplot handout) Analyze>Correlate>Bivariate

Properties:

  1. Sign of correlation coefficient matches direction of relationship
  2.  Between -1 and +1.   0: no linear relationship,   +1 or  -1: perfect straight line.
  3. Measures relationship--same whichever variable is on the x-axis
  4. "Unitless"--original measurment units are "standardized out"
  5. Not affected by changes of center or scale
  6. Does NOT give info about curved relationships (only measures linear part of relationship).
  7. NOT resistant to outliers--quite sensitive.
correlation graph


Correlation experiments:
ActivStats 7-3, 2nd activity:  Slider to see shapes ~~ r's.  3rd activity: non-linear data and r's. 4th: center and scale change.

Website,  http://www.whfreeman.com/scc,
   Click Netscape toolbars to minimize them, if needed.
    Choose "Statistical Applets",  Correlation/Regression.  Play with data points, observing the Correlation Coefficient.
       Check in the "Show Mean X & Mean Y lines" box.  See how much is in each quadrant. Compare with above.
--You won't have to calculate a correlation coefficient by hand. This formula is a bad one for hand computation (roundoff error); if you must do one by hand, find the computational formula in an old textbook.
--Eyeballing:  sketch xbar and ybar lines, see how much data is in + quadrants, how much in - quadrants.

Strength of correlation says NOTHING about causality!  Strong correlation could be:
     A causes B/  B causes A/ C causes both A and B (lurking C)/ just Chance that they go together in this data set.

Sievers home  Math151-Sp05/Days11.htm  1pm 2/23/05
This page belongs to Sally Sievers who is solely responsible for its content. Please see our statement of responsibility.