Activity 2.1
Estimating Dates: Scatterplots
10 points
Due at the beginning of class, Wednesday, February 4, 2009
In this activity you will estimate the dates of several major events and then use a scatterplot to compare your estimates with the actual dates these events occurred. You will analyze relationships between two variables that can be read from a scatterplot.
You will start with an estimation experiment. It might be helpful to work with a partner to estimate the year in which the event, in the following table, occurred.
1. For each of the following twentieth century events, estimate the year in which each event occurred. (Record only the last two digits of the year; because you know all dates are in the 1900's, you don't need to record the "19.")
Event |
Estimated Year Event Occurred |
Mark Spitz wins 7 gold medals in the summer Olympics |
|
Penn State football coach Joe Paterno born |
|
Senator Robert Kennedy assassinated |
|
Original Woodstock Music Festival held |
|
Amendment repealing prohibition passed |
|
Mark McGwire hits 70 home runs, Sammy Sosa hits 66 |
|
Aerosol can invented |
|
World War II ends |
|
President Reagan elected to a second term |
|
Forrest Gump wins Academy Award for best picture |
|
Long-distance telegraphic radio signal sent across the
Atlantic |
|
Time Magazine first published |
|
The World Wide Web developed |
2. After you have made your guesses, use the file, Data for Activity 2.1 to find the correct dates. On a separate sheet of paper, hand-draw a scatterplot of the data, with x representing "year event occurred," and y representing "estimated year event occurred." (You might find it helpful to record these actual dates immediately to the left of your previous estimates.) You should turn in this scatterplot.
3. Why is it appropriate to use "year event occurred" as the explanatory variable and "estimated year event occurred" as the response variable?
4. How close were your predictions of events that occurred to the actual dates?
5. What would the scatterplot look like if you had guessed the correct year for each event?
6. Sketch the line y = x on your graph. Does it appear you overestimated more than you underestimated, or vice-versa? How can you determine this from your graph?
7. Use Excel to redraw the scatterplot you created previously. To do so, you need to enter the data in two columns. One column should contain the values of the explanatory variable and the second column the values of the response variable.


8. Create a new graph in Excel where the estimated and actual years are the same. Describe the graph. Is this what you had expected in #5 above?
Summary
In this activity, you learned to use Excel to create a scatterplot. In creating
scatterplots, you decided which variable should go on the horizontal axis (that
is, which variable is the explanatory variable) and which should go on the vertical
axis (that is, which is the response variable). You also discovered how the
line y = x can help you see relationships
in paired data. You will use these skills to visualize relationships between
variables in bivariate data sets.