Statistics Detective Review
Recall that an underlined phrase means that it is a link off of the web page itself. This page can be accessed from the class highlights page. Take our your mean, median and mode lab in addition to your regression lab. Use the clues below and effective reasoning skills in order to identify the "odd person out" in our class data set. To mark off eliminated people on the computer, be sure that View/Toolbar/Formatting is checked. You can use the fill-in feature to eliminate suspects by clicking on the row number (in grey) and then the paint can in the formatting toolbar. You may change fill-in colors by clicking on the arrowhead just to the right of the paint can.

### The suspect...

1. satisfies the statement "did improve their MRT score"

Describe the combinations of scores of the people that can be eliminated (the people who contradict the statement - ie the people that scored the same or declined in score).

How many people can you eliminate?

2. does hit the 1st quartile (q1) "on the head" for the number of competitors of the family bathroom. The general command for the 1st quartile in the sth column is =quartile(s2:s26,1). Do not re-order the column - Excel doesn't need that for the command to work.

Which column does the clue apply to?

What is q1?

Describe the kinds of numbers that can be eliminated (the people who contradict the statement).

How many additional suspects can you eliminate?

How many total people have now been eliminated?

3. falls within the middle 50% of the class on the boxplot of the distance from home

Sketch the boxplot here (you should have this in class notes - use our by-hand work).

Describe the kinds of distances that can be eliminated (people who contradict the statement).

How many additional suspects can you eliminate?

How many total people have now been eliminated?

4. has a golden mean of (1+sqrt(5))/2 embedded in the forearm to hand ratio within a 0.2 decimal range.

Compute the golden mean in decimal form and write it down here.

Describe the kinds of numbers that can be eliminated (those who contradict the statement).

In Excel, compute the forearm to hand ratios of the remaining suspects (in the second row of an empty column, type =G2/F2     and hit return. Then, go back up to that box, go to the bottom right until you see the symbol that resembles a square with arrowheads on the top left and bottom right corners, click, and pull the mouse down to fill down the column (as we did in the golden mean lab). Now use the clue to eliminate people.

How many additional suspects have been eliminated?

How many total people have now been eliminated?

5. helps the statistics that say that people are better able to remember real words than nonsense words.

How many additional suspects have been eliminated?

6. has the median numerical value for foot length (=median(d2,d26)).

How many additional suspects have been eliminated? You should be down to one suspect.

7. pulls the original regression line for "does armspan predict height" down since the actual height value corresponding to the actual armspan is below the predicted value for the actual armspan given by plugging into the equation of the best fit line.

What is the equation of the best fit line (use the one from your last lab with the problem points left in)?

Compute the predicted value for the actual armspan for your suspect and show work to give evidence that your suspect does indeed satisfy this clue.

Your Suspect Once you have your guess, call me over and show it to me, and have your suspect approved.

Gender______   Armspan______   Height______   Foot Length______   Head Circ______ Hand______

Forearm______   Class Yr_________________   Siblings______   Home_______

Major_______________________   Minute______   RealWds______   NonsenseWds______

Timed MRT______   Untimed MRT______