# Quiz 1

Download the Excel spreadsheet for Quiz 1. For all plots, make screen shots and load your graphics file in your quiz submission. Be sure all of you plots have clear labels and titles so it is easy for the reader to know what is being presented.

1.     (5 points) Make a box plot of the data.

2.     (5 points) Are there any points that look like outliers that should be eliminated from the data before any further analysis should be done? If yes, state which point(s) should be eliminated and why. If not, state why you think there are no outliers.

If you eliminated any points, use your revised data set for the rest of the quiz.

3.     (5 points) Make a stem and leaf plot of the data.

4.     (5 points) What is the mean of the sample?

5.     (5 points) What is the median of the sample?

6.     (5 points) What is the mode of the sample?

7.     (5 points) What is the standard deviation (stdev.s) of the sample?

8.     (5 points) What is the size n of the sample?

9.     (5 points) Suppose the data in the spreadsheet is not a sample but a population. What is the standard deviation (stdev.p) of the population?

10.  (5 points) The relationship between stdev.s and stdev.p is:

stdev.s/stdev.p =

Show that your numbers obey the above relationship, or re-derive your numbers until they do work.

11.  (5 points) Copy and paste the Excel data into the www.shodor.org histogram applet. Find an optimal bin size by changing the interval size. What bin size do you conclude will best show the data? Include a screen shot of your histogram.

12.  (5 points) Go back to the Excel spreadsheet and sort the data from smallest to largest. Go to “Home”, “Sort and Filter”, “Smallest to Largest”. Find the median of the sorted data. Does your value agree with what the computer program gave you in part 5? (yes or no)

13.  (5 points) The percentile tells you what percentage of points is below that value. What value is the 70th percentile for this data set?

14.   (5 points) Fill in the frequency table below with your bin intervals from part 11. Click on the “Show Frequency Table” button.

(5 points) Make a relative frequency plot of the data.

15.  (5 points) Make a cumulative frequency plot of the data.

16.  (5 points) One pre-election poll predicted the following results of the popular vote for president:

Clinton = 46%

Trump = 40%

Johnson = 9%

Stein = 4%

Others = 1%

The final elections results were:

Clinton = 48%

Trump = 46%

Johnson = 3%

Stein = 1%

Others = 2%

One of constant things you hear about election polls is that the margin of error is +/- 3%.  Obviously, if the margin of error is too large, the poll is of no use. For example, in almost all elections, the winner gets 50% +/- 10% of the vote. So for this pre-election poll, did all of the predictions all fall within the margin of error of +/- 3%? (yes or no). If you answered “no”, then what should the pollster have said the margin of error was in order for all of the predictions to be correct?

17.  (5 points) Use the diagram below to answer the following questions.

(a)   Which distribution has the highest mean ( )? (A or B)

(b)   Which distribution has the largest standard deviation?

(c)    Which distribution has the largest variance?

(d)   Which distribution has the largest skewness?

(e)   Does the distribution you chose in (d) have a right or left skew?

18.  (10 points) In the election of 1860, there were 4 major candidates. The popular and electoral college vote was as follows.

Candidate
% popular vote
Lincoln
39.8
180
Douglas
29.5
12
Breckenridge
18.1
72
Bell
12.6
29
a.     Make a pie chart of the popular vote.

b.     Make a pie chart of the electoral vote.