Homework Assignment #4
All homework assignments must typed or legibly handwritten, and must show your name, the assignment number, course number, and the date clearly. Homework is due at the beginning of class on the specified date.
Due Thursday, October 5
Part 1, Text chapter exercises:
ch. 4: #10 (compute median and mode as well)
ch. 5: #4
Part 2, SDA:
Go to the SDA web site and pick a data set to explore (it doesn't have
to be the GSS). Browse the variables in the codebook and select an
interval scale variable you have not yet analyzed in previous assignments
that you would like to learn more about. Then use all techniques
you know to give a comprehensive description of this variable in terms
of central tendency, dispersion, and shape. To do this, you will
need to do the "Frequencies or Crosstabulations" action and follow the
procedures you used in previous assignments or were demonstrated for you
in the fertility handouts (e.g., selecting the "statistics" box on the
"SDA Tables Program" screen). The "statistics" output may not give
you all the information you need to compute some measures, so you will
also need to produce a frequency/percentage distribution. Even though
SDA does not include graphical procedures, you should still draw (by hand)
a box plot and histogram using the numerical output from SDA. Report
on all appropriate measures of central tendency and dispersion (be inclusive
here, not restrictive like the text recommends). Include with your
summary the 10th and 90th percentiles. When describing the shape
of the distribution, be sure to note any special features (e.g., outliers,
multimodality, etc.). Write a summary paragraph for your comprehensive
description of the distribution and be sure to include all SDA output and
graphical displays you draw.
Part 3, WebStat
Go to the WebStat site and load the "1000 random digits" sample data
set. Plot these data with a histogram or dotplot. What is the
shape of this distribution? Interpret the meaning of this shape.
Why would you expect random numbers to be distributed in this way?
Part 4:
Go to the "Mean, median, and standard deviation" web site and click
on "Begin." Work on changing the distribution for this exercise like
we did in the lab on Tuesday, Sept. 27. Keep the range fixed and
make it so each value has at least one observation (each value has a bar
at least "1" tall). Play around to make standard deviation as large
and as small as you can. (This may take some time, but it is fun).
What are the features of distributions that have the greatest standard
deviations, given the constraints of at least one observation per value?
What are the features of distributions that have the smallest standard
deviations?
Draw (by hand) histograms for the distributions you've created with
the largest and smallest standard deviations. There will be a special
prize for those who get the highest and lowest standard deviations in the
class.
What is the standard deviation when all values have the same number
of observations? Does this change when all values have the same number
of observations?