(a) Importing
data from the H drive. Let’s
work with the serum creatine phosphokinase data of exercise 2.50 on page 49 in
the text to illustrate importing data which is stored on the H: drive. To do this, open up the Minitab software
package (follow “Start à Programs à Math Applications à
Minitab”). The data from the
Samuels/Witmer text are stored in ://prof_pub/mgb/Stat335/NewWitmerData/Data/,
making sure that “File of type” has “All (*.*)” highlighted, clicking on
the file “Serum-ck.mtp,” and finally clicking on the “Open” and “OK”
buttons. The data values should appear
in the column “C1.” You can get a
histogram of the data by clicking on “Graph” then “Histogram,” then typing “C1”
under “X” (or double clicking on “C1” while the cursor is under “X”), and
hitting the “OK” button. Summary
statistics can be obtained for these data by clicking on “Stat,” then “Basic
Statistics,” then “Display Descriptive Statistics,” and entering “C1” under
“Variables.” Please do not print out
the graphs and output for this exercise (you are charged for printing}, rather,
just use the results you see to answer the first question on the accompanying
Assignment sheet. Once you’re finished,
you can close all the graphs and get a fresh worksheet by highlighting the
first column and clicking “Edit” and “Delete Cells.” You can clear the Session window by highlighting and hitting the
Backspace key.
(b)
Typing in your own data. For
small data sets, typing in the data is not a problem. For example, an ecologist counts the number of moths caught in
ten different traps and obtains the data: 2400, 6500, 320, 2700, 80, 230, 490,
13000, 1200, 300.
1. Type in these data into column “C1” (you
could give the column a name like “Counts” if you’d like) and obtain
descriptive statistics and plots as above.
2. Before proceeding further, please answer the
first part of the second question on the Lab01 assignment.
3. Once this is completed, our goal is to
transform the data using the natural logarithm transformation (called “loge” in
Minitab). Click on “Calc,” then
“Calculator,” enter “c2” after “Store results in variable,” and type “loge(c1)”
under “Expression,” then hit “OK.” The natural log’s of the original counts
will then appear in the second column.
4. Now finish the second exercise, and, once
finished, clear the worksheet as above.
(c)
Having the computer generate random data to
perform a simulation study. Now let’s generate 200 samples of size n
from an exponential distribution with mean = 3.0. With the student version of Minitab, please be aware that you are
limited to 5000 entries in your worksheet.
I
1. To give you and idea of the corresponding
probability histogram (“the population”), type the integers 0, 1, 2, through 20
into the first column.
2. Obtain the probabilities in the second column
by clicking “Calc,” “Probability Distributions,” “Exponential.” In the displayed table make sure that
“probability density” is checked. Enter
“3.0” after “Mean,” then “c1” after “Input column,” then “c2” after “Optional
storage,” and hit “OK.”
3. Then graph these probabilities by clicking
“Graph,” ““Plot,” “Y” is “c2” and “X” is “c1,” then “OK.” Note that our population follows an
exponential curve and is very skewed to the right.
4. Now clear these values, and generate 200
samples of size n = 4 from this population by clicking “Calc,” “Random Data,”
“Exponential,” after “Generate” type “200” to get 200 rows of data (each one is
a sample), after “Store in Column(s),” type “c1-c4,” type “3.0” after “Mean,”
then hit “OK.”
5. Let’s form the sample average of each of
these samples of four integers by clicking “Calc,” “Row Statistics,” clicking
next to “Mean,” “Input variable(s)” are “c1-c4,” and “Store results in” “c5”,
then hit “OK.”
6. Now answer the first part of question 3 of
the Lab01 assignment.
7. Once finished, repeat the above process, but
store the random data in the columns “c1-c9” and put the sample means into
“c10,” and answer the second part of question 3 of the Lab01 assignment.
8. Now repeat the above process, but store the
random data in the columns “c1-c16” and put the sample means into “c17,” and
answer the third part of question 3 of the Lab01 assignment.
9. Finally, to answer the final part of the
third question, repeat the above process for random data stored in columns
“c1-c24” and the sample means stored in column “c25.”