statistics
SPSS Assignment 1
Part A
You will be entering the scores showing in the table below into SPSS.
Table:
PatientID Gender Age Measured Cholesterol
1 Male 44 254
2 Female 35 240
3 Male 41 279
4 Female 31 284
5 Male 61 315
6 Female 61 250
7 Female 44 298
8 Male 58 384
9 Female 52 310
10 Male 52 337
11 Female 52 367
12 Male 40 273
13 Female 49 273
14 Female 34 314
15 Male 37 243
Specifically, do the following:
a. Start SPSS
b. Indicate that you want to “New Dataset” on the Welcome to IBM SPSS Statistics
window.
c. Click on the “Variable View” tab
d. Name the variables. Give Gender and Measured Cholesterol the name Sex and
Cholesterol respectively. Keep the other variable names the same on the table above.
e. Label the variables for the variables you changed their names. Give them the label the
Gender and Measured Cholesterol.
f. Assign the variables. For Gender variable, go to Values column, double click the cell and
assign zero (0) value for Female label and one (1) value for Male label.
g. Switch to the “Data View” screen in the “Data Editor”
h. Type in the scores shown in the table above.
i. Check the accuracy of your entries.
j. Save the data set by clicking the floppy disk image on the toolbar, top of the “Data
Editor”, giving it name Patients Measured Cholesterol.
Part B
You will be running descriptive and frequency statistics and report the outputs for the created
Patients Measured Cholesterol dataset in Part A.
Specifically, do the following for descriptive statistics:
a. Select “Variable View” and ensure that “Scale” appears in the “Measure” column
b. Click on “Data View” and “Analyze” near the top of the screen
c. Go to “Descriptive Statistics”, and click the “Descriptives” on popped up window
d. Get Descriptive Statistics for Age and Cholesterol variables.
e. Report the output.
Specifically, do the following for frequency statistics:
a. Click on “Data View” and “Analyze” near the top of the screen
b. Go to “Descriptive Statistics”, and click the “frequencies” on popped up window
c. Get frequencies for Age and Cholesterol variables, but don’t forget to click the
“Statistics” button on frequencies window and select mean, median, mode, standard
deviation, and variance.
d. Click Ok.
e. Report the output.
Based on reported descriptive and frequency statistics outputs, answer the following questions.
1) What are mean, mode and median statistics for Age and Cholesterol?
2) According to mean, mode and median statistics, what kind of distributions we should
expect to have for Age and Cholesterol variables?
3) What are the standard deviations and variances for Age and Cholesterol?
4) Is there any relationship between standard deviation and variance statistics? Please
explain your answer.
Part C
You will be creating a histogram and boxplot graphs for the Cholesterol variable in the
created Patients Measured Cholesterol dataset in Part A.
Specifically, do the following for histogram
a. Click on “Data View” and “Graphs” near the top of the screen
b. Go to “Chart Builder” and select “Histogram” on the popped up window under “Gallery”
c. Drag the “Simple Histogram” to “Chart Preview” area and drop it
d. Drag the Cholesterol variable from “Variable” section to “X-axis of the histogram.
e. Click Ok.
f. Report the graph
Specifically, do the following for boxplot
a. Click on “Data View” and “Graphs” near the top of the screen
b. Go to “Chart Builder” and select “Boxplot” on the popped up window under “Gallery”
c. Drag the “Simple Boxplot” to “Chart Preview” area and drop it
d. Drag the Cholesterol variable from “Variable” section to “Y-axis of the graph.
e. Drag the Sex variable from “Variable” section to “X-axis of the graph.
f. Click Ok.
g. Report the graph
Based on reported graphs, answer the following questions.
1) Are there any outliers for Cholesterol variable? Please explain your answer.
2) According to the created histogram for Cholesterol variable, what can you say about the
distribution of the variable? Does it support your answer in Part B question 2?
3) According to the created boxplot, what can you say about female and male distributions?
