SPSS Introductory Workshop

1
SPSS Introductory Workshop

• Humboldt State University
• May 6, 2011

2
Sponsors
College of Arts, Humanities and Social
Sciences http//www.humboldt.edu/cahss/

• and the
• http//www.ssric.org

3
SPSS Help Online

• SPSS for Windows 16.0 A Basic Tutorial by Linda
  Fiddler, Laura Hecht, Edward E. Nelson, Elizabeth
  Ness Nelson, and James Ross.
• Resources to Help You Learn and Use SPSS (UCLA)
• SPSS Tutorials (Texas AM)

4
SPSS

• A statistical package for beginning,
  intermediate, and advanced data analysis
• Other statistical packages include SAS and Stata
• Online statistical packages that dont require
  site licenses include SDA

5
Agenda

• Introduction and Overview
• A Brief Tour of SPSS
• Creating Your Own SPSS Files or Opening Existing
  Datasets
• Transforming data
• Recode
• Compute
• Select If
• Univariate analysis
• Frequencies
• Descriptives
• Explore
• Introduction to Graphics

6
A Brief Tour of SPSS
7
Data View
8
Variable View
Variable Names
Variable Labels
Value Labels
MissingValues
9
Menu Bar
10
The Edit Menu
11
The Edit Menu(continued)
12
The Data Menu
13
The Transform Menu
14
The Analyze Menu
15
The Graphs Menu
16
Opening SPSS

• Go to start and find SPSS for Windows or look for
  the SPSS icon on your desktop.
• Click on SPSS 18.0 for Windows in
• the Start menu or double click on the icon.
• Youll need to update your SPSS license every
  year (or your school technician will do it for
  you Faculty/staff can load software on home
  computers).

17
Opening an Existing File

• Often you will want to open a data set that you
  got from someplace else.
• These files will usually be in the form of a
• SPSS portable file
• SPSS data file
• Raw data file with a SPSS syntax file
• Raw data file without a syntax file

18
SPSS Files and Extensions

• Portable file -- .por
• Data file -- .sav
• Output file -- .spo
• Syntax file -- .sps

19
Opening a Portable (.por) file

• Click on the open yellow folder
• to open a new file.
• Change file type to .por
• Browse to where the portable file you want to
  open is located and double click on that file.

20
Opening SPSS Syntax Window
21
Opening a Text file

• Click on File gt Read Text Data
• In the Open Data
• window change
• file type

22
Opening an Existing SPSS System File Example
the 2010 General Social Survey

• In browser, go to http//www.norc.org/GSSWebsite/
  
• Select Download and SPSS Format

23
Opening an Existing SPSS System File Example
the 2010 General Social Survey

• Select 2010

24
Opening an Existing SPSS System File Example
the 2010 General Social Survey

• Select OK to Save File
• Double Click on 2010.sav file

25
Saving an Existing SPSS System File Example the
2010 General Social Survey

• Go to File and Save As and select Variables
  button
• Select Drop All

26
Saving an Existing SPSS System File Example the
2010 General Social Survey

• Select variables of interest
• Age
• Cappun
• Degree
• Educ
• Grass
• Hrs1
• Hrsrelax
• Income06
• Maeduc

• Marital
• Masei
• Paeduc
• partyid
• Pasei
• Realinc
• Relig
• Sei
• Sex

27
Saving an Existing SPSS System File Example the
2010 General Social Survey

• Select Continue and Save (to either desktop
  or your own flash drive)
• We will continue to work with this same GSS 2010
  data file during the workshop

28
Opening an Existing SPSS System File Example
the 2008 General Social Survey

• Open the file from network

29
Opening an Existing SPSS System File (continued)

• Opening the file
• Open from desktop (double-click) OR
• Open SPSS first (as you would any windows
  program), then navigate to file.

30
Opening an Existing SPSS System File (continued)

• Move cursor to
• File
• Open
• Data
• Click on Data
• Navigate to file location (e.g., desktop) and open

31
Transforming Data

• We can transform variables by recoding, i.e.,
  combining categories in an existing variable into
  fewer categories.
• We can also transform variables by creating new
  variables out of existing variables.
• We can select particular cases and analyze only
  these cases.

32
Recoding into Different Variables

• Click on Transform gt Recode gt Into different
  variables.
• Select the variable you want to recode. age

• Start by giving the new variable a new name
  (age1)
• Click on Change
• Click on Old and New Values

33
Recoding age into AGE1

• Use Range (fourth option down) to recode as
  follows. Remember to click on Add after
  entering each recode.
• 18 to 29 1
• 30 to 49 2
• 50 to 69 3
• 70 to 89 4
• Click Continue
• And then OK.

34
Assign Value Labels to the Four Categories of
AGE1

• Select the Variable View tab.
• Scroll down the variables to age1 (at the bottom
  of the list).
• In the Values column of age1 click on the small
  gray box.
• Enter the first value followed by its label.
  Click Add.
• Enter remaining 3 values.
• Then click on OK.

18 to 29 1 30 to 49 2 50 to 69 3 70 to 89
4
35
Exercises for Recoding

• Now recode income06 and call the new variable
  income2
• This time use 8 categories under 10K,
• 10K to under 20K, 20K to under 30K,
• 30K to under 40K, 40K to under 50K,
• 50K to under 60K, 60K to under 75K,
• and 75K and over
• Add the value labels
• Run a frequency distribution for income2 and
  check to make sure that you recoded it correctly
  by comparing the unrecoded and recoded frequency
  distributions

36
Creating a New Variable with Compute

• Lets create a new variable and call it timewaste
  which is the percentage of relaxation time
  (hrsrelax) devoted to watching TV (tvhours)
• Click on Transform gt Compute
• Enter the new variable name (timewaste) into the
  Target Variable box.
• Enter the formula for
• this new variable (100tvhours/hrsrelax)
• into the Numeric
• Expression box.
• Click on OK

37
Caution!

• If, for any case, any of the variables used to
  create a new variable has a missing value, the
  new variable will automatically be assigned a
  missing value as well.

38
Exercise for Compute

• The data file includes indexes of socio-economic
  status for respondents (sei), their mothers
  (masei) and their fathers (pasei).
• Create an index of mobility by subtracting sei
  from an average of masei and pasei.

39
10 MINUTE BREAK!
40
Using Select Cases to Select Specific Cases for
Analysis

• Lets select only Protestants for further
  analysis.
• Click on Data gt Select Cases.
• Click on If condition is satisfied and then
• on the If button below it.

41
Using Select Cases to Select Specific Cases for
Analysis

• Select the variable relig ( Rs RELIGEOUS
  PREFERENCE) and move it into the box
• on the right.
• In this box, enter the
• expression relig 1.
• Click on Continue
• and on OK.

42
Using Select Cases to Select Specific Cases for
Analysis

• Note all cases not accepted
• are crossed out on the left.
• Again click on
• Data gt Select Cases.
• Click on all and then
• OK.

43
Important Note on Using Select Cases

• When you are finished using Select Cases and want
  to revert to using all the cases be sure to click
  on Data gt Select Cases and select All cases.
  Then click on OK
• If you dont do this, you will continue to use
  only those cases you last selected

44
Exercises for Select Cases

• Select all males (1 on the variable sex) and do a
  frequency distribution for the variable partyid
  (political party identification)
• Now select all females (2 on the variable sex)
  and run a frequency distribution for partyid
• Is there a gender gap in party identification.
  How large is it?
• Note same thing could have been done with
  Crosstabs

45
Univariate Analysis

• Now that we know how to open existing files and
  transform variables, were ready to begin
  analyzing data
• Univariate analysis refers to analyzing variables
  one-at-a-time

46
Types of Univariate Analysis Procedures

• Frequencies
• Descriptives
• Explore

47
Frequencies

• Go to
• Analyze gt Descriptive Statistics gt Frequencies
• Select age1 and age
• Notice Statistics and Charts buttons at upper
  right and Display frequencies tables check-box at
  lower left

48
Frequencies Statistics

• Click on Statistics
• Select the statistics you want
• Click on Continue

49
Frequencies Charts

• Click on Charts
• Select Histograms and check With normal curve
• Click on Continue
• Click on OK

50
Frequencies Output - Tables
51
Frequencies Output - Statistics
52
Frequencies Output - Charts
53
Exercises for Frequencies

• Run frequency distributions for hrsrelax and
  tvhours with appropriate statistics and charts
• Run frequency distributions for cappun, grass,
  and gunlaw with appropriate statistics and charts

54
Descriptives

• Click on
• Analyze gt Descriptive Statistics gt Descriptives
• Select age and educ
• Click on Options and select the statistics you
  want and then click on Continue and OK

55
Descriptives (continued)
56
Exercise for Descriptives

• Use Descriptives to compute the following
  statistics for hrs1 (hours worked per week)
• Mean
• Standard deviation
• Variance
• Skewness
• Kurtosis

57
More Exercises for Descriptives

• Use Descriptives to compute the mean for educ,
  maeduc, and paeduc
• Who has the most education respondents or their
  parents?
• Who has the most education mothers or fathers?

58
Explore

• Click on
• Analyze gt Descriptive Statistics gt Explore
• Select hrs1 and put it in the Dependent List
• In the Display box on the lower left, click on
  Both

59
Explore (continued)

• Click on Statistics
• Select the statistics you want
• Click on Continue

60
Explore (continued)

• Click on Plots
• Select the plots you want
• Click on Continue
• Click on OK

61
Explore (continued)
62
Explore (continued)
63
Graphs Bar Charts

• Click on Graphs gt Legacy Dialogs gt Bar

64
Graphs Bar Charts(continued)

• Click on Simple
• Click on Define

65
Graphs Bar Charts(continued)

• Click on of cases
• Drag or move marital to second box on right
• Click on OK

66
Graphs Pie Charts

• Click on Graphs gt Legacy Dialogs gt Pie

67
Graphs Pie Charts

• Click on Define

68
Graphs Pie Charts

• Click on of cases
• Drag or move marital to second box on right
• Click on OK

69
Graphs Box and Whiskers Plots

• Click on Graphs gt Legacy Dialogs gt Boxplots

70
Graphs Box and Whiskers Plots(continued)

• Drag or move tvhours to first box on right
• Drag or move degree to second box on right
• Click on OK

71
Graphs Box and Whiskers Plots(continued)
Extreme Values (gt3.0 X IQR)
Outliers(1.5 3.0 IQR)
Box (IQR)
Median
Whiskers(lt 1.5 X IQR)
72
Graphs Scatterplots

• Click on Graphs gt Legacy Dialogs gt Scatterplot

73
Graphs Scatterplots(continued)

• Click on Simple Scatter
• Click on Define

74
Graphs Scatterplots(continued)

• Drag or move maeduc to first box on right
• Drag or move paeduc to second box on right
• Click on OK
• Double-click on chart
• Click on Elements and Fit Line at Total

75
Graphs Histograms

• Click on Graphs gt Legacy Dialogs gt Histogram

76
Graphs Histograms(continued)

• Drag or move realinc to first box on right
• Check Displaynormal curve
• Click on OK

77
Feedback?

• Please fill out an evaluation form.
• Thanks!