Title: SPSS Basics for Institutional Researchers
1SPSS Basics for Institutional Researchers
- Gayle Fink
- Director of Institutional Research
- University System of Maryland
- gfink_at_usmd.edu
November 30, 2007
2Commonly Asked Questions
- 1. Will I be able to get copies of the slides
after the event? - 2. Is this web seminar being taped so I or others
can view it after the fact?
3Commonly Asked Questions
- 1. Will I be able to get copies of the slides
after the event? - 2. Is this web seminar being taped so I or others
can view it after the fact?
Yes
Yes
www.spss.com/airseries
4Welcome Agenda
- Explore a number of SPSS basic features that make
data analysis easier - Aggregate
- Date/Time Wizard
- Custom Tables
- Each feature will be demonstrated using census
data - Student registration activity file matched with
course characteristics, or - Student demographic file
- Answer typical IR questions with these features
5Demonstration
- If you are not automatically taken to the "Shared
Application" screen during the demonstration,
please click on the "Shared Application" button
at the bottom of your screen.
6SPSS Version and Data File Detail
- SPSS 15.0
- Does not matter what version you are running
features included! - Registration Activity file (Community College)
- Student demographics
- Course information
- Time/Date/Type of Registration
- Instructional delivery/course type
- Student Demographic file (4-Year Institutions)
- Student Demographics
- Major
- Tuition Status
- Multiple Institutions and Multiple Years
7Aggregate Command
- AGGREGATE combines groups of cases in the active
dataset into single cases and creates a new file
or creates new variables in the active dataset
that contain aggregated data. - The values of one or more variables in the active
dataset define the case groups. These variables
are called break variables. - A set of cases with identical values for each
break variable is called a break group. - Aggregate functions (mean, median, sum, etc.) are
applied to source variables in the active dataset
to create new aggregated variables that have one
value for each break group.
8Aggregate Command Syntax Example
- AGGREGATE
- /OUTFILE'c\temp\temp.sav
- /BREAKgender marital
- /age_meanMEAN(age)
- /age_medianMEDIAN(age)
- /income_medianMEDIAN(income).
- AGGREGATE creates a new SPSS-format data file,
temp.sav, that contains two break variables
(gender and marital) and all of the new aggregate
variables. - BREAK specifies gender and marital as the break
variables. In the aggregated file, cases are
sorted in ascending order of gender and in
ascending order of marital within gender. The
active dataset remains unsorted. - Three aggregated variables are created age_mean
contains the mean age for each group defined by
the two break variables age_median contains the
median age and income_median contains the median
income.
9Using Aggregate to Create a Student Demographic
File from a Registration Activity File
Student Demographic File
Registration File By student and course
10Lets Aggregate!
- To Aggregate a Data File
- From the menus choose
- Data Aggregate...
11Lets Aggregate!
- Select one or more break variables that define
how cases are grouped to create aggregated data. - Select one or more aggregate variables.
- Select an aggregate function for each aggregate
variable. - Optionally, you can override the default
aggregate variable names with new variable names,
provide descriptive variable labels, and create a
variable that contains the number of cases in
each break group.
12Lets Aggregate!
Aggregate Functions
13Lets Aggregate!
- Saving Aggregated Results
- Add aggregate variables to the active dataset or
create a new, aggregated data file. - Add aggregated variables to active dataset. New
variables based on aggregate functions are added
to the active dataset. The data file itself is
not aggregated. Each case with the same value(s)
of the break variable(s) receives the same values
for the new aggregate variables. - Create a new dataset containing only the
aggregated variables. The active dataset is
unaffected. - Write a new data file containing only the
aggregated variables. Saves aggregated data to an
external data file. The active dataset is
unaffected.
14Aggregate Example
15Date and Time Wizard
- Why use this?
- Most dates/time in census files are text
- no functionality
- Common dates/time
- Birth date
- Registration date
- Course/Section start and end dates
- Course start/end times
- Suggestion about time
- Military time is easier to manipulate across
applications - Examples
- Checking age calculation
- Establishing N of weeks before day 1 of class a
student registered for a course
16Using the Date and Time Wizard!
- To use the Date/Time Wizard on a Variable
- From the menus choose
- Transform Date/Time Wizard...
17Using the Date and Time Wizard!
- Need to confirm that the Age calculation from the
census extract is calculating age correctly - How to calculate Age?
- Examples
- Current year minus birth year
- Day 1 date minus birth date
- Freeze date minus birth date
- Create a date/time variable from a string
containing a date or time. - Extract a part of a date or time variable.
18Using the Date and Time Wizard!
- Student demographic file we just built with only
the birth date and age. - Convert BIRTH_DATE to a date variable
- Extract BIRTH_YEAR from the new DOB variable
- Calculate different dates and compare to system
calculation!
19Resulting Data file!
20Date and Time Wizard Example
21Custom Tables
- To Build a Table
- Analyze Tables Custom Tables...
- Drag and drop one or more variables to the row
and/or column areas of the canvas pane. - Click OK to create the table.
- To delete a variable from the canvas pane in the
table builder - Select (click) the variable on the canvas pane.
- Drag the variable anywhere outside the canvas
pane, or press the Delete key. - To change the measurement level of a variable
- Right-click the variable in the variable list
(you can do this only in the variable list, not
on the canvas). - Select Categorical or Scale from the pop-up
context menu.
22Custom Tables
23Custom Tables
- What types of variables do you have?
- Categorical. Data with a limited number of
distinct values or categories - Nominal. A variable can be treated as nominal
when its values represent categories with no
intrinsic ranking (for example, the department of
the company in which an employee works). Examples
of nominal variables include region, zip code,
and religious affiliation. - Ordinal. A variable can be treated as ordinal
when its values represent categories with some
intrinsic ranking (for example, levels of service
satisfaction from highly dissatisfied to highly
satisfied). Examples of ordinal variables include
attitude scores representing degree of
satisfaction or confidence and preference rating
scores. - Scale. Data measured on an interval or ratio
scale, where the data values indicate both the
order of values and the distance between values.
24Custom Tables
Which variable is a scale variable? All the rest
are.?
25Custom Tables Example
- Build a multi-year/multi-institution student
demographic profile - For you think about using different
divisions/locations/colleges instead of
institutions - Using a flat file that is sent to State
coordinating board with data from 3 USM
institutions - Demographics/Residency
- Program/Level
- First-time flag
- Attendance Pattern/Credit hours
- Build a fact book trend table with gender,
ethnicity, residency with totals
26Custom Tables
Column Variable Year
Where do you put Institution?
Change Variable Type
Row Variables Gender Ethnicity Residency
27Custom Tables Example
28Quick recap
- Learned how to
- Aggregate
- Use the Date/Time Wizard
- Build a custom table
- Need to take time to play with these features
to become proficient - VERY helpful for turning things around quickly
29Question Answer
- To ask a question over telephone, press 1
- Text questions by using QA tab in lower right
30For More Information
- In case you missed it recorded version and
slides available at www.spss.com/airseries - Product questions? Call SPSS at 1-800-543-2185 or
sales_at_spss.com - Enjoy todays presentation? Please fill out the
post event survey