Social Work Statistics
Correlated Groups T-test
Also commonly referred to as
the Paired Samples T-test
New dataset
These problems require a different type of data than what is available in GSS2000. We need data where the same measure is administered multiple times.
The data set that we will used is called Omaha.sav, and can be downloaded from the course web site.
This data set contains a variety of attitude and functioning scales for a group of domestic violence victims from Omaha, taken one week, six months, and twelve months after the incident.
Links to the description of the project and download of the code book at ICPSR are on the course data download page.
Coding scheme
To make the data amenable to the types of problems we will use it for, variables have been renamed and recoded.
There are four types of measures:
Variables on self esteem begin with the letters "se"
Variables on depression begin with the letters "dep"
Variables on locus of control being with "loc"
Variables on fears begin with the letters "fear"
The time period for the measure is designated by the number following the initial letters:
1 indicates 1 week after the incident, e.g. fear1, loc1
6 indicates 6 months after the incident, e.g. fear6, loc6
12 indicates 12 months after the incident, e.g. fear12, loc6
The specific content item is represented by an underscore followed by a number:
fear1_1 is the item "I have spells of terror/panic (1 week)"
fear6_4 is the item "At times I fear for my life (6 months)"
Analyzing data
We will analyze relationships among various measures at different time periods, e.g. fear1_1 versus fear6_1, fear1_1 versus fear12_1, and fear6_1 versus fear12_1.
All of these items are rating scales, e.g. strongly disagree, disagree, agree, strongly agree. All have been recoded so that the most positive rating has the highest code number.

下一页