A colleague once to compare effects of welfare reform on urban and rural
women. He has the proportion of single women with no children who are
employed in rural counties and the corresponding proportion of single women
with no children who are employed in urban counties. He has the same two
proportions for single women who have children. He is using the CPS data and
has between 1,100 and 5,000 women for each proportion. He has these
p;proportions for 1990(?) before the welfare reform and 2000.
I don't have the data, but it looks like this.
URBAN COUNTIES
1990 2000 diff
% no kids working 80% 82% 2%
% with kids work 42% 62% 20%
The difference of the difference is 18%, so single mothers increased labor
force participation more than single women who were not mothers.
They have the same data for rural counties and lets say the difference of
difference for rural counties is 10%.
Thus, the difference of difference of difference is 8% meaning that in urban
counties, after welfare reform mothers increased laborforce participation by
this much more than happened in rural counties. If this were true, they
would argue that welfare reform had less influence in rural counties.
QUESTION--How do you test this difference of difference of difference of a
proportion? Each sample is independent and between 1,000 and 5,000 women in
their state.
Alan Acock
Alan C. Acock
[EMAIL PROTECTED]
[EMAIL PROTECTED]
http://www.orst.edu/dept/hdfs/acock/
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
. http://jse.stat.ncsu.edu/ .
=================================================================
