Dear all,
I am using the natural experiments methodology and
calculating difference-in-difference estimators for
different cohorts of children in different treatment
areas.
Yit= b1 + b2 (Cit) + b3 (Tit) + b4 (CTit)+ e
I want to see the effect of the treatment on young
cohorts and wonder if I have enough observations to
split my sample in 5 cohorts and 4 areas (3 treatment
areas + 1 control) and then run my diffs-diffs
estimation for each treatment/cohort.
my total sample includes 14,000 children spread shown
in the following table:
Cohort
District 0 1 2 3 4 5 Total
Treatment 1 152 292 703 949 892 799 3,787
Treatment 2 95 173 478 608 575 504 2,433
Treatment 3 186 403 975 1,230 1,211 1,009 5,014
Control 118 246 626 823 745 642 3,200
Total 551 1,114 2,782 3,610 3,423 2,954 14,434
I wonder if I could use sampsi:
mean1=cohort0 mean2=cohort5
sampsi .0270862 -1.122313, p(0.90) sd1(1.867671)
sd2( 1.340558)
Estimated sample size for two-sample comparison of
means
Test Ho: m1 = m2, where m1 is the mean in population 1
and m2 is the mean in population 2
Assumptions:
alpha = 0.0500 (two-sided)
power = 0.9000
m1 = .027086
m2 = -1.12231
sd1 = 1.86767
sd2 = 1.34056
n2/n1 = 1.00
Estimated required sample sizes:
n1 = 43
n2 = 43
or I should be using the mean of cohort0 in treatment
area1 Vs mean cohort0 in control area?
thanks
Gaby
Gaby Guerrero Serdan
Deparment of Economics
Royal Holloway, University of London
TW20 OEX
Egham, Surrey
England, UK
http://www.rhul.ac.uk/economics/About-Us/postgrads.html
http://www.flickr.com/photos/49939890@N00/show/
Tel: +44 7912657259
____________________________________________________________________________________
Be a better friend, newshound, and
know-it-all with Yahoo! Mobile. Try it now. http://mobile.yahoo.com/;_ylt=Ahu06i62sR8HDtDypao8Wcj9tAcJ
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
