Evaluation Toolkit:
Statistical Analysis
 
1) Nonrandomized Group Data Analysis [pdf
Version] [HTML Version]
This paper provides guidance on
which analysis techniques work best under different data
conditions and makes recommendations
to researchers on how to choose among the
various techniques. The
authors use data from CSAP's Workplace Managed Care (WMC)
initiative to compare the
performance of the various methods commonly applied in quasi-
experimental and group assignment
designs.
2) Primer on Statistical Power [pdf
Version] [HTML Version]
This paper provides summary
information about statistical power. A good understanding of
statistical power is important
because it provides a rational basis for establishing sample
sizes for the various components of
a study, and it facilitates a more definitive
interpretation of the results at the
end of the study.
3)
Propensity Analysis [pdf]
These presentation slides were used
as part of CSAP's Workplace Managed Care (WMC)
initiative to help grantees with
nonrandomized designs and enhance their ability to make
causal inferences by using
propensity
scores.
|
