kernelbased
matching, radius matching and mahalanobis metric matching.
Before matching the bias is in the range of 18%–25% and after matching
the bias is quite low and is in the range of 4%–8%. The percentage bias
reduction is in the range of 63%–80%. The percentage bias reduction indicates
that after matching the covariates have been balanced and there
are not many differences among the participants and non-participants
of the community forest management households. Another test
employed to check the matching quality is the value of R2 before and
after matching. In the current analysis, the value of R2 is quite high before
matching and is in the range of 0.415–0.812. The value of R2 is
quite low after matching and is close to zero indicating that after
matching the covariates have been balanced and there are no systematic
differences between participants and non-participants. The joint significance
of covariates is another indicator of covariates balancing. The
joint significance of covariates should always be accepted before
matching and should always be rejected after matching. In the current
analysis the p-value is quite low before matching and is quite high
after matching hence indicating that after matching the participants
and non-participants are not systematically different from each other.
The results regarding covariates balancing are in line with the previous
studies like (Ali and Sharif, 2011, 2012). The Fig. 1 also indicates that covariates
have been balanced and there are not systematic differences
between the participants and non-participants.