Impact Evaluation of Development Interventions by White Howard;Raitzer David A.;

Author:White, Howard;Raitzer, David A.;
Language: eng
Format: epub
Publisher: Asian Development Bank Institute
Published: 2017-08-15T00:00:00+00:00

1 Many interventions that initially appear to be dichotomous may actually be continuous, because the degree of treatment varies within the treated population. For example, road infrastructure will have different effects on travel times and cost, depending on a household’s distance down the road.

2 A caveat is that if there are expectation effects created by the intervention, then these may affect baseline values. For example, people may adjust savings or investment behavior if they know they will be receiving access to microfinance in the near future.

3 To keep this exposition simple, it is assumed that there is a linear relationship. In practice a nonlinear form is tested, since assuming linearity may give the impression of a discontinuity which is not in fact there. However, testing more complex functional forms may require using the whole sample, thus giving weight to observations away from the cutoff.

4 A switching regression is one in which two separate regression equations are estimated, each equation being called a regime. Each observation is assigned to one of the two “regimes.”

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.