This thesis estimates the treatment effect of inflation targeting adoption on inflation, inflation variability, output, and output variability for 25 explicit inflation targeting countries. I implement the propensity score matching methodology that takes into account the problems of non-experimental nature, such as selection bias or selection on observable, and allows me to effectively mimic properties of randomized experiment and compute unbiased treatment effect estimates. I introduce a variety of propensity score matching methods that were recently developed in the treatment effect literature, including Nearest Neighbor, Radius matching, Kernel matching, and Inverse Probability Weighting. The results indicate that both industrial and developing inflation targeting countries exhibit lower inflation levels and at the same time higher output growth than non-targeting countries. The estimates are however in most cases statistically insignificant. Moreover, it appears that both industrial and developing countries achieve combination of lower inflation variability and output variability compared to non-targeting countries. Nonetheless, majority of the estimates are again statistically insignificant. The results are to a small extent sensitive to the choice of propensity score matching method. Radius matching with tight calipers (r=0.005, r=0.001) tends to provide the most reliable estimates. Balancing properties of the models are reasonable and compared to the previous research the standardised biases are quantitatively better.
| Identifer | oai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:262347 |
| Date | January 2016 |
| Creators | Kamarád, Martin |
| Contributors | Potužák, Pavel, Kadeřábková, Božena |
| Publisher | Vysoká škola ekonomická v Praze |
| Source Sets | Czech ETDs |
| Language | English |
| Detected Language | English |
| Type | info:eu-repo/semantics/masterThesis |
| Rights | info:eu-repo/semantics/restrictedAccess |
Page generated in 0.0017 seconds