社會科學領域中，單條件變量的間斷回歸估計方法已被廣泛運用。由單條件變量決定的機制確實廣泛，但許多實證研究更顯示了多條件變量設計的普遍性。再者，文獻在過去著重平均政策效果的估計，而忽略了估計分位數效果可提供的政策資訊。本文針對多條件變量的間斷回歸，提出新的估計方法。此無母數方法可運用於平均效果與分位數效果的估計。根據蒙地卡羅模擬分析，過去方法的表現皆嚴重受到交乘項的納入與條件變量的波動影響。本文提出的估計方法對於所有模擬情況都表現穩定，且其估計結果亦較現有的方法準確。

The estimation methods of regression discontinuity (RD) designs with a single assignment variable have recently been acknowledged to have a wide range of applications in social science. While treatment assignment is often determined by one threshold value, many empirical studies have shown the pervasiveness of RD designs with more than one assignment variable. Moreover, the literature has focused on the average treatment effect and overlooked the interesting perspectives provided by treatment effects at different quantiles of the outcome distribution. In this paper, we propose new approaches for RD designs with multiple assignment variables. The approaches allow nonparametric estimation and could be applied to estimating average treatment effects and quantile treatment effects. Based on our Monte Carlo simulation study, we suggest that the performance of the existing approaches is sensitive to the interaction terms in data generating processes as well as large variations in assignment variables. Our new approaches produce robust and more accurate estimates compared to the existing approaches with respect to all scenarios.

1 Introduction (page 2~5)
2 Literature Review (page 6~23)
2.1 ATE with One Assignment Variable (page 7~12)
2.2 QTE with One Assignment Variable (page 12~14)
2.3 RD Designs with Multiple Assignment Variables (page 14~23)
3 The Proposed Two-Dimensional Approaches (page 24~29)
3.1 The Intersection Approach (page 24~27)
3.2 The Average Approach (page 27~29)
4 Simulation Designs and Results (page 29~37)
4.1 Simulation Results of ATE (page 31~35)
4.2 Simulation Results of QTE (page 35~37)
5 Concluding Remarks (page 37~38)
References (page 38~42)
Appendix (page 43~70)

Angrist, J. D. and A. B. Krueger (1999): “Empirical strategies in labor economics,” Handbook of labor economics, 3, 1277–1366.
Angrist, J. D. and V. Lavy (1999): “Using Maimonides’ Rule to Estimate the Effect of Class Size on Scholastic Achievement*,” The Quarterly Journal of Economics, 114, 533.
Becker, S. O., P. H. Egger, and M. Von Ehrlich (2013): “Absorptive capacity and the growth and investment effects of regional transfers: A regression discontinuity design with heterogeneous treatment effects,” American Economic Journal: Economic Policy, 5, 29–77.
Black, S. E. (1999): “Do better schools matter? Parental valuation of elementary education,” The Quarterly Journal of Economics, 114, 577–599.
Chiang, H. D. and Y. Sasaki (2016): “Causal Inference by Quantile Regression Kink Designs,” arXiv preprint arXiv:1605.09773.
Choi, J. and M. Lee (2015): “Regression discontinuity with multiple running variables allowing partial effects,” in World Congress Meeting of the Econometric Society at Montreal.
Choi, J.-y. and M.-j. Lee (2016): “Regression discontinuity: review with extensions,” Statistical Papers, 1–30.
Dee, T. (2012): “School turnarounds: Evidence from the 2009 stimulus,” Tech. rep., National Bureau of Economic Research.
DesJardins, S. L. and B. P. McCall (2008): “The impact of the gates millennium scholars program on the retention, college finance-and work-related choices, and future educational aspirations of low-income minority students,” Unpublished Manuscript.
Fan, J. and I. Gijbels (1992): “Variable bandwidth and local linear regression smoothers,” The Annals of Statistics, 2008–2036.
——— (1996): Local polynomial modelling and its applications: monographs on statistics and applied probability 66, vol. 66, CRC Press.
Goodman, J. (2008): “Who merits financial aid?: Massachusetts’ Adams scholar- ship,” Journal of public Economics, 92, 2121–2131.
Hahn, J., P. Todd, and W. Van der Klaauw (2001): “Identification and Estimation of Treatment Effects with a Regression-Discontinuity Design,” Econometrica, 69, 201–209.
Han, H.-W., H.-M. Lien, and T.-T. Yang (2016): “Patient Cost Sharing and Healthcare Utilization in Early Childhood: Evidence from a Regression Discontinuity Design,” .
Ha ̈rdle, W. (1990): Applied nonparametric regression, 19, Cambridge university press.
Ha ̈rdle, W. and O. Linton (1994): “Applied nonparametric methods,” Handbook of econometrics, 4, 2295–2339.
Hoekstra, M. (2009): “The effect of attending the flagship state university on earnings: A discontinuity-based approach,” The Review of Economics and Statis- tics, 91, 717–724.
Huang, P.-C. and T.-T. Yang (2016): “The Effects of Extended Unemployment Benefits: Evidence from a Regression Discontinuity Design (Latest version available here),” .
Imbens, G. and K. Kalyanaraman (2012): “Optimal bandwidth choice for the regression discontinuity estimator,” The Review of economic studies, 79, 933–959.
Imbens, G. and T. Zajonc (2011): “Regression discontinuity design with multiple forcing variables,” Report, Harvard University.[972].
Imbens, G. W. and T. Lemieux (2008): “Regression discontinuity designs: A guide to practice,” Journal of econometrics, 142, 615–635.
Lee, D. S. and T. Lemieux (2010): “Regression discontinuity designs in eco- nomics,” Journal of economic literature, 48, 281–355.
Lee, M.-j. (2000): “Median treatment effect in randomized trials,” Journal of the Royal Statistical Society: Series B (Statistical Methodology), 62, 595–604.
Ludwig, J. and D. L. Miller (2007): “Does Head Start improve children’s life chances? Evidence from a regression discontinuity design,” The Quarterly journal of economics, 122, 159–208.
Martorell, P., I. McFarlin Jr, and Y. Xue (2014): “Does Failing a Placement Exam Discourage Underprepared Students from Going to College?” Education Finance and Policy.
McCrary, J. and H. Royer (2003): “Does Maternal Education Affect Infant Health? A Regression Discontinuity Approach Based on School Age Entry Laws,” Unpublished manuscript, November.
Papay, J. P., R. J. Murnane, and J. B. Willett (2014): “High-school exit examinations and the schooling decisions of teenagers: Evidence from regression- discontinuity approaches,” Journal of research on educational effectiveness, 7, 1– 27.
Porter, J. (2003): “Estimation in the regression discontinuity model,” Unpub- lished Manuscript, Department of Economics, University of Wisconsin at Madi- son, 5–19.
Porter, K. E., S. F. Reardon, F. Unlu, H. S. Bloom, and J. R. Cimpian
(2017): “Estimating causal effects of education interventions using a two-rating regression discontinuity design: Lessons from a simulation study and an application,” Journal of Research on Educational Effectiveness, 10, 138–167.
Reardon, S. F. and J. P. Robinson (2012): “Regression discontinuity designs with multiple rating-score variables,” Journal of research on Educational Effectiveness, 5, 83–104.
Robinson-Cimpian, J. P. and K. D. Thompson (2016): “The Effects of Changing Test-Based Policies for Reclassifying English Learners,” Journal of Policy Analysis and Management, 35, 279–305.
Ruppert, D. and M. P. Wand (1994): “Multivariate locally weighted least squares regression,” The annals of statistics, 1346–1370.
Snyder, S. E. and W. N. Evans (2006): “The effect of income on mortality: evidence from the social security notch,” The Review of Economics and Statistics, 88, 482–495.
Thistlethwaite, D. L. and D. T. Campbell (1960): “Regression-discontinuity analysis: An alternative to the ex post facto experiment,” Journal of Educational psychology, 51, 309–317.
Van der Klaauw, W. (2002): “Estimating the effect of financial aid offers on college enrollment: A regression–discontinuity approach,” International Economic Review, 43, 1249–1287.
Wong, V. C., P. M. Steiner, and T. D. Cook (2013): “Analyzing regression discontinuity designs with multiple assignment variables: A comparative study of four estimation methods,” Journal of Educational and Behavioral Statistics, 38, 107–141.