Experiments and Natural Experiments

Further a comparison of 8 we actually define the

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: The employment variable measured in the surveys, however, was based on calendar months. A participant whose 12-month period started on January 21st, for example, would have until January 21st of the following year to qualify. However, “Month 1” for that person would be the January in which random assignment occurred. If he or she found a full-time job in the first three weeks of the second January, full-time employment would have been coded as starting in Month 13. 9 At Month 14, all program group members who could qualify for the supplement would have qualified for it. However, only a subset of eligible program group members were typically working in any given month, since take-up group members were free to leave full-time work without forfeiting their supplement eligibility. -14- Source: Riddell and Riddell (2006) Figure 1: Employment Rates, High School Upgrading Sample 1 0.6 0.5 0.4 0.3 Upgraders 0.2 Non-upgraders 0.1 0 -12 -10 -8 -6 -4 -2 1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39 41 43 45 47 49 51 53 Month Figure 2: Hourly Wages, High School Upgrading Sample 1 11 10 9 8 7 6 Upgraders Non-upgraders 5 4 -12 -10 -8 -6 -4 -2 1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39 41 43 45 47 49 51 53 Month -34- 1764 D. CARD AND D. R. HYSLOP 1.0 0.9 0.8 < 0.7 0 o ? 0.6 U 0.5 0.4 0.3 0.2 0 12 6 18 24 30 36 42 48 54 60 66 Months Since Random Assignment FIGURE .-Decomposition of predicted IA of eligible treatments. 9 work and leaving IA during the eligibility window (plotted as a dotted line with squares). Although the establishment treatment effects peak just after 0.04 Predicted ,, / Actual -0.04 1 ., O -0.08 \Vx'r \ -0.12- i -0.16 0 6 12 . r95% I 18 Ii 24 30 Confidence Interval and lower shown) -'(upper i^ I iI 36 42 48 Months Since Random Assignment FIGURE 10.-Actual and predictedtreatmenteffects. 54 60 66 Fortin – Econ 560 Lecture 1C They are then able to simulate the impact of alternative eligibility on welfare entry and exit rates among those who achieved eligibility and the simulation suggests that allowing more time for people to establish eligibility would have led to at most a 20% larger program impact in months 18-45 and also would have shifted the peak program impact to the right somewhat. 3. Quasi-Natural experiments a. Lottery winners Imbens, Rubin, and Sacerdote (2001) analyze the effects of the magnitude of lottery prizes on earnings, consumption, and savings using an original survey of people playing the lottery in Massachusetts in the mid-1980's. Under the underlying assumption that among lottery winners the magnitude of the prize is randomly assigned, they address the problem of identifying exogenous variation in unearned income by exploiting the randomized assignment of large amounts of money over long periods of time through lotteries. Fortin – Econ 560 Lecture 1C Caveats: o the population of lottery players is not necessarily representative of the U.S. population, with middle-aged people with lower incomes being overrepresented. o responses to lottery prizes may not be typical of responses to other form...
View Full Document

Ask a homework question - tutors are online