hh_id | wave | Gender_head | Education_Hhead | Monthly Per_CapitaExp | Poverty_status | Distance(km)_ |
1 | 2002 | 1 | 0 | 130.05 | 1 | 30 |
1 | 2005 | 1 | 0 | 250.20 | 1 | 30 |
1 | 2010 | 1 | 1 | 350.20 | 1 | 30 |
2 | 2002 | 2 | 1 | 45.33 | 0 | 120 |
2 | 2005 | 2 | 1 | 75.0 | 0 | 120 |
2 | 2010 | 2 | 1 | 100.45 | 1 | 120 |
Education_hhead - (0 not educated, 1 educated)
poverty_status - (0- poor, 1- not poor)
Distance(km) - household distance from an industrial cluster.
I want to understand the effect of the closeness of industrial clusters on households.
How can I
1. Run an rd using the distance as my running variable and have a treatment group household within distance 30km (cut off point)
2. Better still conduct a sensitivity analysis to understand the relationship between my indicator variables (per_capita Exp or poverty status) and distance.
3. run an rd plots and hist
4. is it possible to also conduct a Propensity score matching before Identify LATE in the rd Design. (how).
0 Response to regression discontinuity- panel data
Post a Comment