Hello. I am conducting a project examining the change in value of residential properties in areas before and after the certification of nearby commercial properties as LEED certified (sustainability certification), compared to control groups of residential properties that are not near these certified buildings.
I am controlling for property type (apartment, detached, terrace etc) and bedroom amount (1 bed - 4+ bed). I am currently using the xtdidregress command for the analysis, with a sample line of command shown below:
xtdidregress (VALUE onebedroom apartment) (treated), group(Location_numeric) time(Quarters)
(The panel is xtset by Location_numeric as the identifier variable only. It is an unbalanced panel. I cannot set a time variable too, as each combination of identifier and time should occur, at most, once and this is not the case for this dataset. For this dataset, the panel variable has repeated observations for each quarter as it has to account for different property types and bedroom amounts within the same location.)
where VALUE = the average quarterly rental value of properties.
onebedroom and apartment = indicators for bedroom amount and property type respectively.
treated = 1 for the treated location post treatment time, 0 for treated location pre treatment and control group.
Location_numeric = all locations in my dataset
time = all time periods (38 quarters) in my dataset.
Thankfully, the xtdidregress command is working and I am obtaining results.
I am just wondering: is there a better way of conducting this analysis? Are there more controls that I should be including? Any controls that I add for time are dropped due to collinearity issues with the time(Quarters) variable. Aside from estat ptrends, trendplots, granger, are there any other robustness checks I should be running?
Many thanks,
Hugh
Some code
I am controlling for property type (apartment, detached, terrace etc) and bedroom amount (1 bed - 4+ bed). I am currently using the xtdidregress command for the analysis, with a sample line of command shown below:
xtdidregress (VALUE onebedroom apartment) (treated), group(Location_numeric) time(Quarters)
(The panel is xtset by Location_numeric as the identifier variable only. It is an unbalanced panel. I cannot set a time variable too, as each combination of identifier and time should occur, at most, once and this is not the case for this dataset. For this dataset, the panel variable has repeated observations for each quarter as it has to account for different property types and bedroom amounts within the same location.)
where VALUE = the average quarterly rental value of properties.
onebedroom and apartment = indicators for bedroom amount and property type respectively.
treated = 1 for the treated location post treatment time, 0 for treated location pre treatment and control group.
Location_numeric = all locations in my dataset
time = all time periods (38 quarters) in my dataset.
Thankfully, the xtdidregress command is working and I am obtaining results.
I am just wondering: is there a better way of conducting this analysis? Are there more controls that I should be including? Any controls that I add for time are dropped due to collinearity issues with the time(Quarters) variable. Aside from estat ptrends, trendplots, granger, are there any other robustness checks I should be running?
Many thanks,
Hugh
Some code
Code:
* Example generated by -dataex-. For more info, type help dataex clear input double VALUE long(PropertyType_numeric Location_numeric) float Bedrooms_numeric long Quarters float(treated onebedroom apartment) 1846.71 4 1 4 28 . 0 0 1802.75 4 1 4 30 . 0 0 1798.23 4 1 4 31 . 0 0 1712.27 4 1 2 31 . 0 0 1712.27 4 1 3 31 . 0 0 1823.27 4 1 4 32 . 0 0 1096.45 1 2 4 3 . 0 1 1094.67 1 2 2 3 . 0 1 1150.5 1 2 4 4 . 0 1 1153.71 1 2 2 5 . 0 1 1153.59 1 2 4 5 . 0 1 1171.79 1 2 4 6 . 0 1 1172.47 1 2 2 6 . 0 1 1194.97 1 2 2 7 . 0 1 1194.97 1 2 4 7 . 0 1 1654.97 1 2 2 19 . 0 1 1654.97 1 2 4 19 . 0 1 890.71 4 4 2 1 . 0 0 1019.33 3 4 3 1 . 0 0 1030.92 4 4 5 1 . 0 0 end label values PropertyType_numeric PropertyType_numeric label def PropertyType_numeric 1 "Apartment", modify label def PropertyType_numeric 3 "Semi detached house", modify label def PropertyType_numeric 4 "Terrace house", modify label values Location_numeric Location_numeric label def Location_numeric 1 "Arbour Hill, Dublin 7", modify label def Location_numeric 2 "Aungier Street, Dublin 2", modify label def Location_numeric 4 "Cabra, Dublin 7", modify label values Quarters Quarters label def Quarters 1 "2014Q1", modify label def Quarters 3 "2014Q3", modify label def Quarters 4 "2014Q4", modify label def Quarters 5 "2015Q1", modify label def Quarters 6 "2015Q2", modify label def Quarters 7 "2015Q3", modify label def Quarters 19 "2018Q3", modify label def Quarters 28 "2020Q4", modify label def Quarters 30 "2021Q2", modify label def Quarters 31 "2021Q3", modify label def Quarters 32 "2021Q4", modify
