Dear Statalisters,
I need some help related to Oster estimates for my OLS estimates.
My code is:
reg ch_malaria toilet_access, independent controls......., i.wealthq i.district, cluster(village)
beta of toilet access= 0.22119 R-sq= 0.29
For coeff. stability test, I want to use Oster estimates. the code i use is psacalc delta imp_san
-------------+----------------------------------------------------------------
delta | 0.00000
-------------+----------------------------------------------------------------
---- Inputs from Regressions ----
| Coeff. R-Squared
-------------+----------------------------------------------------------------
Uncontrolled | 0.66419 0.033
Controlled | 0.22119 0.290
-------------+----------------------------------------------------------------
---- Other Inputs ----
-------------+----------------------------------------------------------------
R_max | 1.000
Beta | 0.220000
Unr. Controls|
-------------+--------------------
. psacalc beta imp_san, rmax(0.35) delta(1)
---- Treatment Effect Estimate ----
| Estimate Sq. difference Bias changes
| from controlled beta direction
-------------+----------------------------------------------------------------
Beta | -1.2722e+31 1.62e+62
Alt. sol. 1 | 0.22119 0 Yes
Alt. sol. 2 |
-------------+----------------------------------------------------------------
---- Inputs from Regressions ----
| Coeff. R-Squared
-------------+----------------------------------------------------------------
Uncontrolled | 0.66419 0.033
Controlled | 0.22119 0.290
-------------+---------------------------------------------------------------
. psacalc beta imp_san, delta(1)
---- Treatment Effect Estimate ----
| Estimate Sq. difference Bias changes
| from controlled beta direction
-------------+----------------------------------------------------------------
Beta | -1.5055e+32 2.27e+64
Alt. sol. 1 | 0.22119 0 Yes
Alt. sol. 2 |
-------------+----------------------------------------------------------------
---- Inputs from Regressions ----
| Coeff. R-Squared
-------------+----------------------------------------------------------------
Uncontrolled | 0.66419 0.033
Controlled | 0.22119 0.290
-------------+----------------------------------------------------------------
---- Other Inputs ----
-------------+---------------------------------------------------------
I am not sure how the interpret the delta, having -ve sign and defining the threshold for delta and R-square.
I would appreciate if i can get some help. I looked for previous posts , but i am still need some explanation on the way i am doing.
I need some help related to Oster estimates for my OLS estimates.
My code is:
reg ch_malaria toilet_access, independent controls......., i.wealthq i.district, cluster(village)
beta of toilet access= 0.22119 R-sq= 0.29
For coeff. stability test, I want to use Oster estimates. the code i use is psacalc delta imp_san
-------------+----------------------------------------------------------------
delta | 0.00000
-------------+----------------------------------------------------------------
---- Inputs from Regressions ----
| Coeff. R-Squared
-------------+----------------------------------------------------------------
Uncontrolled | 0.66419 0.033
Controlled | 0.22119 0.290
-------------+----------------------------------------------------------------
---- Other Inputs ----
-------------+----------------------------------------------------------------
R_max | 1.000
Beta | 0.220000
Unr. Controls|
-------------+--------------------
. psacalc beta imp_san, rmax(0.35) delta(1)
---- Treatment Effect Estimate ----
| Estimate Sq. difference Bias changes
| from controlled beta direction
-------------+----------------------------------------------------------------
Beta | -1.2722e+31 1.62e+62
Alt. sol. 1 | 0.22119 0 Yes
Alt. sol. 2 |
-------------+----------------------------------------------------------------
---- Inputs from Regressions ----
| Coeff. R-Squared
-------------+----------------------------------------------------------------
Uncontrolled | 0.66419 0.033
Controlled | 0.22119 0.290
-------------+---------------------------------------------------------------
. psacalc beta imp_san, delta(1)
---- Treatment Effect Estimate ----
| Estimate Sq. difference Bias changes
| from controlled beta direction
-------------+----------------------------------------------------------------
Beta | -1.5055e+32 2.27e+64
Alt. sol. 1 | 0.22119 0 Yes
Alt. sol. 2 |
-------------+----------------------------------------------------------------
---- Inputs from Regressions ----
| Coeff. R-Squared
-------------+----------------------------------------------------------------
Uncontrolled | 0.66419 0.033
Controlled | 0.22119 0.290
-------------+----------------------------------------------------------------
---- Other Inputs ----
-------------+---------------------------------------------------------
I am not sure how the interpret the delta, having -ve sign and defining the threshold for delta and R-square.
I would appreciate if i can get some help. I looked for previous posts , but i am still need some explanation on the way i am doing.
