SyntheticControlMethods
SyntheticControlMethods copied to clipboard
OscarEngelbrektson
A Python package for causal inference using Synthetic Controls
First of all, THANK YOU for putting together this awesome package with clear documentation! I am trying to follow along with your example code, and have tried with the german_reunification...
I'm trying to run a synthetic control model with my data and I'm getting the error message below. Can someone help me, please? Traceback (most recent call last): File "C:\ProgramData\Anaconda3\lib\site-packages\SyntheticControlMethods\main.py",...
Flatten the loss returned from method total_loss so that the code could run with scipy>=1.5.0
@OscarEngelbrektson Thanks for developing this great package. One issue I've had with this package is that I only got 2 years before intervention, which is so insufficent that lead to...
I found `np.apply_along_axis(np.std, 0, big_dataframe)` was a bug here. The outcome will become something like below. ``` array([[inf, inf, inf, inf, inf, inf, inf, inf, inf, inf, inf, inf, inf,...
The README says: "Lastly, let Z1 be a (1 x T0) matrix containing every observation of the outcome for the treated unit in the pre-treatment period. Similarly, let Z0 be...
Hello! One issue I've had with this package is that there's no built in way (that I can see) of saving figures generated by .plot() commands, potentially by passing a...
@OscarEngelbrektson Thanks for developing this great package. Qualitatively, What is the causal **interpretation** for the pointwise and cumulative counterfactual prediction plots given in the Germany example ? Kindly elaborate For...
The weight vector, sc.original_data.weight_df, obtained from the model is not consistent across multiple runs although the Units used for constructing synthetic control are consistent. random_seed is passed while creating Synth...
Hello, When I want to copy stata's code and realize it by SyntheticControlMethods, I found it hard to make such actions. Thus I come here to see if any know...
Metadata
Owner
Metadata
A Python package for causal inference using Synthetic Controls