Comments (4)
I just want to confirm that this bug is still ongoing and that an implementation of the suggestion by @mefergus does indeed work (i.e. wrap the variable Pred in abs() for line 248). I have forked the package and you can find it here: https://github.com/vector-news/CausalImpact and you can install it using devtools::install_github("vector-news/CausalImpact")
I have also opened a pull request to fix this issue, which you can see here: #60. Thank you @mefergus and others for looking into this issue. Hopefully, it will be resolved for future versions.
from causalimpact.
Hi there, this will be resolved in the upcoming CausalImpact 1.3.
from causalimpact.
It may be sufficient to issue a warning when Pred is negative -- further consideration reminds me that working with relative measures "around" zero is fundamentally problematic.
from causalimpact.
Bump I encountered this too.
If the expected impact is negative but the intervention impact is positive, the relative response value stops making sense. For example expected = -0.00041, response = 0.00057, the model outputs -239% when it should be +239%.
from causalimpact.
Related Issues (20)
- Statistically Testing the post-period two series or testing the Difference equals zero HOT 1
- `Plot` function cause R to crash for no particular error message HOT 3
- CausalImpact is masking the 'select' function from dplyr HOT 1
- BoomSpikeSlab installation failed | -DNDEBUG does not search in the correct /Boom/include directory HOT 1
- how to input control time series in causal impact
- multiple caampaign effects
- CausalImpact Simulation data HOT 1
- Error during installation - fails to install bsts HOT 4
- Effect of an intervention that took place during separate periods
- Error installing BoomSpikeSlab HOT 1
- Adding Gformula Function to Package HOT 3
- I can't get summury from date indexing data: 'NoneType' object has no attribute 'loc' HOT 1
- Testing for the Presence of Autocorrelation?
- Power Analysis for Geo experiments
- Is it possible for support on multivariate analysis (MBSTS)? HOT 1
- Error with Relative effect HOT 1
- Rationale for explicit bsts parameters in `CausalImpact::ConstructModel` for StaticRegression
- CausalImpact do not works at all HOT 1
- How coefficients work?
- Can I smooth the time series data before running the CausalImpact package
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from causalimpact.