Questions tagged [causalimpact]
CausalImpact R package for estimate the effect of an intervention on a time series.
65
questions
1
vote
0answers
38 views
Logistic Regression Coefficient Intrepretation - Impact On Churn
I am using logistic to see the relationship between churn and minute seen.
I get something like this
...
-1
votes
1answer
46 views
Using CausalImpact to estimate uplift attributed to a promotion for logged-in users
I'm working for an online travel agency, and we've been exploring the use of the causalImpact algorithm for the following problem:
Hotel owners that sell room-...
0
votes
0answers
38 views
R Causal Impact package implementation
I'm trying to apply the CausalImpact R package and have few questions I'd like to clarify before proceeding:
Is the ...
0
votes
0answers
46 views
How to aggregate individual results with CausalImpact
In this answer, the author's suggestion is to:
aggregate the individual MCMC traces and then summarise the result in terms of an expectation and a credible interval
I understand that the MCMC ...
0
votes
1answer
49 views
These summary statements seem contradictory, or have I misunderstood something?
So here's the output summary I got when running an analysis.
This means that, although it may look as though the intervention has exerted a negative effect on the response variable when ...
0
votes
1answer
71 views
Causal Impact: how to show all data points in predicted series? [closed]
This might be a very basic code question, but thank you for your help. I have used the Causal Impact package to run a regression on a data set with 144 monthly observations, cutting at point 88. I ...
2
votes
1answer
167 views
Estimate the time series like an event was never happened
I have data from a website where a specific advertising campaign happened a couple of years ago. What I want to do is to estimate how the signups on that website would have been without that big ...
0
votes
1answer
78 views
Matching subjects with themselves when evaluating short term outcomes
I am considering a simple causal inference scenario; Let's say we want to examine the effect of paracetamol (treatment) on curing headache (outcome).
When performing matching, is it okay to match ...
1
vote
0answers
37 views
Ok to use PSM to create treatment groups and then plug into CausalImpact? [closed]
Is it ok to use propensity score matching to create treatment and control groups and then plug these two time series into CausalImpact to estimate your treatment effect? I might want to do this, for ...
0
votes
1answer
130 views
CausalImpact Conflicting Results - Posterior prob. v Confidence Interval
I'm getting conflicting results from a Causal Impact analysis I'm running. The 95% C.I. indicates that 0 is included and thus the impact is not significant; however the Posterior Probability is <....
1
vote
0answers
103 views
How should I specify seasonality in CausalImpact? [closed]
I am working with the Python implementation of Google's CausalImpact package. My data is at daily frequency (365 observations per year); however, to inspect the effect of intervention, my pre-period ...
0
votes
0answers
33 views
Endogenous subgroups in impact estimation
I am using RCT data to estimate the impact of a program. After doing the straightforward analysis, I decided to estimate the program impact by subgroups (treatment status*subgroup). The subgroups were ...
0
votes
1answer
81 views
Using CausalImpact in R, observed data affected by event that could not affect priors
I am just starting out using the Causal Impact package in R. I am looking at observed data where I know there will be periods of extra traffic due to outside forces. However I cant find any unbiased ...
3
votes
0answers
100 views
How to calculate causal effects with repeated exogenous shocks over a time series
A rather frequent problem in causal inference is that we come across various shocks over time and try to measure their impact.
In the case of a single shock we can use bayesian methods to predict how ...
0
votes
0answers
100 views
Impact of propensity model
I have built a propensity model, which gives out probabilities of a customer paying given a collection intervention using a xgboost model. The model has an AOC-ROC of 81% with an accuracy of 77% ...
1
vote
0answers
93 views
Default CausalImpact Package
I am trying to gain an understanding of the CausalImpact package and the BSTS approach. Consider the following model:
$y_t = \mu_t + z_t + \epsilon_t$, where $\epsilon_t \sim N(0,s^2)$, and
$\mu_{t+...
0
votes
1answer
141 views
How is the posterior tail-area probability calculated?
I am currently using the CausalImpact package for some research and in this context I need to know and be able to explain, how the posterior tail-area probability is calculated in order to reproduce ...
1
vote
0answers
42 views
inclusion of static variables as covariates [closed]
Is there a clear way to include static variables e.g. elevation as covariates in the CausalImpact pacakge. Any guidance would be greatly appreciated.
Anand
0
votes
1answer
83 views
Incorporating Fixed Effects with Causal Impact
I have observations on a dependent variable of interest, $Y_{ijt}$, where $t \in [1,2,...T]$ denotes the time, $i$ denotes a particular brand and $j$ a specific product item. At $t=k$, there was an ...
3
votes
1answer
210 views
Synthetic control and unobserved confounders
The synthetic control (cohort) method is a very promising approach to causal inference that has been used in a number of interesting studies. It's particularly useful in situations where data are only ...
0
votes
1answer
76 views
Pre.intervention and post.intervention should be contiguous in CausalImpact?
I am running a CausalImpact analysis on a time series and my pre.period goes from 01.01.15 to 30.03.15. I want my post period to be from 15.04.15 to 17.04.15.
Is it ok if I create a time series that ...
1
vote
0answers
33 views
Assesing impact for rolling enrollment data
I'm running an experiment where some of the users are shown a new widget when they become eligible (some conditions that are unrelated to the experiment itself). I have a control counterfactual group ...
1
vote
1answer
87 views
Is it possible to predict the pre-intervention period rather than the post-period using Google's CausalImpact function?
I want to use to Google's causal impact function to impute the effect of an intervetion. However, my data is structured as: pre-period=1991-1995, intervetion occurs, post-period=1996-2017. To clarify, ...
2
votes
2answers
551 views
How to choose Control groups for Causal Impact algorithm?
I'm running an experiment and want to use the Causal Impact function to assess how well it performs.
I have 10 different cities. I'm looking to find out what is the best method for choosing which ...
0
votes
1answer
139 views
How to use a custom model in CausalImpact where preperiod.start is not right after preperiod.end?
I want to train on a period that isn't immediately preceding the prediction period. You can do this using the default causal model but I'm not sure how with a custom model.
Straight from the ...
0
votes
2answers
456 views
Interpreting Mediation Output when ACME is stat. sig but ADE and Total are not
The mediation package in R returns results in which:
The Average Causal Mediated Effect (ACME) (the effect of the mediator alone) is positive and statistically significant
Average Direct Effect (ADE) ...
3
votes
0answers
405 views
Pro and cons between Bayesian structural time series (BSTS) vs difference-in-differences?
Google's paper markets BSTS's benefits over DID such that
"In contrast to classical difference-in-differences schemes,
state-space models make it possible to (i) infer the temporal
evolution of ...
1
vote
1answer
152 views
Explaining the results of the CausalImpact package where effect is not statistically significant
I've been using the CausalImpact package to compare patent renewal rates across different classes of patents (to determine whether subject matter decisions have particular impacts on the rise or fall ...
2
votes
2answers
1k views
How to study the causal impact on multiple time series of interest against multiple baselines
My data consist of time series of Wikipedia hits for football players. I want to use the CausalImpact package to explore the effect of the World Cup on their ...
1
vote
0answers
239 views
Causal Impact: Continuous Pre-Intervention to Post-Intervention Time Periods?
Within the context of using R package CausalImpact (Brodersen et. al, 2015), is it valid to use time Periods that are noncontinuous for the Pre-Intervention and Post Intervention time periods?
For ...
1
vote
2answers
140 views
CausalImpact: Valid for Single Market [closed]
Is it possible to use the R package CausalImpact (Brodersen et. al, 2015) to estimate the incremental lift of running a local TV ad campaign in Iowa City,IA? We are also running national TV ads across ...
0
votes
0answers
200 views
Generalizing “Causal Impact” synthetic controls, to multiple outcomes
Does anybody know a way to generalize the use of the Causal Impact google R package to multiple outcome time series?
Say I ran a time series experiment and was able to set up multiple test outcome ...
1
vote
1answer
448 views
Scaling control time series with CausalImpact
I'm doing Causal Impact analytics with this python package. Since my control time series have a much larger scale (100-10000 times larger) than my modeled variable, at some point I tried to scale the ...
2
votes
1answer
445 views
Reduce credible intervals in Causal Impact model
I'm hitting an issue with a causal impact model that I'm building.
I'm trying to create a counter factual for daily sales at one store (nseasons = 7). I've included sales for 5 other stores nearby. ...
0
votes
1answer
109 views
How can you quantify the effect of a campaign in CausalImpact?
I have been working with the CausalImpact R-package to check whether new campaigns or features had a significant impact on a time-series.
I would like to know if it is possible to quantify this ...
1
vote
1answer
218 views
How to reason about causal effect in time series when the treatment group reacts even before treatment?
Context:
I'm running into a strange phenomenon about treatment effect and causality that I'll try to recreate here. Let's say I'm doing an observational study: Do people spend more time online as a ...
2
votes
1answer
663 views
Difference between using propensity score matching and CausalImpact for causal inference?
I'm investigating causal effect in some financial data, and I'm using two different approaches: propensity score matching with stratification and the CausalImpact package for Bayesian structural time ...
0
votes
1answer
194 views
BSTS employing purposedly spurious regressors for causal impact analysis
I'm employing Google Correlate time series to evaluate the causal impact of an intervention on a variable of interest y. I made sure that the Google series are highly correlated with y during the pre-...
0
votes
1answer
423 views
CausalImpact with Custom BSTS Model
I'm wanting to use a custom bsts model within the CausalImpact package, and I understand that I need to use a control group in my data; however, I don't really understand where that control group fits ...
3
votes
0answers
491 views
Specifying seasonality component in Causal impact
How do I supply yearly(month/week of the year) + day of the week seasonality in causal impact? I have 1 year of data in the pre period at daily granularity i.e. 365 data points.
would, nseasons =52 ...
1
vote
1answer
267 views
Synthetic Control and Causal Analysis
I am creating a synthetic control variable in which I want to use in order to perform a causal impact analysis of our marketing campaign.
The goal is to find a set of predictor time series that are ...
2
votes
2answers
260 views
Meta-Analysis on Effect Sizes with 95% Bayesian CI from CausalImpact R package
I am using the CausalImpact package in R to calculate the impact of a marketing intervention using Bayesian Structural Time Series. This methodology and package is explained in Broderson et al. 2015 ...
2
votes
0answers
422 views
Remove price and promotion effects from sales time series
I'm trying to measure the effect of an in-store media campaign on the sales. I have sales data along the time for test (treated) stores and control (not treated) stores.
Before comparing test and ...
1
vote
0answers
300 views
Bayesian structural time series with few data points (using CausalImpact)
I am experimenting with the CausalImpact package https://google.github.io/CausalImpact/CausalImpact.html (Brodersen et al. 2015) which uses Bayesian structural time-...
0
votes
1answer
552 views
Q: R - CausalImpact | order of control time series [closed]
My colleagues and I have been using Google's R-package CausalImpact for a while but recently discovered something that we can't quite explain. Depending on the order of including the different control ...
1
vote
1answer
299 views
Causality Analysis and test of Independence
First the problem: I am refering to lecture note, on page 480, 2nd paragraph, it mentions
If
X is in fact useless for predicting Y given Z, then an adaptive bandwidth selection
procedure (like ...
0
votes
0answers
139 views
Can I use a list (or similar) of multiple date ranges for pre and post periods?
In the documentation (https://google.github.io/CausalImpact/CausalImpact.html) for CasualImpact there is an example of setting pre and post periods of the treatment:
...
3
votes
1answer
926 views
Bayesian Structural Time Series in BSTS package: implementing mixed model
I have been using BSTS package for quite a while and I have found it pretty effective with respect to ARIMAX models.
I was wondering whether it would be possible to share regression coefficients in ...
2
votes
1answer
413 views
CausalImpact: model in the paper and default in the package
I was utilising CausalImpact for a study. Only recently did I realise that the model described in the associated paper was different to the default model implemented in the package.
The paper was ...
1
vote
1answer
1k views
What does Posterior tail-area probability mean in Causal Impact?
I'm new to CausalImpact package in R. I'm trying to understand what the p-value or Posterior tail-area probability mean in the summary. Does it mean that because the p-value is very low, the chance ...
