| Title: | Spillover Time Series Causal Inference |
|---|---|
| Description: | A time series causal inference model for Randomized Controlled Trial (RCT) under spillover effect. 'SPORTSCausal' (Spillover Time Series Causal Inference) separates treatment effect and spillover effect from given responses of experiment group and control group by predicting the response without treatment. It reports both effects by fitting the Bayesian Structural Time Series (BSTS) model based on 'CausalImpact', as described in Brodersen et al. (2015) <doi:10.1214/14-AOAS788>. |
| Authors: | Zihao Zheng and Feiyu Yue |
| Maintainer: | Feiyu Yue <[email protected]> |
| License: | GPL-2 |
| Version: | 1.0 |
| Built: | 2024-12-17 07:01:33 UTC |
| Source: | CRAN |
A time series causal inference model for Randomized Controlled Trial (RCT) under spillover effect. 'SPORTSCausal' (Spillover Time Series Causal Inference) separates treatment effect and spillover effect from given responses of experiment group and control group by predicting the response without treatment. It reports both effects by fitting the Bayesian Structural Time Series (BSTS) model based on 'CausalImpact', as described in Brodersen et al. (2015) <doi:10.1214/14-AOAS788>.
The DESCRIPTION file:
| Package: | SPORTSCausal |
| Type: | Package |
| Title: | Spillover Time Series Causal Inference |
| Version: | 1.0 |
| Imports: | CausalImpact, keras, stats, graphics, grDevices |
| Date: | 2021-03-13 |
| Author: | Zihao Zheng and Feiyu Yue |
| Maintainer: | Feiyu Yue <[email protected]> |
| Description: | A time series causal inference model for Randomized Controlled Trial (RCT) under spillover effect. 'SPORTSCausal' (Spillover Time Series Causal Inference) separates treatment effect and spillover effect from given responses of experiment group and control group by predicting the response without treatment. It reports both effects by fitting the Bayesian Structural Time Series (BSTS) model based on 'CausalImpact', as described in Brodersen et al. (2015) <doi:10.1214/14-AOAS788>. |
| License: | GPL-2 |
| NeedsCompilation: | no |
| Packaged: | 2021-03-28 08:33:14 UTC; zhengzihao |
| Depends: | R (>= 3.5.0) |
| Repository: | CRAN |
| Date/Publication: | 2021-03-30 08:10:02 UTC |
| Config/pak/sysreqs: | make libpng-dev python3 |
Index of help topics:
SPORTSCausal-package Spillover Time Series Causal Inference
ad_cost Advertising cost: a real experimental data
under spillover effect
sportscausal Time series causal inference of Randomized
Controlled Trial (RCT) under spillover effect
Zihao Zheng and Feiyu Yue
Maintainer: Feiyu Yue <[email protected]>
Brodersen et al. Inferring causal impact using Bayesian structural time-series models. Annals of Applied Statistics, 2015
http://google.github.io/CausalImpact/CausalImpact.html
## For more detail of the package, try ?sportscausal and ?ad_cost## For more detail of the package, try ?sportscausal and ?ad_cost
This dataset comes from an A/Btest, which is to evaluate how a newly-proposed algorithm will affect the cost of advertising. Assuming that the bidding environment of an advertising market is stable in a short period of time, there will be no net increase or decrease of cost. When a treatment is applied, the mutual interference between the experiment group and the control group can not be ignored. For example, the difference in cost between the experiment group and the control group might not only come from the increase of experiment group, caused by treatment effect, but also from the potential decrease in control group. That is the typical situation for spillover causal inference to be implemented.
data("ad_cost")data("ad_cost")
A data frame with 49 observations on the following 3 variables.
y.expA numeric vector of responses in experiment group.
y.conA numeric vector of responses in control group.
timeA numeric vector indicating time period before/after the treatment, time = 1 represents post treatment period.
This data has been linearly transformed for confidential issue.
### load data data(ad_cost) ### define variables and visualize y.exp = ad_cost$y.exp y.con = ad_cost$y.con plot(y.exp, col = "red", type = "l", xlab = "time", ylab = "response") lines(y.con, col = "blue") ### fit the model and return treatment/spillover effect # notice that day-34 is the first day of treatment fit = sportscausal(y.exp = y.exp, y.con = y.con, pre.period = c(1:33), post.period = c(34:49), is.plot = FALSE) fit$est.treatment fit$est.spillover### load data data(ad_cost) ### define variables and visualize y.exp = ad_cost$y.exp y.con = ad_cost$y.con plot(y.exp, col = "red", type = "l", xlab = "time", ylab = "response") lines(y.con, col = "blue") ### fit the model and return treatment/spillover effect # notice that day-34 is the first day of treatment fit = sportscausal(y.exp = y.exp, y.con = y.con, pre.period = c(1:33), post.period = c(34:49), is.plot = FALSE) fit$est.treatment fit$est.spillover
'SPORTSCausal' produces treatment effect and spillover effect estimation from responses of experiment group and control group.
sportscausal(y.exp, y.con, pre.period, post.period, is.plot = TRUE, model.select = "AIC", max.p = 3, max.d = 3, max.q = 3, feature = NULL)sportscausal(y.exp, y.con, pre.period, post.period, is.plot = TRUE, model.select = "AIC", max.p = 3, max.d = 3, max.q = 3, feature = NULL)
y.exp |
Response of experiment group, from pre-treatment to post-treatment |
y.con |
Response of control group, from pre-treatment to post-treatment |
pre.period |
Time period before the treatment |
post.period |
Time period during the treatment |
is.plot |
If |
model.select |
Model used to predict the time series without treatment. If |
max.p |
The max number of autoregressive terms in ARIMA model, by default |
max.d |
The max number of nonseasonal differences needed for stationarity in ARIMA model, by default |
max.q |
The max number of lagged forecast errors in the prediction equation in ARIMA model, by default |
feature |
The covariate matrix associated with the response. By default, |
In the presense of spillover effect, the response of control group could be interferenced by the treatment. In order to seprate the treatment effect and spillover effect, sportscausal uses ARIMA model or LSTM model to predict the response behavior without treatment. The point estimator and significance of both effect follow using Bayesian Structrual Time Series (BSTS) model.
est.treatment |
Information of treatment effect estimation, containing point estimation, confidence interval and p-value |
est.spillover |
Information of spillover effect estimation, containing point estimation, confidence interval and p-value |
Zihao Zheng and Feiyu Yue
Brodersen et al. Inferring causal impact using Bayesian structural time-series models. Annals of Applied Statistics, 2015
See also ?ad_cost
## simulate data set.seed(1) y0 = 100 + arima.sim(model = list(ar = 0.3), n = 125) y.con = y0 + rnorm(125) y.con[101:125] = y.con[101:125] - 10 ## -10 as spillover effect y.exp = y0 + rnorm(125) y.exp[101:125] = y.exp[101:125] + 10 ## 10 as treatment effect pre.period = c(1:100) post.period = c(101:125) ## visualize plot(y.exp, col = "red", type = "l", ylab = "response", ylim = c(80, 120)) lines(y.con, col = "blue") abline(v = 101, col = "grey", lty = 2, lwd = 2) legend("topleft", legend = c("exp", "con"), col = c("red", "blue"), cex = 1, lty = 1) ## try SPORTSCausal with ARIMA + AIC fit.aic = sportscausal(y.exp = y.exp, y.con = y.con, pre.period = pre.period, post.period = post.period, is.plot = FALSE) fit.aic$est.treatment fit.aic$est.spillover ## you can also try model.select = "CV" or "lstm"## simulate data set.seed(1) y0 = 100 + arima.sim(model = list(ar = 0.3), n = 125) y.con = y0 + rnorm(125) y.con[101:125] = y.con[101:125] - 10 ## -10 as spillover effect y.exp = y0 + rnorm(125) y.exp[101:125] = y.exp[101:125] + 10 ## 10 as treatment effect pre.period = c(1:100) post.period = c(101:125) ## visualize plot(y.exp, col = "red", type = "l", ylab = "response", ylim = c(80, 120)) lines(y.con, col = "blue") abline(v = 101, col = "grey", lty = 2, lwd = 2) legend("topleft", legend = c("exp", "con"), col = c("red", "blue"), cex = 1, lty = 1) ## try SPORTSCausal with ARIMA + AIC fit.aic = sportscausal(y.exp = y.exp, y.con = y.con, pre.period = pre.period, post.period = post.period, is.plot = FALSE) fit.aic$est.treatment fit.aic$est.spillover ## you can also try model.select = "CV" or "lstm"