Bayesian structural time series (BSTS) model is a

statistical Statistics (from German language, German: ', "description of a State (polity), state, a country") is the discipline that concerns the collection, organization, analysis, interpretation, and presentation of data. In applying statistics to a s ...

technique used for

feature selection In machine learning, feature selection is the process of selecting a subset of relevant Feature (machine learning), features (variables, predictors) for use in model construction. Feature selection techniques are used for several reasons: * sim ...

, time series forecasting, nowcasting, inferring causal impact and other applications. The model is designed to work with

time series In mathematics, a time series is a series of data points indexed (or listed or graphed) in time order. Most commonly, a time series is a sequence taken at successive equally spaced points in time. Thus it is a sequence of discrete-time data. ...

data. The model has also promising application in the field of analytical

marketing Marketing is the act of acquiring, satisfying and retaining customers. It is one of the primary components of Business administration, business management and commerce. Marketing is usually conducted by the seller, typically a retailer or ma ...

. In particular, it can be used in order to assess how much different marketing campaigns have contributed to the change in web search volumes, product sales, brand popularity and other relevant indicators. Difference-in-differences models and

interrupted time series Interrupted time series analysis (ITS), sometimes known as quasi-experimental time series analysis, is a method of statistical analysis involving tracking a long-term period before and after a point of intervention to assess the intervention's effe ...

designs are alternatives to this approach. "In contrast to classical difference-in-differences schemes, state-space models make it possible to (i) infer the temporal evolution of attributable impact, (ii) incorporate empirical priors on the parameters in a fully Bayesian treatment, and (iii) flexibly accommodate multiple sources of variation, including the time-varying influence of contemporaneous covariates, i.e., synthetic controls."

General model description

The model consists of three main components: #

Kalman filter In statistics and control theory, Kalman filtering (also known as linear quadratic estimation) is an algorithm that uses a series of measurements observed over time, including statistical noise and other inaccuracies, to produce estimates of unk ...

. The technique for time series decomposition. In this step, a researcher can add different state variables: trend, seasonality, regression, and others. # Spike-and-slab method. In this step, the most important regression predictors are selected. # Bayesian model averaging. Combining the results and prediction calculation. The model could be used to discover the causations with its counterfactual prediction and the observed data. A possible drawback of the model can be its relatively complicated mathematical underpinning and difficult implementation as a computer program. However, the programming language R has ready-to-use packages for calculating the BSTS model, which do not require strong mathematical background from a researcher.

References

{{Reflist

General model description

See also

References

Further reading