Statistical Analysis Stack Exchange
Statistical Analysis Stack Exchange

Questions tagged [bsts]

Bayesian Structural Time-Series

29 questions
16
votes
2 answers

Predictions from BSTS model (in R) are failing completely

After reading this blog post about Bayesian structural time series models, I wanted to look at implementing this in the context of a problem I'd previously used ARIMA for. I have some data with some known (but noisy) seasonal components - there are…
anthr
  • 777
  • 3
  • 8
  • 21
12
votes
2 answers

Bayesian spike and slab versus penalized methods

I'm reading Steven Scott's slides about BSTS R package (You can find them here: slides). At some point, when talking about including many regressors in the structural time series model he introduces the spike and slab priors of regression…
Tommaso Guerrini
  • 1,099
  • 9
  • 27
8
votes
1 answer

question about bayesian structural time series model

I am investigating the stability of results from a bayesian structural time series model using bsts package in R. The following code estimates a local linear trend model (using an example from the R package) for three different numbers of MCMC draws…
kanimbla
  • 564
  • 4
  • 15
6
votes
2 answers

Incorporating Prior Information Into Time Series Prediction

Suppose I have data on my child C's height measured every week. Presumably there is a positive trend, due to growth, and some noise due to measurement errors, and maybe even seasonality (winter boots or haircuts add extra height). If want to predict…
Evan Rosica
  • 253
  • 1
  • 8
6
votes
2 answers

How to improve forecast accuray of bsts model

I have a question about the use of the bsts package. In general my question is if my approach is feasible. Because my holdout MAPE is much worse than all the other approaches I have in my ensemble. Here is my code.…
burton030
  • 97
  • 1
  • 13
5
votes
0 answers

BSTS forecasts not incorporating holiday effects

Using the R package "bsts", I am attempting to forecast daily data from 3 years of history. The model looks good, and the forecast looks good, other than the fact that it fails to account for the Memorial Day effect. I thought that using the…
mmmm
  • 53
  • 5
5
votes
1 answer

Do I need stationary time series for Bayesian structural time series (BSTS)?

I'm trying to model with BSTS, with exogenous variables. It appears that my y-sequence is not stationary. Do I need to diff that to stationary? Or could BSTS handle that? P.S. I'm using R package bsts Thank you for your time! All the best, Kathy
Chenying Gao
  • 61
  • 4
4
votes
0 answers

time series: What is the performance difference between ARIMA models and Bayesian Structural Time Series models

I have been looking at ARIMA/SARIMA models and some of the Bayesian Structural Time-Series models lately. The formulation of the two models does not seem that different but the fitting method of Kalman filter versus MCMC seems like the main…
krishnab
  • 1,008
  • 7
  • 12
3
votes
1 answer

Custom model using BSTS does not match with CausalImpact in R (please help!)

I am trying to match the results from using CausalImpact with those from using BSTS for a custom model. I followed exactly what the package instruction says but the results completely do not match. Here I tried a simple local level model. Dataset…
Kang Inkyu
  • 441
  • 1
  • 3
  • 9
3
votes
1 answer

predict.bsts does not capture holiday information

EDIT (Tue12Mar): The bug fixes are on their way. See https://github.com/steve-the-bayesian/BOOM/issues/25 I've been working with bsts to model time-series and make forecasts, but have run into some problems with the predict function and…
Simon Whelan
  • 31
  • 2
3
votes
1 answer

Problems running bsts with a Poisson response

I'm attempting to run a bayesian time series analysis using the bsts package, but I'm getting bizarre forecasts when I set family to "poisson." My time series are counts and follow a Poisson distribution, so this is necessary. I suspect I need to…
user218440
  • 31
  • 4
3
votes
0 answers

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 attributable impact, (ii) incorporate empirical…
hhh
  • 283
  • 3
  • 17
2
votes
0 answers

Is there anyway I can limit my forecast to a upper limit using bsts package?

I am using bsts package for forecasting. I need my forecast to be less than the upper limit. Like shown in the below figure. FaceBook Prophet allows this by an option. I would like to do the similar stuff using bsts package. Is there anyway I can…
praveen
  • 21
  • 1
2
votes
0 answers

Modelling dynamic price elasticity with bsts

I have approximately 2000 daily data which contains total daily sales and median price of sales for a particular product. I read the paper but the level of bayseian math is too high for me but from my past experience with price elasticity, I think…
thulungair
  • 21
  • 2
2
votes
1 answer

Forecasting with BSTS and external predictors

Can I use bsts with external predictors such as promotions, holidays etc? How do I do it?
Sid Verma
  • 101
  • 2
  • 9
1
2