Time Series Lab Software
Time Series Lab is the name of a family of software programs designed to model and forecast structural time series models. These models use advanced techniques but are designed to be easy to use. At the most basic level all that is required is some appreciation of the concepts of trend, seasonal and irregular. The hard work is done by the program, leaving the user free to concentrate on formulating models and using them to make forecasts.
Time Series Lab Research
The Time Series Lab Article Series are dedicated to research performed with Time Series Lab software. The scope of the series includes the analysis and forecasting of a wide range of time series including economics, finance, sports, climatology, biology, and health science.
Time Series Lab Consultancy
Time Series Lab offers consultancy services to companies who require data analysis that go beyond what is offered by our software packages. We advise on data analysis methods and implementation of them. Time Series Lab also designs software packages specifically suited to your company.
TSL Sports Statistics
The Time Series Lab team dives into the world of Sports Statistics. We developed a new package called Time Series Lab - Sports Statistics Edition. This is a software program for analysing, modelling, and forecasting of time series focusing on sports results. The software allows you to choose from several probability distributions and model specifications to extract sports team strengths from your data. The software is based on football models that appeared in the academic literature.
Time Series Lab Engine
The engine behind our State Space Edition software is a set of C routines with the name SsfPack. We pride ourselves in having extremely efficient State Space algorithms that result in fast optimisation times even for large systems. When working with large datasets our optimised algorithms are an important asset in keeping estimation times as low as possible.
Time Series Lab product range
Everything you need for state space modelling
Basic
- Free, even for commercial use
- Easy to use interface
- Extract unobserved components like Level, Slope, Seasonal, and Cycle
- Analyse the effect of Explanatory variables on your forecasts
- Advanced Kalman filter and Smoother algorithms
- Highly efficient code engine
- Compare models on forecasting ability
Extended
- No limit on time series length
- No limit on number of explanatory variables
- Three seasonal components to model complex seasonal patterns
- Three cycle components
- Optimality algorithm for seasonal components
- Automatic intervention analysis
- Exact initialisation
- And more...
Sequentially univariate
- No limit on number of sequentially analyzed univariate time series
- Immediately see which time series require extra modelling attention
- Detect patterns shared across the time series
- Batch processing module
- Quickly store forecasts of all time series
- And more...
Multivariate
- Capture the dynamics of multiple time series simultaneously
- Factor modelling for large panels of time series
- Cointegration analysis
- Batch processing module
- And more...
Basic
- Free, even for commercial use
- Easy to use interface
- Extract unobserved components like Level, Slope, Seasonal, and Cycle
- Analyse the effect of Explanatory variables on your forecasts
- Advanced Kalman filter and Smoother algorithms
- Highly efficient code engine
- Compare models on forecasting ability
Extended
- No limit on time series length
- No limit on number of explanatory variables
- Three seasonal components to model complex seasonal patterns
- Three cycle components
- Optimality algorithm for seasonal components
- Automatic intervention analysis
- Exact initialisation
- And more...
Sequentially univariate
- No limit on number of sequentially analyzed univariate time series
- Immediately see which time series require extra modelling attention
- Detect patterns shared across the time series
- Batch processing module
- Quickly store forecasts of all time series
- And more...
Multivariate
- Capture the dynamics of multiple time series simultaneously
- Factor modelling for large panels of time series
- Cointegration analysis
- Batch processing module
- And more...
Time Series Lab - State Space Edition features
| Topic | Basic | Extended | Sequentially | Multivariate |
|---|---|---|---|---|
| Free download | ✔ | ✖ | ✖ | ✖ |
| Univariate time series analysis | ✔ | ✔ | ✔ | ✔ |
| User friendly Graphical User Interface | ✔ | ✔ | ✔ | ✔ |
| Advanced Kalman filter and Smoother algorithms | ✔ | ✔ | ✔ | ✔ |
| Analyse the effect of explanatory variables on your time series | ✔ | ✔ | ✔ | ✔ |
| Missing values are handled with ease | ✔ | ✔ | ✔ | ✔ |
| Advanced graphing capabilities | ✔ | ✔ | ✔ | ✔ |
| Model forecast comparison | ✔ | ✔ | ✔ | ✔ |
| No limit on time series length | ✖ | ✔ | ✔ | ✔ |
| No limit on number of explanatory variables | ✖ | ✔ | ✔ | ✔ |
| Number of seasonal components | 1 | 3 | 3 | 3 |
| Number of cycle components | 1 | 3 | 3 | 3 |
| Optimality algorithm for seasonal components | ✖ | ✔ | ✔ | ✔ |
| Advanced explanatory variable treatment* | ✖ | ✔ | ✔ | ✔ |
| Automatic outlier and break detection | ✖ | ✔ | ✔ | ✔ |
| Sequentially analyse large numbers of time series** | ✖ | ✖ | ✔ | ✖ |
| Analyse multiple series in one system*** | ✖ | ✖ | ✖ | ✔ |
** This is often used if large numbers of univariate time series need to be forecasted, often on a regular basis. You can think of the forecasting of sales products for example.
*** Capture the dynamics of multiple time series simultaneously. This includes the modelling of large systems with the use of factor models.
Our team
Developers with a close connection to academia
R. Lit, PhD
Rutger Lit is a research fellow at the Vrije Universiteit Amsterdam and has a PhD in econometrics, specialising in time series analysis. In 2017, he founded Nlitn, a company offering consultancy services. It also offers full data solution packages to meet the data analysis needs of clients. For example, the Time Series Lab software series.
Short BioProfessor S.J. Koopman
Siem Jan Koopman is Professor of Econometrics at the Department of Econometrics and Data Science, Vrije Universiteit Amsterdam. He is also a research fellow at Tinbergen Institute and a long-term Visiting Professor at CREATES, University of Aarhus.
He held positions at London School of Economics and CentER (Tilburg University), and had long-term visits at US Bureau of the Census, European University Institute, and European Central Bank, Financial Research.
Academic websiteProfessor A.C. Harvey
Andrew Harvey is Emeritus Professor of Econometrics in the Faculty of Economics and Politics, University of Cambridge. He was Professor of Econometrics at the London School of Economics before coming to Cambridge in 1996. His most recent book is a monograph entitled Dynamic Models for Volatility and Heavy Tails. Andrew Harvey is also a Fellow of the Econometric Society and a Fellow of the British Academy.
Academic websiteP. Gorgi, PhD
Paolo Gorgi is Associate Professor at the department of Econometrics and Data Science, Vrije Universiteit Amsterdam. He obtained a double PhD in statistics and econometrics from the University of Padova and Vrije Universiteit Amsterdam. His main research interests concern: time series analysis, statistical inference for dynamic models and forecasting economic variables. He has published articles in several academic journals, including Journal of the Royal Statistical Society: Series B and Journal of Econometrics.
Academic websiteGet in touch
Sign up
Receive updates from Time Series Lab