About STAMP

STAMP

STAMP is a time series software system for the models with unobserbed components such as trend, seasonal, cycle and irregular. It provides a user-friendly environment for the analysis, modelling and forecasting of time series. Estimation is carried out using state space methods and Kalman filtering. However, STAMP is set up in an easy-to-use form which enables the user to concentrate on model selection and interpretation. STAMP 8 is an integrated part of the OxMetrics modular software system for data analysis with excellent data manipulation, graphical and batch facilities.

The full name of STAMP is Structural Time series Analyser, Modeller and Predictor. Structural time series models are formulated directly in terms of components of interest. Such models find application in many subjects, including economics, finance, sociology, management science, biology, geography, meteorology and engineering. STAMP bridges the gap between the theory and its application – providing the necessary tool to make interactive structural time series modelling available for empirical work. (Another such tool is SsfPack, by Koopman, Shephard and Doornik (1999), which provides more general procedures but with a programmatic interface, see www.ssfpack.com.)

STAMP uses the Kalman filter and related algorithms to fit unobserved component time series models. We are excited to present the new version 8 of STAMP, which provides another big step forward from the previous version. The new version is updated for the new OxMetrics environment and it therefore provides even higher standards in program functionality: by clicking the mouse a few times, everyone is able to start with a full exploratory, statistical or econometric analysis of the time series at hand using the powerful capabilities of the STAMP 8.

Earlier versions of the program were written by Andrew Harvey and Simon Peters, while the data management side was dealt with by Bahram Pesaran. These projects were supported by the Economic and Social Research Council. Version 5 was entirely rewritten in C by the current authors of STAMP. Much of the data management and the graphical interface of STAMP 5 was shared with the PcGive 7 and 8 programs of Jurgen A. Doornik and David F. Hendry. STAMP 6 was the first version of STAMP in which the front-end program GiveWin is separate from the econometric module STAMP. Other modules included PcGiveTM, TSPTM (by TSP International) and X12Arima for GiveWin (based on X12-ARIMA by the US Census Bureau). The current version STAMP 8 is fully integrated with the OxMetrics program.

STAMP 8

New features in STAMP 8.10

• The forecasting dialog allows the forecasting of the unobserved components as well as the future observations.
• Various errors have been removed from the program and some improvements have been introduced.
• Most notably, the batch facilities have improved and some bugs in the routines for models with explanatory variables and intervention variables have been solved.
• The automatic outlier and break detection procedure has been optimized further.

New features in STAMP 8

Many new features have been introduced in version 8 of STAMP. The most notable are:

• Multivariate models

  The multivariate structural time series model where the unobserved components become vectors and the disturbance variances become disturbance variance matrices can be considered for the analysis of a set of multiple time series. The number of multivariate options has increased considerably compared to earlier versions of the program:

  • Select components by equation: Different components can be selected for different equations. This enables the user to analyse time series with different dynamic characteristics jointly. For example, consider two time series where one series may be subject to seasonal dynamics while the other series does not require a seasonal component. The trends of the two time series may move together. STAMP 8 allows the user to select a seasonal component for the first series but not for the second series. This applies to all components in STAMP: trend, seasonal, cycle, autoregressive, irregular, time-varying regressions, etc.
  • Select regressions and interventions by equation: An option for selecting different explanatory variables and interventions for different equations has been available in STAMP versions 5 and 6. However, the current facility of distributing explanatory variables over different equations has improved and is more flexible.
  • Design a dependence structure for each component: Multivariate models in STAMP 5 and 6 were limited in their choice of variance matrices: only full variance matrices of different ranks could be considered. A reduced-rank variance matrix implies common features in multiple time series. This option remains in STAMP but the specification has changed slightly. The disturbance variance matrix imposes a dependence structure within the component vector (between the different equations). This dependence can be designed by the user in a simple way and for each component separately. For example, the cycle component in equation 1 can be forced to depend on the cycles in equations 2 and 3 only.
  • In STAMP 8 different variance matrices for different disturbances can be chosen: The range of variance matrices includes scalar and diagonal matrices, scaled matrices of ones (when applied to the slope component, this implies balanced growth) and one rank plus diagonal matrices. The latter case implies that a vector component can be decomposed into common and idiosyncratic effects. In many applications, these different specifications can be interpreted easily and can be highly interesting.
  • The multivariate options extend to all models introduced in STAMP 7: This includes the higher-order smooth trend models, the higher-order (bandpass) cycle components and the (vector) autoregressive components of orders 1 and 2.
  • Missing observations: They can also be handled within multivariate time series models. This allows the interpolation of missing observations through time but also through different time series.
  • Forecasting of multivariate time series made simple: In particular, STAMP 8 allows the incorporation of available future observations for the explanatory variables in the database. Furthermore, future observations of dependent variables are considered in graphical presentations of forecasts and for the measurement of forecast accuracy (using standard measures such as the root mean squared forecast error (RMSE) and the mean absolute percentage error (MAPE).
  • Estimation of parameters in multivariate time series models is based on exact procedures: The diffuse initialisation of the Kalman filter is implemented, the exact likelihood function is computed and the score function with respect to variance parameters is computed analytically and fast. This leads to a robust estimation procedure in STAMP 8 and a relatively fast estimation process.
  • The number of graphical output for multivariate models is increased: STAMP 8 offers an easy handling of the graphical output. An option for graphics output selection for each equation is provided. The powerful tools in OxMetrics 5 to edit graphical output are fully available to STAMP 8 users.

• Automatic outlier and break detection

  Another major development in STAMP 8 is the implementation of a new automatic detection procedure for outliers and breaks in univariate and multivariate time series models. The following features are available:

  • STAMP 8 is able to propose a set of potential outliers and trend breaks for univariate and multivariate time series. It is a basic but effective two-step procedure based on the auxiliary residuals. First the selected model is estimated and the diagnostics are investigated. Then a first (larger) set of potential outliers and trend breaks are selected from the auxiliary residuals. After re-estimation of the model, only those interventions survive that are sufficiently significant. In the multivariate case, this selection procedure is carried out jointly for each equation in the model.
  • After the automatic selection, the results are reported. All considered outliers and breaks are kept in the intervention dialog and they can be deleted from the model or added to the model in the usual way and implemented as in STAMP 7. For future use, the interventions can be saved. It prevents the manual input of outliers and breaks altogether.
  • The automatic selection procedure can be repeated with the inclusion of a fixed set of explanatory and intervention variables.

• Other new features
  • Each parameter in the models of STAMP 8 can be edited directly. Parameters can be kept fixed at a particular value. Variances can be kept fixed at values relative to a particular variance of another component (q-ratio). This facility also applies to multivariate models.
  • General forecasting options have been extended and made more flexible. The number of output options for prediction and forecasting have been increased. Future values of explanatory variables available in the database can be used for the forecasting of dependent variables.
  • More output diagnostics are presented for predictions (one-step and multi-step), auxiliary residuals and weight and gain functions.

STAMP 7

STAMP 7.10: enhancements and solved problems

• Store in Database option for multiple cycles is corrected
• Batch options are improved:
  • forecast option is activated, new syntax
    forecast(aa,bb,cc);
        aa is number of forecasts
        bb is optional and give rate of change for Xs
        cc is optional, when it is equal to "logs", it will anti-log the forecasts.
    examples
    

    		
    								forecast(5);
    								forecast(5, 0.01);
    								forecast(5, 0.01, logs);
    						

  • testsummary option is introduced
  • teststate option is introduced
• date labels of forecasting in written output is corrected
• gain functions (for gain, phase and shift in time) graphs corrected:
  • are displayed as fractions of the year (suggested by David Findley)
  • for trend and cycle, only displayed for frequencies longer than a year
  • phase plots may switch between +/- M_PI (known problem) corrected this
  • added to shift in time graph (due to filtering) phase / lambda
• regression results for interventions are corrected;
• corrected the residuals when interventions are present;
• weight functions corrected when explanatory and intervention variables are present;
• before estimation starts, a check for multicolinearity is introduced: if multicolinear X: msg "KalmanInitial(): collapse to Kalman filter has failed Failed to get starting values." appears.
• date labels of predictions (Test/Prediction analysis) in written output is corrected

STAMP 7.04

• program error when cycle is estimated is corrected;
• forecast plots corrected when interventions are selected;
• default set of values for parameters can be selected before editing the parameters;

New features in STAMP 7

• Time-varying regression coefficients can be included as part of the model.Three specifications can be selected: (i) random walk, (ii) spline sprecification (or smooth trend) and (iii) return-to-normality (deviations from a fixed coefficient follow an autoregressive process of order 1).

• Missing values can be treated in this version of STAMP. In all levels of the analysis, missing observations are accounted for automatically. Model-based estimates of the missing values can be produced. Confidence intervals can be included in the graphs with estimated components. The predicted, filtered and smoothed estimates of the components can be presented simultaneously.

• The observation weight functions that are used for the estimation of the unobserved components are given as output. The associating spectral gain and phase functions can also be produced.

• Model-based forecasting and backcasting can be carried out.

• Unobserved stationary autoregressive processes of orders 1 and 2 can be included in the model together with three stochastic cycle components.

• Higher-order smooth trends and cycles with band-pass filter properties can be included in the model.

• The trigonometric seasonal component consists of separate processes for the different seasonal frequencies. These processes can be selected separately in the model. Also different seasonal variances can be attached to the seasonal processes.

• More flexible options for the handling and estimation of parameters are provided. The parameters can be treated without transformation.

• Dates for outliers and breaks can be stored and remain part of the model once selected.

STAMP data (excel)

To download the data, which are used in the STAMP manual, please click here. Note that the data are contained in a zipfile.

Screenshots