Home  /  Products  /  Stata 10  /  Time series

This page announced updates in Stata 10. See a complete overview of all of Stata's time-series features.

ORDER STATA

Time series

  1. All time-series analysis commands now support data with frequencies as high as 1 millisecond (ms), corresponding to Stata’s new date/time variables. Since your data are probably not recorded at the millisecond level, existing command tsset has new option delta() that allows you to specify the frequency of your data. Previously, time was recorded as t0, t0 + 1, t0 + 2, ..., and if time = t in some observation, then the corresponding lagged observation was the observation for which time = t − 1. That is still the default. When you specify delta(), time is assumed to be recorded as t0, t0 + δ, t0 + 2δ, and if time = t in some observation, then the corresponding lagged observation is the observation for which time = t − δ. Say that you are analyzing hourly data and time is recorded using Stata’s new %tc values. One hour corresponds to 3,600,000 ms, and you would want to specify
            tsset t, delta(3600000)
    Option delta is smart; you can specify
            tsset t, delta(1 hour)
    See [TS] tsset.
  2. tsset now reports whether panels are balanced when an optional panel variable is specified.
  3. Many ts estimation commands now accept option vce(vcetype). As mentioned in the What’s new in statistics (general), vce(robust) and vce(cluster varname) are the right ways to specify the old robust and cluster() options, and option vce() allows other VCE calculations as well.
  4. Options vce(hc2) and vce(hc3) are now the preferred way to request alternative bias corrections for the robust variance calculation for existing estimation command prais. See [TS] prais.
  5. Existing estimation commands arch and arima have new option collinear that specifies that the estimation command not remove collinear variables. Typically, you do not want to specify this option. It is for use when you specify constraints on the coefficients such that, even though the variables are collinear, the model is fully identified. See [TS] estimation options.
  6. Existing command irf now estimates and reports dynamic-multiplier functions and cumulative dynamic-multiplier functions, as well as their standard errors. See [TS] irf.
  7. The [TS] manual has an expanded glossary.

Back to highlights