Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Estimating transfer/response function parameters inIntervention/Impact/Interrupted Time Series Analysis


From   Häge, Frank <FHaege@fsw.leidenuniv.nl>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Estimating transfer/response function parameters inIntervention/Impact/Interrupted Time Series Analysis
Date   Fri, 1 Feb 2008 16:24:03 +0100

Dear all,

Is there a way in Stata to estimate the parameters of first order step functions in ARIMA interrupted time series analysis? The first order step function is usually used to model impacts with gradual onset and permanent duration (see e.g. McDowall et al. (1980) Interrupted Time Series Analysis; McCleary and Hay (1980) Applied Time Series Analysis for the Social Sciences; Yaffee (2000) Time Series Analysis and Forecasting). 

The function takes the following form: f(It) = (w * It-b) / (1 - d * L)

w is the coefficient of the dichotomous intervention variable It-b, where t indicates an observation in time and b the delay of the impact.
d is the rate parameter and L the lag operator.

Given that the form of this transfer function is theoretically derived, how can w and d be estimated in Stata?

Any help on this would be highly appreciated!

Thanks,
Frank


**********************************************************************
This email and any files transmitted with it are confidential and
intended solely for the use of the individual or entity to whom they
are addressed. If you have received this email in error please notify
the system manager.
**********************************************************************


*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index