Hi Statalist,
This is a statistics question: how to adjust outliers by
incorporating seasonal pattern?
I have a monthly retails sales of 52 observations intended for
regression analysis. There are 2 outliers that I have replaced with the
mean of its two adjacent months. It seems not a good strategy as it does
not incorporate the seasonal fluctuation.
I learn that an alternative to accommodate outlier is to create a
dummy for each outlier, equivalent to treat the outliers as missing value.
What is the consequence of applying this to time series data ?
Could you please suggest solutions or references ?
Regards,
Rita Luk
Research Officer
Ontario Tobacco Research Unit
University of Toronto
33 Russell Street, T511
Toronto, ON M5S 2S1
Voice: 416-535-8501 x4727
Fax: 416-595-6068
*
* 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/
