Re: Stationary means


Jason Foster wrote:
I don't think that this is a FAQ, but if it is I apologize for the
noise...

Discussions about "regression to the mean" tend to focus on fallacies
relating to heights, grades, sickness, etc. Something I have not seen
discussed is when/whether it is appropriate to assume a stationary mean
(or, I think alternatively, a fixed distribution)?

Assuming a constant distribution and repeated sampling, I can
intuitively understand regression to the mean. However, I can imagine
situations where the distribution is changing over time. For example
(and here I'm talking outside of my area of expertise) the mean height
in North America is increasing over time (ostensibly due to dietary and
health factors). If this is the case, then what would "regression to
the mean" mean? Towards which mean would the regression take place?
How would an observer know that a regression analysis is appropriate?

Any thoughts (or pointers to resources) on the issues would be
gratefully appreciated.

Jason

Jason ..

Any time (pun intended !) that you have time series data , immediately
look beyond regression methodology/textbooks ..The complications
(opportunities) that time series data bring to the table are many and
far beyond this simple response. If you wish you might go to
http://www.autobox.com and enroll at AFS University and pursue Intro to
Time Series/Forecasting and review some material ...particularly
http://www.autobox.com/pdfs/regvsbox.pdf

Academics and practitioners who know Regression Analysis often misapply
these methods ( founded on cross-sectional data where you have n
independent readings each with p characteristics ) to
chronological/correlated over time data.

If you wish to pursue this ...please feel free to call...

dave reilly
automatic forecasting systems
215-675-0652
http://www.autobox.com

.

Relevant Pages

  • Re: Linear regression - a few questions
    ... worry about normality. ... So could I still use regression to show something? ... I understand it's not a time series problem. ... regression applied to time series data I would suggest you make sure ...
    (sci.stat.math)
  • Re: Dealing with correlated predictors
    ... I use them as predictors in a linear regression. ... reduced r-sq. ... I guess that if the correlations among x1..x17 were lower the loss of ... is this time series data? ...
    (sci.stat.consult)
  • Time Series Regression Analysis
    ... One of my colleagues pointed out that I could not perform the regression ... analysis I was working on (comparing several sets of time series data) ...
    (microsoft.public.excel.misc)
  • Re: Rich Ulrich continues his statistical Muddle, Quackery, and MALPRACTICE
    ... A discrete uniform distribution of ranks. ... >> the distribution of the X used in any multiple regression. ... >> RU> Normality is only one sort ... decided to do a fitting of a particular Y on several X that had already ...
    (sci.stat.math)
  • Re: Linux 2.6.16.30-pre1
    ... the goal of -stable as I remember it is not "no regression" ... i.e. patches don't go in without a good ... Whether a distribution uses 2.6.16 or a more recent kernel (that will ... on the goals of the distribution. ...
    (Linux-Kernel)