Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Interpreting cumulative sum output

From   Reza C Daniels <>
Subject   st: Interpreting cumulative sum output
Date   Fri, 11 Nov 2005 12:25:30 +0200

Dear Statalisters,

I am having difficulty interpreting the output of the -cusum- command.
My results are:

Variable |   Obs    Pr(1)   CusumL    zL    Pr>zL
ind_co~1 | 26270   0.3672   972.04   8.522  0.000

Variable |	CusumQ    zQ   Pr>zQ
ind_co~1 | 	1092.41   8.727 0.000

This would suggest that I have both a significant linear z-score (zL)
and a significant quadratic z-score (zQ). How is it possible that there
can be both a significant linear relationship and a significant
quadratic relationship?

If I graph this output, the cumulative sum has a u-shape (< zero running
sum) in the first decile of the x-axis variable, then has an inverted
u-shape (> zero running sum) for the remainder of the distribution. If
looked at analogously to a density, it is highly left-skewed.

Any assistance on this would be appreciated.

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index