st: Clarification Re: Stata 13, +

[Lucas <lucaselastic@gmail.com>]

This is GOOD NEWS!!!  I have a clarification request and a
documentation . . . request.

Clarification:

Am I correct in understanding that the perpetual license entails
exactly the same terms as before if I do not choose the maintenance
option?  Am I correct in understanding that I will be able to update
stata (as long as it is still stata 13.x) if I choose not to pay the
maintenance option?  Or, am I mistaken, and the maintenance fee is
required to "maintain" an up-to-date stata prior to the next major
release?

Documentation Request:

It is great that stata allows users to look through the manual for the
new release early.  I did, and found myself wishing for one simple
change in the multilevel segment, an addition, really.  Many analysts
use the multilevel model to introduce level-2 variables into equations
for level-1 slopes.  So, for example, the analyst might add a variable
for per pupil expenditure to the model such that it alters the slope
for parents' income in a model predicting student test score.

This is a common use of the MLM (e.g., Mason, Wong, and Entwisle 1983;
Bryk and Raudenbush 1986; Gamoran 1992; McCall 2000; Beise and Voland
2002; Hank and Kreyenfeld 2003; Lucas and Berends 2007; Flaherty and
Brown 2010).  Yet, when I look at the manual, it is VERY difficult to
find a single example of the syntax one should use to introduce a
level-2 variable into the model appropriately such that it is
specified as (essentially) a regressor in the equation for a given
slope.  One finds a few examples where a level-2 variable is entered
in (essentially) as a regressor in an equation for the intercept.  I
understand the intercept/slope distinction is "uneasy," yet, this
seems even more reason to wonder -- is it not possible to offer just a
few examples of the syntax for the common use of the MLM to explain
variation in one or more level-1 slopes?

We all tend to look at methods from our location in specific
communities. And, I accept my community is just one of many such that
manuals will often have lots of material not directly relevant to my
work. Yet, as I would go so far as to say that in sociology almost no
one (comparatively) estimates the MLM simply to sweep out nuisance
variation, and the main use is to introduce level-2 (or higher)
variables, it seems odd to have almost zero examples of this use.  I
am not complaining, just observing that it is VERY easy to specify a
model very different from the one one is trying to estimate, because
of the increasing complexity of the possibilities (which is a good
thing).  Given that complexity, a few examples that show how to
specify this kind of model, which many people want to estimate, would
be extremely helpful. Thus, my request for future documentation
through stata for this common (in some fields) use of the MLM.

Respectfully,

Sam
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/