Nick, thank you for the extensive reply. I shall definitely look into
smoothers in future.
As for graphing,
. twoway (connected xxx year, msymbol(O)) if (int(year/12) == year/12)
is great shortcut and
. use http://www.stata-press.com/data/r9/air2.dta
. tsline air if mod(t, 12) == 1
is the exactly the same solution I stumbled upon while going over
"Scheming your way to consistent graphs" by Vincent L. Wiggins (12th
UK Stata Users Group meeting).
Again, the data I have is [1970m01-2007m01] so that there are 37yrs
and 445 obs. The original question arose purely from the
presentational standpoint. When graphing (in black-and-white) 3 or
more time-series that exhibit almost the same behaviour, the use of
"dot-dash" lines requires the reader to exert additional effort to
differentiate the series. Thus, the use of markers seemed to be the
option to apply instead. With many observations & variables though
markers really start to make the graph look bizarre.
Cyril
*
* 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/