*
* Example 10.8 from page 349
*
cal 1913
open data fertil3.raw
*
* "t" is a pre-defined variable in RATS, so we've renamed it as "trend"
*
data(org=columns) 1913:1 1984:1 gfr pe year trend tsq pe_1 pe_2 pe_3 $
  pe_4 pill ww2 tcu cgfr cpe cpe_1 cpe_2 $
  cpe_3 cpe_4 gfr_1 cgfr_1 cgfr_2 cgfr_3 cgfr_4 gfr_2
*
* If it didn't exist in the data set, the trend and trend squared could be
* created by
*
set trend = t
set tsq   = t**2
*
* The variable "t" refers to the current entry in a SET instruction
*
linreg gfr
# constant pe ww2 pill trend
linreg gfr
# constant pe ww2 pill trend tsq