*
* Example generating graphs like page 801
*
all 500
*
* Draw random numbers. These won't be the same as the ones used in the graphs in
* the text. If you want to control the "random" numbers so you get the same
* results each time, you can use the "SEED" instruction, which takes the form
* SEED number, such as  SEED 59304. If you don't the random numbers will be
* different each time you run a program.
*
* %RAN1.0) gives random Normals with mean zero and standard deviation 1.0.
*
set u = %ran(1.0)
*
* Create the two series, one with no drift, one with drift
*
set(first=0.0) ynd = ynd{1}+u
set(first=0.0) yd  = yd{1}+2+u
*
* Graph the series. Figure 21.4 was clearly generated by a different process than
* the one cited (it actually looks quite similar to 21.3), since
* y(t)=2+y(t-1)+u(t) should be increasing by 2 on average, and should be
* somewhere around 1000 by the end of the sample.
*
graph
# ynd
graph
# yd