1, µ2, γ1, γ2 ) n=100 n=1000
(0,0,0,0) 0.032 0.038
(1, -1, 0.1, 0.1)
(1, -1, 0.2, 0.2)
(2, -2, 0.1, 0.1)
(2, -2, 0.2, 0.2)
0.033
0.024
0.080
0.002
0.056
0.024
0.507
0.055
(1, 0, 0.2, 0.1) 
( 0, -1, 0.2, 0.1)
(2, 0, 0.2, 0.1)
  ( 0, -2, 0.2, 0.1)
0.197 
0.073
0.730
0.319
1.000
0.661
1.000
1.000
(1, -1, 0.2, 0.1)
(1, -2, 0.1, 0.1)
(2, -2, 0.2, 0.1)
(2, -1, 0.2, 0.2)
0.045
0.138
0.088
0.135
0.541
0.958
0.946
0.999
Shown above are results from testing the omnibus null hypothesis based on a
simulation of size 1000 and using the procedure from Section 2.
Table 3: Daytime high temperature 3-day forecast vs actual, ranked by the
standard deviations of forecast errors.