Poisson autoregressive models of order p of daily wildland arson fire occurrences for selected high-arson California national forests, 1994-2002
The majority of these findings are consistent with those of Prestemon and Butry (2005), supporting an economic model of crime and one that confirms the temporal clustering of arson ignitions on these forests. However, some conflicting results lead us to conclude that further research into the daily arson firesetting process for California national forests is necessary.
| San Bernadino N.F. |
| Sierra N.F. |
| Cleveland N.F. |
| Angeles N.F. |
|
Intercept | -1.49 |
| 26.97 |
| -1.73 |
| 34.65 | *** |
Average Annual Palmer Drought Severity Index, t | 0.93 |
| 3.11 |
| -0.65 |
| 0.24 |
|
Weekday | -0.66 | *** | -0.35 |
| 0.16 |
| -0.12 |
|
Saturday | -0.74 | ** | 1.22 | ** | 0.66 | * | 0.40 |
|
Sunday | -0.47 |
| -0.54 |
| 0.76 | ** | 0.15 |
|
Holiday | -0.36 |
| 1.57 | ** | 0.35 |
| 0.17 |
|
January | -0.20 |
| n.p. |
| -0.73 |
| 0.37 |
|
February | 1.07 |
| n.p. |
| -1.18 |
| 0.87 |
|
March | -0.72 |
| 1.97 |
| -0.36 |
| 0.20 |
|
April | -0.62 |
| 1.62 |
| 0.22 |
| 1.15 | ** |
May | 1.46 | * | 0.55 |
| 0.66 |
| 1.55 | *** |
June | 1.72 | ** | 0.96 |
| 1.22 | * | 1.57 | *** |
July | 1.62 | * | 1.72 |
| 1.32 | * | 2.04 | *** |
August | 1.96 | ** | 0.96 |
| 1.36 | ** | 2.16 | *** |
September | 2.02 | ** | -0.25 |
| 1.72 | *** | 1.75 | *** |
October | 1.84 | ** | -0.30 |
| 0.87 |
| 1.37 | ** |
November | 0.82 |
| 1.26 |
| 0.46 |
| 0.81 |
|
Law Enforcement Officers Per Capita, t-1 | -1.90 |
| 13.67 | * | -17.09 | * | -1.75 |
|
Population, t | n.p. |
| -0.088 |
| 5.6549 |
| -0.0028 | * |
Unemployment, t | 4.76 | * | -6.37 | ** | 10.39 | *** | -3.71 | * |
Wildfire, t-1 to t-3 | 0.02 |
| -1.12 |
| -0.37 | ** | -0.08 | * |
Wildfire, t-4 to t-6 | 0.01 |
| 0.59 |
| -0.14 |
| -0.11 |
|
Wildfire, t-6 to t-9 | 0.06 |
| 0.77 |
| 0.03 |
| -1.02 | ** |
Wildfire, t-10 to t-12 | -0.23 |
| 0.06 |
| 0.02 |
| -1.09 | ** |
Wildfire, t-13 to t-15 | -0.05 |
| 0.75 |
| -0.27 | ** | -0.04 |
|
AR(1) | 0.29 | *** | 0.49 | ** | 0.37 | *** | 0.26 | *** |
AR(2) | 0.38 | *** | n.p. |
| 0.60 | *** | 0.16 | *** |
AR(3) | 0.24 | ** | n.p. |
| n.p. |
| 0.17 | *** |
AR(4) | n.p. |
| n.p. |
| n.p. |
| 0.21 | *** |
AR(5) | n.p. |
| n.p. |
| n.p. |
| 0.16 | *** |
n | 3,089 |
| 3,090 |
| 3,091 |
| 3,103 |
|
Likelihood Ratio Statistic, Model Versus Intercept Only |
|
|
|
|
|
|
|
|
Likelihood Ratio Statistic, Model All AR Terms Are Zero (df = p) | 38.37 | *** | 7.47 | *** | 70.77 | *** | 142.32 | *** |
Log Likelihood, Model | -651.60 |
| -257.29 |
| -566.56 |
| -896.62 |
|
Note: “***” indicates significance at 1 percent, “**” at 5 percent, and “*” at 15 percent. “n.p.” indicates that models with this variable included would not converge in maximum likelihood estimation.
Copyright: Public Domain
