GIS-based regression modeling of the extreme weather patterns in Arkansas, USA

Geoenvironmental Disasters

Table 1 Ordinary Least Squares results for tornadoes

	Variable	Coefficient	StdError	t-Statistic	Probability	Robust_SE	Robust_t	Robust_Pr	VIF
Event	Intercept	2.9560	0.2807	10.5299	0.000000*	0.2917	10.1329	0.000000*	–
	Month	0.0279	0.0059	4.7338	0.000003*	0.0058	4.8383	0.000002*	1.0391
	ADJ_TIME	0.0246	0.0035	7.0107	0.000000*	0.0031	7.8801	0.000000*	1.1056
	SUM_MAG	0.4708	0.0042	112.0444	0.000000*	0.0049	96.6009	0.000000*	1.1092
	AR_ECO_ID	−0.0021	0.0002	−13.1645	0.000000*	0.0002	−11.4925	0.000000*	1.0497
	Protection	0.1328	0.0517	2.5702	0.010193*	0.0403	3.2951	0.001009*	1.0600
Magnitude	Intercept	−6.3259	0.5174	−12.2254	0.000000*	0.4869	−12.9926	0.000000*	–
	Month	−0.0274	0.0109	−2.5071	0.012203*	0.0107	−2.5624	0.010423*	1.0452
	ADJ_TIME	0.0096	0.0065	1.4702	0.141599	0.0057	1.6650	0.096012	1.1194
	Event (Sum)	1.6066	0.0145	111.0131	0.000000*	0.0173	92.6609	0.000000*	1.1401
	Elevation	−0.0011	0.0004	−3.0899	0.002030*	0.0004	−3.0349	0.002434*	1.9239
	Trailer Parks	−0.0411	0.0080	−5.1587	0.000001*	0.0082	−5.0265	0.000001*	1.1378
	AR_ECO_ID	0.0054	0.0004	15.1201	0.000000*	0.0004	13.6639	0.000000*	1.5146
	Protection	0.0552	0.1118	0.4935	0.621665	0.0894	0.6170	0.537257	1.4571
			Joint Wald	Jarque-Bera	Koenker (BP) Statistic	AICc	Adjusted R2
			11,822.594	254.1233	1002.2988	13,317.7251	0.78686

Significant p-values (p < 0.01) are denoted by *, StdError is the standard deviation error, t-Statistic is the ratio between estimated and hypothesized values relative to StdError, probability and robust probability (_Pr) are significant when (p < 0.01), Koenker statistic determines significance of coefficients, and VIF is the variance inflation factor with values > 7.5 are indicative of redundancy. Joint Wald determines overall significance if Koenker value is significant, AICc and R² represent overall fit and performance