Evaluating alternate discrete outcome frameworks for modeling crash injury severity

Download 0.61 Mb.

Page	10/12
Date	18.10.2016
Size	0.61 Mb.
	#2776

1 ... 4 5 6 7 8 9 10 11 12

TABLE 3 Elasticity Effects

Variables	MGOL				MMNL
Variables	Non-incapacitating injury	Incapacitating /Fatal injury	% of error in Non-incapacitating injury	% of error in incapacitating /Fatal injury	Non-incapacitating injury	Incapacitating /Fatal injury	% of error in Non-incapacitating injury	% of error in Incapacitating/Fatal injury
Estimation sample
Male	-17.28	-20.35	˗	˗	-25.26	-14.51	˗	˗
Age less than 25	-24.07	-29.69	˗	˗	-19.97	-14.72	˗	˗
Passenger car	15.23	18.76	˗	˗	13.02	9.50	˗	˗
High speed limit	43.77	57.44	˗	˗	38.41	63.82	˗	˗
Snowy surface	-32.69	-38.40	˗	˗	-24.20	-44.32	˗	˗
Head-on collision	27.54	153.04	˗	˗	20.27	173.52	˗	˗
Underreported sample without corrections
Male	-11.33	-12.06	34.44	40.74	-16.42	-7.07	35.00	51.25
Age less than 25	-18.47	-25.14	23.26	15.31	-18.80	-13.62	5.85	7.49
Passenger car	12.25	16.76	19.60	10.65	11.08	6.03	14.89	36.47
High speed limit	36.23	55.73	17.23	2.97	28.37	47.52	26.15	25.54
Snowy surface	-22.36	-28.92	31.61	24.70	-11.83	-34.33	51.13	22.53
Head-on collision	6.61	121.98	75.99	20.30	8.55	151.89	57.83	12.46
Average Error	˗	33.69	˗	19.11	˗	31.81	˗	25.96
Underreported sample with corrections
Male	-15.57	-17.32	9.88	14.87	-23.19	-12.78	8.17	11.90
Age less than 25	-20.96	-26.24	12.93	11.62	-23.14	-17.43	15.88	18.39
Passenger car	13.95	17.49	8.43	6.78	17.69	10.42	35.89	9.70
High speed limit	43.44	58.88	0.74	2.51	38.87	57.10	1.20	10.53
Snowy surface	-24.85	-29.97	23.99	21.96	-16.83	-37.70	30.46	14.94
Head-on collision	16.96	130.13	38.41	14.96	24.56	177.21	21.19	2.13
Average Error	˗	˗	15.73	12.12	˗	˗	18.80	11.27

TABLE 4 Disaggregate Measures of Fit in Validation Sample

DISAGGREGATE MEASURE OF FIT IN VALIDATION SAMPLE
Summary statistic		MGOL predictions	MMNL predictions
Number of observations		3993.9900	3993.9900
Number of parameters		55	61
Log-likelihood at zero		-5536.8458	-5536.8458
Log-likelihood at sample shares		-3962.5600	-3962.5600
Predictive Log-likelihood		-3671.0702	-3643.0636
	C.I.	-3685.6638/-3656.4766	-3657.3289/-3628.7984
AICc		7453.7050	7410.0514
	C.I.	7424.5207/7482.8892	7381.5246/7438.5782
BIC		7798.2252	7791.9668
	C.I.	7768.9357/7827.5147	7763.3179/7820.6156
Predictive adjusted likelihood ratio index		0.0597	0.0652
	C.I.	0.0578/0.0615	0.0638/0.0667
Average probability of correct prediction		0.6649	0.6663
	C.I.	0.6636/0.6662	0.6650/0.6677
Average probability for chosen probability>0.70		0.4787	0.4620
	C.I.	0.4774/0.4799	0.4609/0.4632

Directory: neluru -> Papers
Papers -> A latent class modelling approach for identifying vehicle driver injury severity factors at highway-railway crossings
Papers -> Impact of ict access on personal activity space and greenhouse gas production: evidence from Quebec City, Canada
Papers -> Alternative Modeling Approaches Used for Examining Automobile Ownership: a comprehensive Review
Papers -> Travel Mode Choice and Transit Route Choice Behavior in Montreal: Insights from McGill University Members Commute Patterns Naveen Eluru
Papers -> An Analysis of Bicycle Route Choice Preferences in Texas, U. S
Papers -> Analysis of vehicle ownership evolution in montreal, canada using pseudo panel analysis

Download 0.61 Mb.

Share with your friends:

1 ... 4 5 6 7 8 9 10 11 12

The database is protected by copyright ©ininet.org 2024
send message

information presented