Goodness-of-Fit Tests for RAND4

Chi-Square Test

	Chi-Square	Gamma	Normal	Uniform	Weibull
Chi-Square	126,72	107,52	80,96	30,72	76,8
D.f.
P-Value	7,4829E-14	5,91914E-11	8,37522E-7	0,378742	0,00000337147

 

Kolmogorov-Smirnov Test

	Chi-Square	Gamma	Normal	Uniform	Weibull
DPLUS	0,228625	0,097676	0,0788659	0,0317271	0,0727645
DMINUS	0,0697265	0,10737	0,0899839	0,0433768	0,089851
DN	0,228625	0,10737	0,0899839	0,0433768	0,089851
P-Value	0,0	0,019878	0,0784207	0,846001	0,0791743

 

Modified Kolmogorov-Smirnov D

	Chi-Square	Gamma	Normal	Uniform	Weibull
D	0,228625	0,10737	0,0899839	0,0433768	0,089851
Modified Form	3,26245	1,53215	1,27707	0,618984	1,27069
P-Value	<0.01*	<0.05*	<0.01*	>=0.10*	<0.01*

 

Cramer-Von Mises W^2

	Chi-Square	Gamma	Normal	Uniform	Weibull
W^2	1,46688	0,65957	0,31951	0,000422917	0,430021
Modified Form	1,47222		0,320309	-0,00156989	0,436103
P-Value	<0.01*	*	0,000195397*	>=0.10*	<0.01*

 

Anderson-Darling A^2

	Chi-Square	Gamma	Normal	Uniform	Weibull
A^2	9,87324	4,07313	2,51094		3,12265
Modified Form	9,87324		2,52049		3,16681
P-Value	<0.01*	*	0,00000231145*	*	<0.01*

*Indicates that the P-Value has been compared to tables of critical values specially constructed for fitting the selected distribution. Other P-values are based on general tables and may be very conservative (except for the Chi-Square Test).

 

The StatAdvisor

This pane shows the results of tests run to determine whether RAND4 can be adequately modeled by various distributions. The chi-square test divides the range of RAND4 into nonoverlapping intervals and compares the number of observations in each class to the number expected based on the fitted distribution. The Kolmogorov-Smirnov test computes the maximum distance between the cumulative distribution of RAND4 and the CDF of the fitted distribution. The other statistics compare the empirical distribution function to the fitted CDF in different ways.

 

P-values less than 0,05 would indicate that RAND4 does not come from the selected distribution with 95% confidence.

RAND9 - Гамма (3 параметра) - shape = 219,992 scale = 5,70041, lower threshold = -39,3596

Goodness-of-Fit Tests for RAND9

Chi-Square Test

	Cauchy	Gamma (3-Parameter)	Generalized Logistic	Laplace	Normal
Chi-Square	61,44	16,0	23,04	23,36	24,96
D.f.
P-Value	0,000407516	0,965819	0,731036	0,759816	0,680322

 

Kolmogorov-Smirnov Test

	Cauchy	Gamma (3-Parameter)	Generalized Logistic	Laplace	Normal
DPLUS	0,0709505	0,0274212	0,0239477	0,0389754	0,0312147
DMINUS	0,0789628	0,0326974	0,0272204	0,0651018	0,0296915
DN	0,0789628	0,0326974	0,0272204	0,0651018	0,0312147
P-Value	0,165197	0,983083	0,998422	0,368224	0,98989

 

Modified Kolmogorov-Smirnov D

	Cauchy	Gamma (3-Parameter)	Generalized Logistic	Laplace	Normal
D	0,0789628	0,0326974	0,0272204	0,0651018	0,0312147
Modified Form	1,12679	0,46659	0,388433	0,928997	0,443006
P-Value	>=0.10*	>=0.10*	>=0.10*	>=0.10*	>=0.10*

 

Cramer-Von Mises W^2

	Cauchy	Gamma (3-Parameter)	Generalized Logistic	Laplace	Normal
W^2	0,206174	0,0257776	0,0204644	0,13706	0,0273666
Modified Form			0,0185717	0,13575	0,027435
P-Value	*	*	>=0.10*	>=0.10*	0,879694*

 

Anderson-Darling A^2

	Cauchy	Gamma (3-Parameter)	Generalized Logistic	Laplace	Normal
A^2	2,43835	0,199009	0,171928	0,856734	0,200977
Modified Form			0,171928	0,856734	0,201741
P-Value	*	*	>=0.10*	>=0.10*	0,880415*

*Indicates that the P-Value has been compared to tables of critical values specially constructed for fitting the selected distribution. Other P-values are based on general tables and may be very conservative (except for the Chi-Square Test).

 

The StatAdvisor

This pane shows the results of tests run to determine whether RAND9 can be adequately modeled by various distributions. The chi-square test divides the range of RAND9 into nonoverlapping intervals and compares the number of observations in each class to the number expected based on the fitted distribution. The Kolmogorov-Smirnov test computes the maximum distance between the cumulative distribution of RAND9 and the CDF of the fitted distribution. The other statistics compare the empirical distribution function to the fitted CDF in different ways.

 

P-values less than 0,05 would indicate that RAND9 does not come from the selected distribution with 95% confidence.

RAND15 - Хи-Квадрат c количеством степеней свободы - degrees of freedom = 6,22819