Glejser’s test, Advanced Statistics

The Null Hypothesis - H0:  There is no heteroscedasticity i.e. β1 = 0

The Alternative Hypothesis - H1:  There is heteroscedasticity i.e. β1 0

Reject H0 if |t | > t = 1.96155

MTB > Let c29=abs(c11)

MTB > let c30 = sqrt(c7)

MTB > let c31 = 1/(c7)

Regression Analysis: absolutness versus sqrttotexp, 1/totexp, sqtotexp

The regression equation is

absolutness = - 0.131 + 0.0153 sqrttotexp + 5.38 1/totexp - 0.000001 sqtotexp

Predictor          Coef          SE Coef          T         P        VIF

Constant       -0.13074     0.06910       -1.89  0.059

sqrttotexp     0.015309    0.005949      2.57  0.010  69.802

1/totexp          5.376        1.502            3.58  0.000  23.180

sqtotexp    -0.00000105  0.00000055  -1.90  0.057  21.096

S = 0.0535194   R-Sq = 1.5%   R-Sq(adj) = 1.3%

Analysis of Variance

Source               DF         SS        MS     F      P

Regression         3      0.065252  0.021751  7.59  0.000

Residual Error   1498 4.290756  0.002864

  Lack of Fit         26    0.062433  0.002401  0.84  0.702

  Pure Error       1472  4.228323  0.002873

Total           1501  4.356008

 2 rows with no replicates

Source      DF    Seq SS

sqrttotexp   1  0.016223

1/totexp     1  0.038664

sqtotexp     1  0.010364

Inverse Cumulative Distribution Function

Student's t distribution with 1498 DF

P( X <= x )        x

      0.975  1.96155

Since the ltoexp 3.58 > 1.96155 (CV), there is evidence to suggest that H0 would be rejected indicating that there is heteroscedasticity.

Posted Date: 3/5/2013 6:08:37 AM | Location : United States

Related Discussions:- Glejser’s test, Assignment Help, Ask Question on Glejser’s test, Get Answer, Expert's Help, Glejser’s test Discussions

Write discussion on Glejser’s test
Your posts are moderated
Related Questions
An approach to investigations designed to recognize a particular medical condition in the large population, usually by means of a blood test, which might result in the considerable

Mardia's multivariate normality test is a test that a set of the multivariate data arise from the multivariate normal distribution against departures due to the kurtosis. The test

MAZ experiments : The Mixture-amount experiments which include control tests for which the entire amount of the mixture is set to zero. Examples comprise drugs (some patients do no

Matching coefficient is a similarity coefficient for data consisting of the number of binary variables which is often used in cluster analysis. It can be given as follows    he

how to constuct design matrix

An approach to decrease the size of very large data sets in which the data are first 'binned' and then statistics such as the mean and variance/covariance are calculated on each bi

The graph for Partial Autocorrelation Function for RES1 shows that there is no autocorrelation even though there are alternating spikes because they fall inside the 5% significance

4-13. Students in a management science class have just received their grades on the first test. The instructor has provided information about the first test grades in some previou

Behrens Fisher problem : The difficulty of testing for the equality of the means of the two normal distributions which do not have the equal variance. Various test statistics have

Non-response is the term generally used for the failure to give the relevant information being collected in the survey. Poor response can be because of the variety of causes, for