Tests for heteroscedasticity, Advanced Statistics

Assignment Help:

Lagrange Multiplier (LM) test

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 nR2 > 2094_Tests for Heteroscedasticity.png

Regression Analysis: sqresi versus sqfits

The regression equation is

sqresi = 0.00517 + 0.0196 sqfits

Predictor Coef SE Coef T P VIF

Constant 0.005173 0.001130 4.58 0.000

sqfits 0.019650 0.008395 2.34 0.019 1.000

S = 0.0112996 R-Sq = 0.4% R-Sq(adj) = 0.3%

Analysis of Variance

Source DF SS MS F P

Regression 1 0.0006996 0.0006996 5.48 0.019

Residual Error 1500 0.1915214 0.0001277

Lack of Fit 646 0.0819554 0.0001269 0.99 0.559

Pure Error 854 0.1095659 0.0001283

Total 1501 0.1922209

MTB > let k1 = 1502*0.04

MTB > print k1

Data Display

K1 60.0800

Inverse Cumulative Distribution Function

Chi-Square with 1 DF

P( X <= x ) x

0.95 3.84146

Since nR2 = (1502*0.04) 60.0800 > 3.84146 = 2094_Tests for Heteroscedasticity.png , there is sufficient evidence to reject H0 which suggest that there is heteroscedasticity from the Lagrange Multiplier (LM) test at 5% significance level which means that one or more slopes are not zero.

Related Discussions:- Tests for heteroscedasticity

Functional data analysis, The analysis of data which are the functions obse...

The analysis of data which are the functions observed continuously, for instance, functions of time. Basically a collection of statistical techniques or methods for answering quest

Probability weighting, Probability weighting is the procedure of attaching...

Probability weighting is the procedure of attaching weights equal to inverse of the probability of being selected, to each respondent's record in the sample survey. These weights

Gaussian process, The generalization of the normal distribution used for th...

The generalization of the normal distribution used for the characterization of functions. It is known as a Gaussian process because it has Gaussian distributed finite dimensional m

Captures recapture sampling, Captures recapture sampling : Another approach...

Captures recapture sampling : Another approach to a census for estimating the size of population, which operates by sampling the population number of times, identifying the individ

Mortality odds ratio, Mortality odds ratio is the ratio equivalent to the ...

Mortality odds ratio is the ratio equivalent to the odds ratio used in case-control studies where the equivalent of the cases are deaths from the cause of interest and the equival

Computer-intensive methods, Computer-intensive methods : The statistical me...

Computer-intensive methods : The statistical methods which require almost identical computations on the data repeated number of times. The term computer intensive is, certainly, a

Band matrix, Band matrix: A matrix which has its non zero elements arrange...

Band matrix: A matrix which has its non zero elements arranged uniformly near to the diagonal, so that aij = 0 if (i - j)> ml or (j - i)> mu where aij are the elements of matrix a

Naor''s distribution, Naor's distribution is the discrete probability dist...

Naor's distribution is the discrete probability distribution which arises from the following model; Assume an urn contains n balls of which one is red and the remainder is whit

Recursive models, Recursive models are the statistical models in which the...

Recursive models are the statistical models in which the causality flows in one direction, that is models which include only unidirectional effects. Such type of models do not inc

Define mean squarederror, Mean squarederror is the expected value of squar...

Mean squarederror is the expected value of square of the difference between an estimator and the true value of the parameter. If the estimator is unbiased then the mean of the squ

Write Your Message!

Name

Email id

Message

Verfication Code

User Account

All Pages