1
1 Durbin Watson Test The Durbin-Watson statistic is a simple numerical method for checking serial dependence. Let r k be the residuals sorted into time order. Then the Durbin- Watson statistic is: DW = n-1 k=1 (r k - r k+1 ) 2 n k=1 r 2 k . We have the following criterion: DW < 2 2 > 2 Decision Positive Serial Correlation NO serial correlation Negative Serial Correlation As a rough rule, serial correlations corresponding to DW outside the range 1.5 2.5 are large enough to have a noticeable effect on our inference techniques. Note that DW itself is random and may be outside the range 1.5 to 2.5, even if the errors are uncorrelated. For data sets with long runs of units from the same treatment, the variance of DW is a bit less than 4/N. In R, the durbin-watson test is located in library(lmtest): > dwtest(formula)# z - time index. Figure 1: Durbin Watson Test 1

DurbinWatson Test

Embed Size (px)

DESCRIPTION

Type of venting system where the vent connects with a single fixture trap, usually at the back and extends vertically and connects with a stack vent, a vent stack or branch vent.

Citation preview

  • 1 Durbin Watson Test

    The Durbin-Watson statistic is a simple numerical method for checking serialdependence. Let rk be the residuals sorted into time order. Then the Durbin-Watson statistic is:

    DW =n1

    k=1(rk rk+1)2nk=1 r

    2k

    .

    We have the following criterion:

    DW < 2 2 > 2Decision Positive Serial Correlation NO serial correlation Negative Serial Correlation

    As a rough rule, serial correlations corresponding to DW outside the range1.5 2.5 are large enough to have a noticeable effect on our inference techniques.Note that DW itself is random and may be outside the range 1.5 to 2.5, even ifthe errors are uncorrelated. For data sets with long runs of units from the sametreatment, the variance of DW is a bit less than 4/N.

    In R, the durbin-watson test is located in library(lmtest):

    > dwtest(formula) # z time index.

    Figure 1: Durbin Watson Test

    1