Information About

Disattenuation
  CATEGORIES ABOUT DISATTENUATION
   
measurement
   
APPAREL
BABY
BEAUTY
BOOKS
CAR TOYS
CELL PHONES
DVD'S
ELECTRONICS
GOURMET FOOD
GROCERIES
HEALTH & PERSONAL
HOME & GARDEN
JEWELRY
MUSIC
MUSIC INSTRUMENTS
OFFICE PRODUCTS
SOFTWARE
SPORTING GOODS
TOOLS & HARDWARE
TOYS
VIDEO GAMES
SHOPPING HOME
MORE SHOPPING...




BACKGROUND


Correlations between parameters are diluted or weakened by measurement error. Disattenuation provides for a more accurate estimate of the correlation between the parameters by accounting for this effect.

Let \beta_n and heta_n be the measures of two attributes of person ''n'' and let \hat{\beta_n} be a Maximum Likelihood estimate of \beta_n derived from application of a measurement model, such as the Rasch Model . Also, let:

::
\hat{\beta_n} = \beta_n + \epsilon_n


where \epsilon_n is the measurement error associated with the estimate \hat{\beta_n}, as per Fisher Information theory. Specifically, the Variance of the maximum likelihood estimate of a person Parameter is given by the negative of the reciprocal of the second Derivative of the log-likelihood function with respect to the parameter. The person parameter represents the theoretical measure of the person for the relevant attribute or trait.


DERIVATION OF THE FORMULA


The correlation between two sets of estimates is

:
\mbox{corr}(\hat{\beta_n},\hat{ heta_n})= rac{\mbox{cov}(\hat{\beta_n},\hat{ heta_n})}{\sqrt{\mbox{var}[\hat{\beta}]\mbox{var}[\hat{ heta}}]}


:::::
= rac{\mbox{cov}(\beta_n+\epsilon_1 , heta_n+\epsilon_2)}{\sqrt{\mbox{var}[\beta_n+\epsilon_1]\mbox{var}[ heta_n+\epsilon_2]}},


which, assuming the errors are uncorrelated with each other and with the estimates, gives

:
\mbox{corr}(\hat{\beta_n},\hat{ heta_n})= rac{\mbox{cov}(\beta_n, heta_n)}{\sqrt{(\mbox{var}[\beta_n]+\mbox{var}[\epsilon_1])(\mbox{var}[ heta_n]+\mbox{var}[\epsilon_2])}}


:::::
= rac{\mbox{cov}(\beta_n, heta_n)}{\sqrt{(\mbox{var}[\beta_n]\mbox{var}[ heta_n])}}. rac{\sqrt{\mbox{var}[\beta]\mbox{var}[ heta]}}{\sqrt{(\mbox{var}[\beta_n]+\mbox{var}[\epsilon_1])(\mbox{var}[ heta_n]+\mbox{var}[\epsilon_2])}}


:::::
= ho \sqrt{R_\beta R_ heta},


where R_\beta is the ''separation index'' of the set of estimates of \beta_n , n = 1,...,N, which is analogous to Cronbach's Alpha ; this is, in terms of Classical Test Theory , R_\beta is analogous to a reliability coefficient. Specifically, the separation index is given as follows:

:
R_\beta= rac{\mbox{var}[\beta]}{\mbox{var}[\beta]+\mbox{var}[\epsilon_1]}= rac{\mbox{var}[\hat{\beta}]-\mbox{var}[\epsilon_1]}{\mbox{var}[\hat{\beta}]},


where the mean squared standard error of person estimate gives an estimate of the variance of the errors, \epsilon_n, across persons. The standard errors are normally produced as a by-product of the estimation process (see Rasch Model Estimation ).

The disattenuated estimate of the correlation between two sets of parameters or measures is therefore

:
ho = rac{\mbox{corr}(\hat{\beta_n},\hat{ heta_n})}{\sqrt{R_\beta R_ heta}}.


That is, the disattenuated correlation is obtained by dividing the correlation between the estimates by the square root of the product of the separation indices of the two sets of estimates. Expressed in terms of Classical test theory, the correlation is divided by the square root of the product of the reliability coefficients of two tests.


SEE ALSO

Regression Dilution .




EXTERNAL LINKS