Ronald A. Fisher (1922) formulated the concept of the likelihood of the data given a statistical model that is hypothesized to have generated those data and a set of parameter estimates. Maximum likelihood estimates are the parameters values which maximize the likelihood that the observed data would have been generated. Thus MLE values correspond to the mode of the likelihood function.
Thomas Warm (1989) points out the that those modal estimates are biased when viewed from the likelihood function as whole. He suggests that, rather than the mode of the likelihood function, estimates should be based on its mean. These estimates have come to be called "Warm estimates", and his approach is Warm (or Weighted) (Maximum) Likelihood Estimation" (WLE or WMLE).
In the Rasch model, the estimation of MLE and WLE require iteration. WLE is more computationally intensive. Warm demonstrates that the asymptotic variance of MLE and WLE estimates are the same, meaning that the estimates have the same model standard errors.
WLE estimates are generally slightly more central than MLE estimates, though the implications of this for practical applications are not clear, because the difference is usually less than the standard error of the estimates.
Fisher R.A., (1922) "On the mathematical foundations of theoretical statistics" Philosophical Transactions of the Royal Society of London (A) 222, 1922, p. 309-368.
Warm T.A. (1989) "Weighted Likelihood Estimation of Ability in Item Response Theory." Psychometrika, 54, 427-450.
Note: Winsteps and Facets do not use MMLE or WLE, because Winsteps and Facets embody the philosophy that:
1. transposing the data matrix (exchanging the persons and items) should impact estimation as little as possible.
2. estimating the person and item measures from a free analysis should produce the same results as (i) anchoring the items at their free estimates, and estimating the person measures, or (ii) anchoring the persons at their free estimates and estimating the item measures.
Warm (Maximum) Likelihood Estimates. Warm T.A. … Rasch Measurement Transactions, 2007, 21:1 p. 1094
The URL of this page is www.rasch.org/rmt/rmt211h.htm
Website: www.rasch.org/rmt/contents.htm