Traditionally, the errors-in-variables problem is concerned with the point estimation of the slope of the true scores regression line when the regressor is measured with error, and when no specification error is present. In this paper, the errors-in-variables problem is extended to include specification error. Least squares procedures provide a biased estimator of the slope of the true scores regression line. Further, the maximum likelihood estimates of the slope (which are consistent) exist only once some assumptions are made. Maximum likelihood estimates are given for the extended version of the errors-in-variables problem (i.e., when specification error is present) under the usual assumptions and under several new assumptions that are more appropriate for the social and behavioral sciences than the previously used assumptions. A simulation study illustrates this process. The results of the study indicate that the maximum likelihood estimates (both under the old and new assumptions) far outperform the least squares procedures when several different criteria (such as bias and standard error) are used. Eleven tables are presented. (Author/TJH)