The effects of luck and misinformation on ability of multiple-choice test scores to estimate examinee ability were investigated. Two measures of examinee ability were defined. Misinformation was shown to have little effect on ability of raw scores and a substantial effect on ability of corrected-for-guessing scores to estimate examinee ability. Luck was shown to be influential on ability of raw and corrected-for-guessing scores to estimate ability, though this influence was more pronounced for raw scores. Analysis of data confirmed all theoretical results. Furthermore, empirical results showed that raw scores were better estimators of examinee ability. (Author)