The following seven statistical procedures are compared in terms of the ability to recover a unidimensional latent trait from Likert-type data: (1) factor analysis based on Pearson correlations (FA-PR); (2) factor analysis based on polychoric correlations (FA-PL); (3) the graded response model in item response theory (IRT-GRM); (4) internal unfolding (IMDU); (5) external unfolding (EMDU); (6) weighted unfolding (WMDU); and (7) summing up successive integers assigned to response categories (SSI). In this simulation study, sample size varied (n=30, n=100, and n=1,000 subjects), and test length (12 versus 24 items) and skewness of item response distributions were manipulated. Generally speaking, IRT-GRM performed best and was most robust against skewness. FA-PR and FA-PL performed equally well across almost all conditions, but were competitive with IRT-GRM only when item responses were normally distributed. SSI practice performed slightly worse than did the two FA procedures when item responses were normally distributed, but performed better when item responses were highly skewed. WMDU performed as well as did SSI only when item responses were normally distributed or moderately skewed and sample size was large for multidimensional scaling models (e.g., n=100). IMDU and EMDU performed worse than did WMDU and appeared to be inappropriate for Likert-type data. Eight tables present the comparative data. A 48-item list of references is included. (Author/SLD)