Twelve common errors which can invalidate an otherwise sound evaluation are identified, and ways to avoid them are presented. The hazards are: (1) grade-equivalent scores; (2) inappropriate statistical adjustments with nonequivalent control groups; (3) administering norm-referenced tests at inappropriate times of the school year; (4) inappropriate grade levels of tests; (5) missing scores; (6) noncomparable treatment and control groups; (7) use of a single set of scores for both selecting and pretesting participants; (8) constructing a matched control group after the treatment group has been selected; (9) careless administration and scoring; (10) changing instruments between pretesting and post testing; (11) inappropriate formulas such as IQ or pretest scores to generate no-treatment expectations; and (12) mistaken attribution of observed gains. A table indicates which hazards present the biggest threat to the validity of three Title I evaluation models: control group, norm group, and special regression. (CP)