The results of a small research project that studied the effect computer administration has on student performance for writing or essay tests are presented. The introduction of computer-administered tests has raised concern about the equivalence of scores generated by computer versus paper-and-pencil test versions. For this study a sample of students from the Advanced Laboratory School in Worcester, Massachusetts completed performance writing items and items from the National Assessment of Educational Progress in the traditional paper-and-pencil form or in a computerized version developed for the study. The actual number of students who participated was 42 in the computer test group and 47 in the traditional test group. The final test consisted of a combination of multiple-choice and open-ended items. To score the performance writing item, all hand-written responses were entered verbatim into the computer to prevent raters from knowing which responses were originally written by hand. Unlike much previous research on the effects of computer administration of tests, these results indicate substantial effects due to mode of administration. The size of effects was found to be larger on open-ended writing tasks than on multiple-choice tests, and the effect of mode of administration was particularly large on the extended writing task. A textual analysis of student responses to the extended writing task shows that students using the computer tended to write almost twice as much and are more apt to organize their responses into paragraphs. (Contains 6 tables and 18 references.) (SLD)