A procedure which employs a method of item substitution based on item difficulty is recommended for developing parallel criterion referenced test forms. This procedure is currently being used in the Florida functional literacy testing program and the Georgia teacher certification testing program. Reasons for developing parallel test forms involve test security and avoidance of the spread of knowledge about test content resulting from repeated administrations. Both maintenance of strict content parallelism and individual examinee classification consistency are insured when parallel forms are generated using p-values for item-by-item substitution. (MH)