This study investigates two fixed parameter models for calibrating test items for an item bank under local school district control. Mathematics, reading, and language tests administered to students (Grades 7-9) provided the criterion information. Model I used calibrations from the Northwest Evaluation Association Item Bank to calibrate new items on the criterion-referenced test. Six random samples of 150, 200, 250, and 300 students were drawn for the condition of "fixing" 10, 20, or 30 items of a 40-item test. There was no discernible effect of fixing increasing numbers of test items. Model II used student scores from the Rasch scaled Tests of Individual Performance (TIP) for its item calibrations. Calibration accuracy was compared for samples of 100, 150, or 200 students drawn without replacement. A sample size of 200 was recommended for accurate item calibration. Model II applied well, even when the calibrating test and the test to be calibrated were given at different times of the year, with appropriate adjustment for average achievement differences in the time interval. Model II is recommended as an improved item analysis technique because: (1) it uses a mathematically independent criterion; and (2) it can be related to any Rasch scale. (LPG)