Research conducted in the past ten years under the auspices of ASTM G-3 has been pointed at evaluating the quality of test information that is obtained when following the G-3 weathering standards. The results of these studies indicated that gloss data obtained from replicate specimens using identical equipment, following identical standard practices, had poor (lab-to-lab) reproducibility. Many material specifications used by both government and industry rely on weathering tests having “good” reproducibility so that exposure results from different laboratories can be compared. The primary purpose of this paper is to demonstrate a recommended weathering experiment and subsequent data treatment. Emphasis is placed on the use of analysis of variance to determine statistically significant performance differences for materials exposed in weathering tests. When analysis of variance is used in conjuction with an appropriate reference material, weathering specification tests can be established that have excellent reproducibility and are in compliance with the precision and bias recommendations of ASTM G-3 weathering standards.