A conditional‐on‐a‐single‐stimulus (COSS) analysis procedure [B. G. Berg, J. Acoust. Soc. Am.86, 1743–1746 (1989)] was used to measure the weight or relative reliance that normal‐hearing and hearing‐impaired listeners give to different frequencies in the discrimination of the overall level of a multitone complex. On each trial, two multitone‐tone complexes comprised of six octave frequencies from 250 to 8000 Hz were presented to subjects. The levels of the frequencies for each complex were randomly varied. The listeners task was to identify the complex with the higher overall intensity level. Normal‐hearing listeners used a variety of listening strategies to perform the task, showing no general preference to weight one component over another. Hearing‐impaired listeners, however, showed a general tendency to give greatest weight to the spectral information in the region of their hearing loss. Thirteen of the 14 hearing‐impaired listeners, all of whom had a high‐frequency sensorineural hearing loss, weighted one or more of the high‐frequency components in the complex the greatest.