We surveyed drumming ruffed grouse (Bonasa umbellus) to estimate the probability of detecting an individual, and we used Bayesian model selection to assess the influence of factors that may affect detection probabilities of drumming grouse. We found the average probability of detecting a drumming ruffed grouse during a daily survey was 0.33. The probability of detecting a grouse was most strongly influenced by the temperature change during a survey (β̂_{temp change} = 0.23, 95% probability interval [PI] = 0.13 ≤ β̂ ≤ 0.33) and its interaction with temperature at the start of the survey (β̂_interaction = 0.01, 95% PI = 1.42 × 10⁻³ ≤ β̂ ≤ 0.03). Although the best model also included a main effect of temperature at the start of surveys, this variable did not strongly correlate with detection probabilities (β̂_{start temp} = −0.03, 95% PI = −0.06 ≤ β̂ ≤ 9.80 × 10⁻⁵). Model assessment using data collected at other sites indicated that this best model performed adequately (i.e., positive correlation between observed and predicted values) but did not explain much of the variation in detection rates. Our results are useful for understanding the historical drumming index used to assess ruffed grouse populations and for designing auditory surveys for this important game bird.