Cervical manipulation has been considered an effective treatment for managing neck pain. However, clinical observation showed that cervical manipulation was not effective for every patient. Development of clinical prediction rules for identifying patients with neck pain who are likely to respond to cervical manipulation may improve clinical decision-making and the treatment success rate. The purpose of the study was to identify predictors for the immediate responders to cervical manipulation treatment in patients with neck pain. One hundred patients with neck pain (34 males and 66 females, mean age = 46 +/- 11 years) participated in the study. Patient's demographic data, symptom aggravating or easing factors, pain, and disability level were obtained through an initial assessment. A series of physical examinations were also administered. After receiving a single session of cervical manipulation, the patient was re-evaluated immediately to determine if a successful response to treatment was obtained. The successful response was determined by improvements seen in one of the three outcome variables that included reduction of pain intensity, significant perceived improvement, and high satisfaction level. From these judgment criteria, patients were classified into either responders or nonresponders to the cervical manipulation. Univariate analyses were used to assess if the treatment responders and nonresponders were different in their clinical presentations. The clinical factors that showed significant differences between two groups were then entered into a stepwise multiple logistic regression analysis to identify significant predictors and the prediction rule for treatment responders. Six predictors including "initial scores on Neck Disability Index < 11.50", "having bilateral involvement pattern", "not performing sedentary work > 5 h/day", "feeling better while moving the neck", "without feeling worse while extending the neck", and "the diagnosis of spondylosis without radiculopathy" were identified to significantly predict the immediate responders. The presence of four or more of these predictors increased the probability of success with manipulation to 89%. We concluded that using favourable predictors to identify treatment responders before administering cervical manipulations could significantly increase the probabilities of a successful treatment. This study finding may enhance the efficacy of clinical decision-making in using cervical manipulation intervention.