An ignited rupture of a gas transmission pipeline has serious consequences in terms of human safety.  The evaluation of the probability of ignition (POI) for a potential pipeline rupture is therefore critical for the risk assessment of pipelines.  This paper proposes a log-logistic regression model to evaluate the probability of ignition for ruptures of onshore gas transmission pipelines.  The pipeline incident data collected by the Pipeline and Hazardous Material Safety Administration (PHMSA) of the United States Department of Transportation (DOT) are utilized to develop the POI model, as a function of the pipe diameter and operating pressure.  The parameters in the model are estimated using the maximum likelihood method.  The proposed probability of ignition model is applied in the quantitative risk assessment of a hypothetical gas pipeline.  The societal risk level associated with the hypothetical pipeline is quantified by considering the probability of rupture, probability of ignition given rupture, and population distributions in the vicinity of the pipeline.  The proposed POI model will facilitate the risk assessment of onshore gas transmission pipelines.