There have been many reports of dependent measures derived from resting state EEG data that vary as a function of autism diagnosis. Despite intensive research, there is no clear consensus regarding which of the many common variables extracted from EEG data are the variables that most strongly differentiate autistic from neurotypical resting state EEG data. Identifying which variables are most sensitive to autism holds great promise on two fronts. First, if it is the case that certain variables are more sensitive to autism than others, then this might shed light on the mechanistic etiology of autism. Second, those variables which are most sensitive to autism would be the best candidates for biomarkers. In our previous work, we surveyed a large set of potential biomarkers of Autism in a group of 776 individuals during eyes open rest. No useful biomarkers were uncovered. Using the same analysis pipeline, this secondary analysis focuses on a set of data that were available through the NIMH data archive that included both eyes open and eyes closed rest periods for each participant. The sample included both autistic and neurotypical individuals. This analysis will also focus on multi-scale entropy as its primary dependent measure as this has shown promise in previous literature as being sensitive to autism spectrum disorder.