Studies of sound changes in sociolinguistics have shown a consistent trend that women tend to be linguistically innovative and lead most of the major sound changes. Additionally, women have been shown to use more standard variants than men in stable sociolinguistic variables, giving rise to the "gender paradox" where women are both linguistically conservative and innovative. Studies that examine variation within sex groups unravel this paradox by showing that different women behave differently--some being conservative language users while others are innovative. Traditional methods that aim to examine the role of gender in ongoing sociolinguistic change often use sex as a binary variable instead of socially defined degrees of masculinity and femininity. These methods group all women, innovative and conservative, into one sex-based group, and the distinction between those who lead the change and lag behind is lost. Additionally, qualitative studies of leaders of linguistic change have shown similarities in leaders, but there are no quantitative methods to predict leaders of change. This dissertation goes beyond traditional studies of gender variation to create a quantitative methodology to examine leaders in linguistic changes and explain gender-based patterns of linguistic behavior. A representative set of vowel tokens from speakers from Southeastern Michigan was measured and normalized for each subject, and these data were used in multiple regression analyses to identify how speakers pattern in respect to the Northern Cities Shift (NCS), a female-led sound change in the vowel system of speakers from urban Great Lakes areas, and possible factors affecting changes. The main factors studied are self-evaluations on 60 personality traits from Bem's Sex Role inventory, which consists of feminine, masculine, and gender-neutral traits. From the feminine and masculine traits, gender indexes are created to explore gender further and the role of sexual orientation is also examined as a factor. Results indicate that regardless of sex, the more strongly individuals self-identify as "cheerful," the more advanced speakers are in this sound change. Results also show that we can look at the intersection of traits in order to predict the leaders of linguistic change. In general, self-ratings on personality traits that have been traditionally valued as ideal qualities for women to possess are the traits that most positively correlate with further advancement in this sound change. The study also indicates that there are differences between men and women in which traits are indexed socially by the sound change, which emphasizes the importance of looking within sex groups for studies that examine gender as a sociolinguistic variable. This study shows how a more subtle use of labels and traits within the framework of social psychology of language can help shed light on the role of sex, sexual orientation, and gender identity in ongoing linguistic change. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]