To achieve emission reduction targets in China, it is necessary to analyze the factors driving energyrelated carbon emissions from a regional perspective. We used extended STIRPAT model (stochastic impacts by regression on population, affluence, and technology) based on the classical IPAT identity (where I = impact representing carbon emissions, P = population, A = affluence, and T = emission intensity) to determine the main factors driving energy-related carbon emissions in Xinjiang from 1952 to 2014, an important Chinese energy base in northwestern China. Total carbon emissions in Xinjiang were found to increase from 28.51 × 104 t in 1952 to 9,446.61 × 104 t in 2014, representing a 331.34-fold increase over a period of 63 years. Results show that the impacts and influences of various factors on carbon emissions varied among three stages of development: “Before Reform and Opening up” (1952-1977), “After Reform and Opening up” (1978-2000), and “Western Development” (2001-2014). In the first stage, emission intensity and population size were the dominant contributors to increments in carbon emissions, while the energy consumption structure played an important role in curbing carbon emissions. In the second stage, economic growth and population size were the dominant contributors to increments in carbon emissions, while emission intensity had a significant negative effect on carbon emissions. In the third stage, fixed asset investment and economic growth were the dominant contributors to increments in carbon emissions, while emission intensity had a significant negative effect on carbon emissions.