In order to evaluate the impact of Asian dust to the air quality of North America, a relatively new type of factor analysis, positive matrix factorization (PMF), was applied to the PM2.5 particle composition data obtained at two high elevated sampling sites in the western United States from Interagency Monitoring of Protected Visual Environments (IMPROVE) program. These two sites are Crater Lake National Park (1981m) and Lassen Volcanic National Park (1798m). PMF can provide optimal point-by-point weighting by using the estimates uncertainty in the data and can permit efficient treatment of missing and below detection limit values. It also imposes the nonnegativity constraint on the factors. Seven and six sources were resolved from the Crater Lake National Park and Lassen Volcanic National Park data, respectively. The factors were normalized by using aerosol fine mass concentration data through multiple linear regression so that the quantitative source contributions for each resolved factor were obtained. Among the sources resolved at the two sites, six are common. These six sources exhibit not only similar chemical compositions but also similar seasonal variations at both sites. The Asian dust was represented by Al, Ca, Fe, NO3, S, K, and Ti with strong seasonal variation. Secondary sulfate with a high concentration of S and strong seasonal variation correlated with the Asian dust. Wood smoke was represented by organic carbon (OC), elemental carbon (EC), and K; sea salt with the high concentrations of Na, S and NO3. Nitrate was dominated by NO3 and motor vehicle with high concentrations of OC, EC, and dust elements. A incinerator source with the presence of Cu and Zn also was resolved from the Crater Lake site. Generally, most of the sources at these two sites showed similar chemical composition profiles and seasonal variation patterns. The source profile of Asian dust resolved from this study agreed reasonably well with the source characteristics found in other Asian dust studies. This study indicated that PMF was a powerful factor analysis method to extract sources from the ambient aerosol concentration data.