Particulate matter (PM) has been associated with mortality in several epidemiological studies. The US EPA currently regulates PM(10) and PM(2.5) (mass concentration of particles with diameter less than 10 microm and 2.5 microm, respectively), but it is not clear which size of particles are most responsible for adverse heath outcomes. A current hypothesis is that ultra-fine particles with diameter less than 0.1microm are particularly harmful because their small size allows them to deeply penetrate the lungs. This paper investigates the association between exposure to particles of varying diameter and daily mortality. We propose a new dynamic factor analysis model to relate the ambient concentrations of several sizes of particles with diameters ranging from 0.01 to 0.40 microm with mortality. We introduce a Bayesian model that converts ambient concentrations into simulated personal exposure using the EPA's Stochastic Human Exposure and Dose Simulator, and relates simulated exposure with mortality. Using new data from Fresno, CA, we find that the four-day lag of particles with diameter between 0.02microm and 0.08microm is associated with mortality. This is consistent with the small particles hypothesis.