Humans perform a wide range of skillful and dexterous motion by adjusting the dynamic characteristics of their musculoskeletal system during motion. This capability is based on the non-linear characteristics of the muscles and the motor control architecture that can control motion and exerted force independently. Mechanical impedance (i.e. stiffness, viscosity and inertia) constitutes the most solid characteristic for describing the dynamic behavior of human movements. This paper presents a method for estimating upper limb impedance characteristics in the three-dimensional (3D) space, covering a wide range of the arm workspace. While subjects maintained postures, a seven-degrees-of-freedom (7-DoFs) robot arm was used to produce small displacements of subjects' hands along the three Cartesian axes. The end-point dynamic behavior was modeled using a linear second-order system and the impedance characteristics in the 3D space were identified using the measured forces and motion profiles. Experimental results were confirmed with two subjects.