We present a stochastic programming model for investments in thermal generation capacity to study the impact of demand response (DR) at high wind penetration levels. The investment model combines continuous operational constraints and wind scenarios to represent the implications of wind variability and uncertainty at the operational level. DR is represented in terms of linear price-responsive demand functions. A numerical case study based on load and wind profiles of Illinois is constructed with 20 candidate generating units of various types. Numerical results show the impact of DR on both investment and operational decisions. We also propose a model in which DR provides operating reserves and discuss its impact on lowering the total capacity needed in the system. We observe that a relatively small amount of DR capacity is sufficient to enhance the system reliability. When compared to the case with no DR, a modest level of DR results in less wind curtailment and better satisfaction of reserve requirements, as well as improvements in both the social surplus and generator utilization, as measured by capacity factors. The authors acknowledge the U.S. Department of Energy's Wind Power Program, for funding the research presented in this paper. The submitted manuscript has been created by UChicago Argonne, LLC, Operator of Argonne National Laboratory (''Argonne''). Argonne, a U.S. Department of Energy Office of Science laboratory, is operated under Contract No. DE-AC02-06CH11357. The U.S. Government retains for itself, and others acting on its behalf, a paid-up non-exclusive, irrevocable worldwide license in said article to reproduce, prepare derivative works, distribute copies to the public, and perform publicly and display publicly, by or on behalf of the Government.Shan