As the design-manufacturing interface becomes increasingly complicated with IC technology scaling, the corresponding process variability poses great challenges for nanoscale analog design. In this paper we propose to formulate the analog IC design with variability problem as a specific type of chance-constrained optimization problem, namely chance-constrained posynomial programming, in which statistical variations in both the process parameters and design variables can be explicitly incorporated. Using such constrained optimization approach, automated statistical design can be obtained with very suboptimal design cost, and parametric yield of each specification can be guaranteed. Finally, the method is illustrated by considering the example of a ring oscillator