During formulation design of a once-daily controlled release matrix system of divalproex sodium, the in vitro dissolution test (USP II, 100 rpm, pH 6.8 buffer) was found to result in release rates that were slower than in vivo absorption. The test method also did not sufficiently discriminate formulations with different in vivo absorption rates. To develop an in vitro method that is directly correlated with in vivo absorption, statistically designed studies were carried out to investigate the effects of various in vitro testing variables on drug release using USP dissolution apparatuses. The variables studied included agitation intensity, apparatus, pH, surfactant and ionic strength of the dissolution medium. Experimental data were analyzed using ANOVA. In vitro/in vivo correlation was tested based on the hypothesis that the same linear regression equation holds for three formulations with different release rates. A mixed effects model was used in which the dependence among observations from the same subject was taken into account. Factorial studies indicated that higher pH, addition of sodium lauryl sulphate (SLS) to the dissolution medium, and higher agitation intensity increased the release rate from the matrix tablet. Use of SLS not only lead to increased release rates that are more comparable to in vivo absorption rates, but also improved differentiation among formulations with varying release rates. Furthermore, drug release was also affected by interactions among the variables studied. Statistical analysis indicated that a combination of higher SLS concentration and lower pH provided enhanced differentiation between release profiles of the fast and slow releasing formulations. Based on the above findings, a new set of testing conditions was identified and demonstrated to be predictive of in vivo drug absorption for various controlled release formulations of divalproex sodium. The new method uses USP Apparatus II operating at 100 rpm in 500 mL of 0.1 N HCl for 45 min followed by 900 mL of 0.05 M phosphate buffer containing 75 mM SLS, pH 5.5, 37 +/- 0.5 degrees C. In conclusion, adjusting dissolution testing conditions to match the behavior of the formulations in vitro with that in vivo is a useful approach in identifying a predictive method in development of in vitro-in vivo correlation.