The effect of measurement error on estimates of the Q and cash flow model of investment is investigated. Two sources of error are considered: expensing of research and development expenditures and the failure to separate out that component of cash flow which relaxes financing constraints. We apply random-effects and instrumental variables estimators to remedy these sources of error. When the model is properly identified, Q makes a significant contribution. However, the contribution of unexpected cash flow is not as meaningful as theory would predict, which might be explained by the relatively large size of the firms in the sample.