This paper is concerned with control of processes with uncertain delays for disturbance rejection. The effect of the uncertain delays on the stability is studied. First, the method to compute the maximum uncertain delay that a given controller can tolerate is described. Second, in the case of PI/PID controller, all of the admissible controller parameters stabilizing a system with uncertain but bounded delays are determined. Meanwhile, we propose a simple method to construct the parameter space satisfying a given robustness index for the nominal model. In the admissible regions satisfying various objectives, the global optimum controller is achieved for disturbance rejection in the presence of uncertain delay. As a result, the MIGO ( -constrained Integral Gain Optimization) method is revisited in the case of uncertain delay, and the rule of selecting the value of maximum sensitivity function is proposed in terms of the bound on the uncertain delay. Two simulation examples and an experiment are given to demonstrate the effectiveness and advantage of the proposed method.Note to Practitioners-The practitioners can use the methods presented in this paper to solve the following two problems: 1) to estimate the allowable delay that a control system can tolerate and 2) to design the globally optimal PID controller in terms of the delay range. This paper was motivated by how to find the globally optimal PID parameters in the presence of uncertain delays. Conventionally, the uncertain delay is dealt with linear matrix inequalities (LMIs). However, the results based on solving LMIs are not globally optimal. Here, we dealt with the uncertain delay in the frequency domain. We not only proposed a method to compute the maximum delay that the classical PID controller can tolerate but also find all the admissible PID controllers stabilizing a processes in the presence of uncertain delay. To obtain the globally optimal controller for a given process, the boundaries for the norm-based indices were constructed. Then, the globally optimal PID controller satisfying multiple objectives can be easily found in the admissible region. The examples clearly showed that the method based on LMI only provided one local optimal solution. However, the proposed method can find all of the admissible solutions and select the optimal one. We also discussed the application of the well-known MIGO method in the case of uncertain delays. Also, the rules of selecting the robustness index in terms of uncertain delay were proposed. The above methods were proposed based on first-order plus time delay models since Manuscript most chemical processes can be modeled by this type of model. Certainly the methods can be extended to high order processes with uncertain delays. But the methods may not easily be used for multiple-input-multiple-output processes since it is difficult to construct the stability regions of the parameters for such processes. Also, the method cannot be used to deal with the random delays.Index Terms-Parameter space, PID controller, sensitiv...