Process capability analysis is extremely important for optimization and quality improvement. It verifies whether the process under analysis is capable of producing items within engineering and customers' specifications. The use of capability indices when assumptions are not satisfied leads to erroneous conclusions, compromising the study and analysis of the process, jeopardizing the fulfillment of requirements from management or external customers. Aiming at filling a gap identified in the literature, the main contributions of this work are: (i) proposition of capability indices for processes monitored through control charts based on regression models, for symmetric and asymmetric specifications; and (ii) comparison of the proposed indices with traditional capability indices through a simulated process.
Palavras-chave: Process control. Regression models. Capability indices.Abstract would have to be settled for each new setting, in addition to the difficulty of calculating control limits due to the low number of samples of each batch manufactured in each setting. In these cases, the response variable (dependent variable) of a product or process is best represented by a mathematical equation that models its relationship with the control variables of the process (JACOBI et al., 2002;SHU et al., 2004). Mandel (1969) proposed the regression control chart, a combination of control chart techniques and simple linear regression models. This chart is used in processes in which the effect of a response variable is a function of a control variable. Initially a regression model is generated, which represents the relationship between the response variable and the control variable, and subsequently the residual is monitored through the model. Traditional control charts are not able to perform analyses when the response variable is dependent on the control variable, as a constant average over time is presumed.Mandel's original proposal (1969) can only be applied in processes involving a control variable. Haworth (1996) extended Mandel's proposal (1969) by suggesting the multiple regression chart, consisting in the estimation of a multiple linear regression model and monitoring of standardized residuals. However, Haworth's work (1996)