• Journal of Korean Society for Quality Management
• /
• v.39 no.3
• /
• pp.400-411
• /
• 2011

Process variables are factors in an experiment that are not mixture components but could affect the blending properties of the mixture ingredients. For example, the effectiveness of an etching solution which is measured as an etch rate is not only a function of the proportions of the three acids that are combined to form the mixture, but also depends on the temperature of the solution and the agitation rate. Efficient designs for the mixture components-process variables experiments depend on the mixture components-process variables model which is called a combined model. We often use the product model between the canonical polynomial model for the mixture and process variables model as a combined model. In this paper we propose three starting models for the mixture components-process variables experiments. One of the starting model we are considering is the model which includes product terms up to cubic order interactions between mixture effects and the linear & pure quadratic effect of the process variables from the product model. In this paper, we propose a method for finding robust designs and practical designs with respect to D-, G-, and I-optimality for the various starting combined models and then, we find practically efficient and robust designs for estimating the regression coefficients for those models. We find the prediction capability of those recommended designs in the case of three components and three process variables to be good by checking FDS(Fraction of Design Space) plots.

• Journal of the Korean Statistical Society
• /
• v.9 no.2
• /
• pp.145-172
• /
• 1980

Draper and Lawrence (1965a) have given mixture designs for three factors when all the mixture components can vary on the entire factor space so that the region of interest is an equilateral triangle in two dimensions. In this paper their work is extended to the cases when the region of interest is an echelon, parallelogram, pentagon or hexagon, because of the restirctions imposed on some or all of the mixture components. The principles used in the choice of appropriate designs are those originally introduced by Box and Draper(1959). It is assumed that a response surface equation of first order is fitted, but there is a possibility of bias error due to presence of second order terms in the true model. Minimum bias designs for several cases of restricted regions of interest are illustrated.

• Journal of Korean Society for Quality Management
• /
• v.23 no.2
• /
• pp.68-79
• /
• 1995

Good estimation of the slopes of the mixture response function may be important as well as estimation of mean mixture response. It is possible to evaluate and compare several mixture designs with respect to the slope. A graphical method is proposed that allows us to evaluate a given design's support for the fitted model in terms of slope variance. We can plot variances of slopes along Cox direction according to existence of restriction of simplex region when comparing several different mixture designs.

• Journal of Korean Society for Quality Management
• /
• v.48 no.2
• /
• pp.269-282
• /
• 2020

Purpose: The practical design for experiments with mixtures of q components is consisted in the four types of design points, vertex, center of edge, axial, and center points in a (q-1)-dimensional simplex space. We propose a sequential method for the successful construction of the design space in Quality by Design (QbD) by allowing the different number of replicates at the four types of design points in the practical design when the quadratic canonical polynomial model is assumed. Methods: To compare the mixture designs efficiency, fraction of design space (FDS) plot is used. We search for the practical mixture designs whose the minimal half-width of the tolerance interval per a standard deviation, which is denoted as d₂, is less than 4.5 at 0.8 fraction of the design space. They are found by adding the different number of replicates at the four types of the design points in the practical design. Results: The practical efficient mixture designs for the number of components between three and five are listed. The sequential method to establish a design space is illustrated with the two examples based on the simulated data. Conclusion: The designs with the center of edge points replications are more efficient than those with the vertex points replication. We propose the sample size of at least 23 for three components, 28 for four components, and 33 for the five components based on the list of efficient mixture designs.

• Journal of the Korean Statistical Society
• /
• v.17 no.2
• /
• pp.121-133
• /
• 1988

In this paper a class of mixture designs for estimating the slope of second order Scheffe polynomial response surfaces for mixture experiments with q components is presented. The variance of the estimated directional slope at a point is a function of the direction of the slope and the design. If the variance is averaged over all possible directions in the (q-1)-dimensional simplex, the averaged variance is only a function of the point and the design. By choice of design, it is possible to make this variance constant for all points equidistant from the centroid point. This property is called "slope-rotatability over al directions in the simplex", and the necessary and sufficient conditions for mixture design to have this property are given and proved. The class of designs with this property is compared with other mixture designs and discussed.discussed.

• IE interfaces
• /
• v.19 no.2
• /
• pp.117-123
• /
• 2006

Many products, such as gasoline, polymer plastics, alloys, and ceramics are manufactured by mixing two or more ingredients or components. When we are to develop new mixture products, we must deal with a long list of potentially important component variables. This paper introduces some mixture screening designs, analysis tools for screening important variables, and a guideline for applying these analysis tools. The results of this paper will be helpful to engineers who work in the research and development sector of mixture product industries.

• Journal of the Korean Statistical Society
• /
• v.11 no.1
• /
• pp.36-44
• /
• 1982

A new design concept, called axis-slope-rotatability, is presented for the design of experiments with mixtures. This is an analogue of the Box-Hunter (1957) rotatability for second order response surface designs. By choice of design, it is possible to make the variance of the estimated slopes along the component axes constant for all axial points equidistant from the center point of the factor space. This property is called axis-slope-rotatability for mixture experiments. When the Scheffe's second degree polynomial is used, it is shown that some symmetry conditions are sufficient for axis-slope-rotatability. Several designs having this property are illustrated.

• The Korean Journal of Applied Statistics
• /
• v.20 no.2
• /
• pp.267-280
• /
• 2007

Various single-valued design optimality criteria such as D-, G-, and V-optimality are used often in constructing optimal experimental designs for mixture experiments in a constrained region R where lower and upper bound constraints are imposed on the ingredients proportions. Even though they are optimal in the strict sense of particular optimality criterion used, it is known that their performance is unsatisfactory with respect to the prediction capability over a constrained region. (Vining et at., 1993; Khuri et at., 1999) We assume the quadratic polynomial model as the mixture response surface model and are interested in finding efficient designs in the constrained design space for a mixture. In this paper, we make an expanded list of candidate design points by adding interior points to the extreme vertices, edge midpoints, constrained face centroids and the overall centroid. Then, we want to propose a robust design with respect to D-optimality, G-optimality, V-optimality and distance-based U-optimality. Comparing scaled prediction variance quantile plots (SPVQP) of robust designs with that of recommended designs in Khuri et al. (1999) and Vining et al. (1993) in the well-known examples of a four-component fertilizer experiment as well as McLean and Anderson's Railroad Flare Experiment, robust designs turned out to be superior to those recommended designs.

• Journal of Korean Society for Quality Management
• /
• v.24 no.4
• /
• pp.156-167
• /
• 1996

D-optimality is used often in design augmentation of mixture experiments. Although such alphabetic criteria provide a valuable foundation for generating designs, they often fail to convey the true nature of the design's support of the fitted model in terms of prediction variance over a region of interest. Thus, a graphical method is proposed to evaluate augmented designs in mixture experiments. This method can be used to evaluate the effect of missing observation and outlier in mixture experiments.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.3
• /
• pp.745-755
• /
• 2007

The concept of slope rotatability introduced by Hader and Park(1978) is available when we are interested in the difference of the responses. Since there can be constraints on the factor levels in mixture experiments, there arises a need for adaptation of the concept of slope rotatability and the measure to assess it. In this article, measures of slope rotatability in mixture experiments are proposed to quantify the amount of slope rotatability for a given design. Measures for a restricted region design as well as for an unrestricted region design are presented. Then, the designs having different optimalities are compared with respect to these measures by some examples.