# Question

The viscosity of a chemical product is read every two minutes. Some data from this process are shown in Table 10E.11 (read down, the across from left to right).

(a) Is there a serious problem with autocorrelation in these data?

(b) Set up a control chart for individuals with a moving range used to estimate process variability. What conclusion can you draw from this chart?

(c) Design a CUSUM control scheme for this process, assuming that the observations are uncorrelated. How does the CUSUM perform?

(d) Set up an EWMA control chart with = 0.15 for the process. How does this chart perform?

(e) Set up a moving center line EWMA scheme for these data.

(f) Suppose that a reasonable model for the viscosity data is an AR(2) model. How could this model be used to assist in the development of a statistical process-control procedure for viscosity? Set up an appropriate control chart, and use it to assess the current state of statistical control.

(a) Is there a serious problem with autocorrelation in these data?

(b) Set up a control chart for individuals with a moving range used to estimate process variability. What conclusion can you draw from this chart?

(c) Design a CUSUM control scheme for this process, assuming that the observations are uncorrelated. How does the CUSUM perform?

(d) Set up an EWMA control chart with = 0.15 for the process. How does this chart perform?

(e) Set up a moving center line EWMA scheme for these data.

(f) Suppose that a reasonable model for the viscosity data is an AR(2) model. How could this model be used to assist in the development of a statistical process-control procedure for viscosity? Set up an appropriate control chart, and use it to assess the current state of statistical control.

## Answer to relevant Questions

Discuss how you would use a CUSM in the short production-run situation. What advantages would it have relative to a Shewhart chart, such as a DNOM version of the x chart? A sample of five units of product is taken from a production process every hour. The results in Table 10E.12 are obtained. Assume that the specifications on this quality characteristic are at 1.0015 and 1.0035. Set up the R ...The data shown in Table 11.E1 come from a production process with two observable quality characteristics: x1 and x2. The data are sample means of each quality characteristic, based on samples of size n -= 25. Assume that ...Suppose that there are p = 2 quality characteristics, and in correlation form both variables have variance unity and the correlation coefficient is 0.8. The in-control value of the process mean vector is μ′ = [0, 0], and ...Consider a T2 control chart for monitoring p = 6 quality characteristics. Suppose that the subgroup size is n= 3 and there are 30 preliminary samples available to estimate the sample covariance matrix. m = 30 preliminary ...Post your question

0