Chap010st - Chapter 10 - Quality Control CHAPTER 10:...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Chapter 10 - Quality Control CHAPTER 10: QUALITY CONTROL Answers to Discussion and Review Questions 1. The elements in the control process are: a. Define b. Measure c. Compare to standard d. Evaluate e. Take corrective action if needed f. Evaluate corrective action to insure it is working 2. Control charts are based on the premise that a process which is stable will reflect randomness: statistics of samples taken from the process (means, number of defects, etc.) will conform to a sampling distribution with known characteristics, so that statistical significance tests can be performed on sample statistics; and successive samples will not reveal any patterns which will enable prediction of future values other than specification of range of variability. 3. Control charts are used to judge whether the sample data reflects a change in the parameters (e.g., mean) of the process. This involves a yes/no decision and not an estimation of process parameters. 4. Order of observation of process output is necessary if patterns (e.g., trends, cycles) in the output are to be detected. 5. a. x chart—A control chart used to monitor process variables by focusing on the central tendency of a process. b. Range control charts are used to monitor process variables, focusing on the dispersion of a process. c. p-chart—is a control chart for attributes, used to monitor the proportion of defectives in a process. d. c-chart—is a control chart for attributes, used to monitor the number of defects per unit. 6. A run is a sequence of observations with a given characteristic. Run tests are helpful in detecting patterns in time series (e.g., control chart) data. 7. All points can be within control limits but with certain patterns developing in the data which would suggest the output is not random, and hence, not in control for long. 8. It is usually desirable to use both an up/down and a median run test on a given set of data because the tests are sensitive to different things. For example, one test can be more sensitive to trend and the other to bias. 9. No, there is always the possibility of a Beta or Type II error which is the probability of calling something random when in fact it is non-random or concluding that non- randomness is not present, when it actually is. 10-1
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Chapter 10 - Quality Control 10. Specifications are limits on the range of variation of output which are set by design (e.g., engineering, customers). Control limits are statistical bounds on a sampling distribution. They indicate the extent to which summary values such as sample means or sample ranges will tend to vary solely on a chance basis. Process variability refers to the inherent variability of a process the extent to which the output of a process will tend to vary due to chance. Control limits are a function of process variability as well as sample size and confidence level. Both are essentially independent of tolerances. 11.
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/29/2012 for the course BUSINESS 100 taught by Professor Allprofessor during the Spring '12 term at Virginia College.

Page1 / 17

Chap010st - Chapter 10 - Quality Control CHAPTER 10:...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online