Engineering statistics

Source: Wikipedia, the free encyclopedia.

Engineering statistics combines

histograms to give a visual of the data as opposed to being just numerical. Examples of methods are:[1][2][3][4][5][6]

  1. optimal (or near optimal) designs reduces the cost of experimentation.[2][7]
  2. process control use statistics as a tool to manage conformance to specifications of manufacturing processes and their products.[1][2][3]
  3. Time and methods engineering
    use statistics to study repetitive operations in manufacturing in order to set standards and find optimum (in some sense) manufacturing procedures.
  4. Reliability engineering which measures the ability of a system to perform for its intended function (and time) and has tools for improving performance.[2][8][9][10]
  5. Probabilistic design involving the use of probability in product and system design
  6. optimal design of experiments for efficiently generating informative data for fitting such models.[11][12]

History

Engineering statistics dates back to 1000 B.C. when the

Slide Rule technique was developed by Robert Bissaker for advanced data calculations. In 1833, a British mathematician named Charles Babbage designed the idea of an automatic computer which inspired developers at Harvard University and IBM to design the first mechanical automatic-sequence-controlled calculator called MARK I. The integration of computers and calculators into the industry brought about a more efficient means of analyzing data and the beginning of engineering statistics.[13][6][14]

Examples

Factorial Experimental Design

Main article: Factorial experiment

A factorial experiment is one where, contrary to the standard experimental philosophy of changing only one independent variable and holding everything else constant, multiple independent variables are tested at the same time. With this design, statistical engineers can see both the direct effects of one independent variable (main effect), as well as potential interaction effects that arise when multiple independent variables provide a different result when together than either would on its own.

Six Sigma

Main article: Six Sigma

Six Sigma is a set of techniques to improve the reliability of a manufacturing process. Ideally, all products will have the exact same specifications equivalent to what was desired, but countless imperfections of real-world manufacturing makes this impossible. The as-built specifications of a product are assumed to be centered around a mean, with each individual product deviating some amount away from that mean in a normal distribution. The goal of Six Sigma is to ensure that the acceptable specification limits are six standard deviations away from the mean of the distribution; in other words, that each step of the manufacturing process has at most a 0.00034% chance of producing a defect.

Notes

  1. ^
    ISBN 0-471-71813-0
  2. ^
    ISBN 0-471-25511-4
    .
  3. ^
    ISBN 0-19-851993-1
    .
  4. ^ Hogg, Robert V. and Ledolter, J. (1992). Applied Statistics for Engineers and Physical Scientists. Macmillan, New York.
  5. ^ Walpole, Ronald; Myers, Raymond; Ye, Keying. Probability and Statistics for Engineers and Scientists. Pearson Education, 2002, 7th edition, pg. 237
  6. ^
    ISBN 013089480X
    .
  7. ISBN 978-0-19-929660-6
    .
  8. MR 1621421
    .
  9. ISBN 0-471-69736-2
  10. ^ LogoWynn
  11. ISBN 0-12-289750-1
    .
  12. ^ Walter, Éric; Pronzato, Luc (1997). Identification of Parametric Models from Experimental Data. Springer.
  13. ^ The Editors of Encyclopaedia Britannica. "Slide Rule". Encyclopaedia Britannica. Encyclopaedia Britannica Inc. Retrieved 17 April 2018. {{cite web}}: |last1= has generic name (help)
  14. ISBN 978-0470631478
    .

References

External links
Retrieved from "https://en.wikipedia.org/w/index.php?title=Engineering_statistics&oldid=1216180110"