Statistics, engineering

The science of statistics involves the collection, organization, and interpretation of nnmerical data. Engineers use statistics for many purposes, including  

To facilitate the collection of adequate and reliable data for the planning of 

To better understand and account for uncertainties in the demands placed on engineering structures and products. 

The data that engineers collect may he raw or unorganized however, when dealing with a large set of raw data, it is helpful to group the data into various classes. The data could he grouped into class intervals to form a frequency distribution, which shows the number of observations that occur within a given interval. In fact, it may be possible to classify the data in this way with a tally sheet as they are collected (see Table 7.13). 

TABLE 7.13 Example of a Tally Sheet Vehicle Speeds Counts  

There are a number of important applications of statistical theory in engineering. These include  

In this chapter, these topics will be introduced in order to give a flavor for this activity. Statistics is a broadly ranging, highly mathematical endeavor, and many of the details are beyond the scope of this book. The objective here is merely to introduce the subject and present a few applications that illustrate its importance to engineering. Statistics is a core subject in industrial engineering and this subject is usually associated with such departments. 

Engineering frequently involves experimental observations and the analysis of data collected. When measurements are made in the process of experimentation, two types of errors may be involved  

A systematic error is an error that is consistently present in an instrument while a random error is associated with a system that is out of control or one that is due to human error. An example of a systematic error is one associated with the zero setting of a scale (ohmmeter, postage scale, etc.). An example of random error is one associated with the difficulty of precisely interpolating between markings on a scale or an instrument. In general, some random errors are positive while others are negative. 

In metrology (measurement technology), a measurement is said to be precise when associated with a small random error, but accurate when associated with a small systematic error. 

---

Bowker, A. H. and Lieberman, G. J. 1959 Engineering Statistics. Englewood Cliffs, NJ Prentice-Hall. 

Margetson, J. 1995 Discussion Meeting on Engineering, Statistics and Probability , 2 May, Inst. Mech. Engrs. HQ, London. 

J. Stuart Hunter Princeton University Engineering Statistics... 

In order to compare various reacting-flow models, it is necessary to present them all in the same conceptual framework. In this book, a statistical approach based on the one-point, one-time joint probability density function (PDF) has been chosen as the common theoretical framework. A similar approach can be taken to describe turbulent flows (Pope 2000). This choice was made due to the fact that nearly all CFD models currently in use for turbulent reacting flows can be expressed in terms of quantities derived from a joint PDF (e.g., low-order moments, conditional moments, conditional PDF, etc.). Ample introductory material on PDF methods is provided for readers unfamiliar with the subject area. Additional discussion on the application of PDF methods in turbulence can be found in Pope (2000). Some previous exposure to engineering statistics or elementary probability theory should suffice for understanding most of the material presented in this book. 

For further information, the NIST/SEMATECFI Handbook of Engineering Statistics, which is freely available online [23], and the American Society for Quality (www.ASQ.org), are excellent sources for background information and technical details related to quality management. 

The least squares fitting of approximate functional relationships to data with even multidimensional explanatory variable x typically goes under the (unfortunately obscure) name of multiple regression analysis, and is given an introductory treatment in most engineering statistics textbooks, including, for example, the ones by Devore,4 Vardeman and Jobe,5 and Vardeman6 listed in the references. A lucid and rather complete treatment of the subject can also be found in the book by Neter et al.7... 

O. lordache. Mathematical Methods for Chemical Engineering-Statistics Methods Polytechnic Institute of Bucharest, Bucharest, 1982. 

The National Institute of Standards and Technology (NIST) has a good online resource for Process Behavior Charts called the Engineering Statistics Handbook. The portion on Process Behavior Charts can be found at ... 

Guttman, I., S. S. Wdlkes, and J. S. Hunter. Introductory Engineering Statistics, 3rd edition, VVdley, New York (1982). 

Important information and feedback for risk engineering statistical information aids to determine which type of zirconia gas sensors to install in different applications and why. 

NIST/SEMATECH Engineering Statistics, Internet Handbook,... 

Engineering Statistics Handbook, 5.3.3.5 Plackett-Burman Designs, National Institute of Standards Technology, Dept. Commerce, United States of America, 2010 (available at http //WWW.itl.nist.gov/div898/handbook/pri/ sections/pri335.htm accessed 7/02/10). 

---