Transcript Ch. 20

Lecture Slides
Chapter 20
Statistical Considerations
The McGraw-Hill Companies © 2012
Chapter Outline
Shigley’s Mechanical Engineering Design
Random Variables
A random experiment is an experiment in which a number of
specimens are selected at random from a larger batch.
 A random variable is a variable quantity whose value depends on
the outcome of a random experiment.
 A random variable is also called a stochastic variable.
 A sample space contains all the possible outcomes.
 An example sample space for a pair of dice,

Fig. 20–1
Shigley’s Mechanical Engineering Design
Probability Distribution
The probability of a random variable x taking on a specific value is
called p = f (x).
 p is the number of times a specific x occurs divided by the total
number of possible outcomes.
 A list of all possible values along with the corresponding
probabilities is called a probability distribution.
 Define a random variable x as the sum of numbers obtained from
tossing a pair of dice. The probability distribution for x,

Table 20–1
Shigley’s Mechanical Engineering Design
Frequency Distribution
Plotting the probability distribution makes it clear that the
probability is a function of x.
 The probability function p = f (x) is often called the frequency
function, or the probability density function (PDF).

Fig. 20–2
Shigley’s Mechanical Engineering Design
Cumulative Probability Distribution
The probability that x is less than or equal to a certain value of xi is
found by summing the probability of all x’s up to and including xi.
 This results in a cumulative probability distribution.

Table 20–2

The function F(x) is a cumulative density function (CDF) of x.
Shigley’s Mechanical Engineering Design
Cumulative Frequency Distribution

A plot of the cumulative density function is called a cumulative
frequency distribution.
Fig. 20–3
Shigley’s Mechanical Engineering Design
Continuous Random Variables

A discrete random variable x can only have discrete values.
A continuous random variable x can have any value in a specified
interval.
For continuous random variables, the distribution plots are
continuous curves.
For a continuous probability density function F(x),

When x goes to ∞,

Differentiation of Eq. (20-2) gives



Shigley’s Mechanical Engineering Design
Arithmetic Mean, Variance, and Standard Deviation

Sample mean of N elements

Sample variance

Sample standard deviation

Alternate form
Shigley’s Mechanical Engineering Design
Population Mean and Standard Deviation
If the entire population is considered,x and sx are replaced with mx
and ˆ x respectively.
 The N – 1 in the denominator is replaced by N.

Shigley’s Mechanical Engineering Design
Discrete Frequency Histogram

A discrete frequency histogram gives the number of occurrences,
or class frequency fi, within a given range.
Fig. 20–4
Shigley’s Mechanical Engineering Design
Mean and Standard Deviation with Class Frequency

When the data are grouped by class frequency fi, the mean and
standard deviation can be expressed as

The cumulative density function that gives the probability of an
occurrence at class mark xi or less is
Where wi is the class width at xi.
Shigley’s Mechanical Engineering Design
Notation
Boldface characters indicate random variables that can be
characterized by a mean and a standard deviation.
 The terms stochastic variable or variate are used to mean a
random variable.
 A deterministic quantity is something that has a single specified
value.
 A coefficient of variation is defined by


A variate x can be expressed in the following two ways:
where X represents a variate probability distribution function.
Shigley’s Mechanical Engineering Design
Example 20–1
Table 20–3
Shigley’s Mechanical Engineering Design
Example 20–1
Shigley’s Mechanical Engineering Design
Example 20–2
Table 20–4
Shigley’s Mechanical Engineering Design
Example 20–2
Shigley’s Mechanical Engineering Design
Probability Distributions

Some standard discrete and continuous probability distributions
◦ Gaussian, or normal
◦ Lognormal
◦ Uniform
◦ Weibull
Shigley’s Mechanical Engineering Design
Gaussian (Normal) Distribution

The Gaussian, or normal, distribution is defined as

It can be expressed as

Typical plots of the Gaussian distribution, with small or large
standard deviation, look like the following
Fig. 20–5
Shigley’s Mechanical Engineering Design
Transformation Variate z

The deviation from the mean is expressed in units of standard
deviation by the transform

The transformation variate z is normally distributed, with a mean
of zero and a standard deviation and variance of unity.
That is, z = N (0, 1)

Shigley’s Mechanical Engineering Design
Cumulative Distribution Function for Gaussian Distribution
Integration of the Gaussian distribution to find the cumulative
density function F(x) is accomplished numerically.
 To avoid the need for many tables for different values of mean and
standard deviation, the z transform is used.
 The integral of the transform is tabulated in Table A–10.
 A sketch of the standard normal distribution, showing the z
transform is given below.
 The normal cumulative density function is labeled F(z)

Fig. 20–6
Shigley’s Mechanical Engineering Design
Example 20–3
Shigley’s Mechanical Engineering Design
Example 20–3
Fig. 20–7
Shigley’s Mechanical Engineering Design
Example 20–3
Shigley’s Mechanical Engineering Design
Lognormal Distribution
In the lognormal distribution the logarithms of the variate have a
normal distribution.
 Thus the variate is said to by lognormally distributed.
 The parent, or principal, distribution is expressed as


The companion, or subsidiary, distribution is express through a
transformation,
Shigley’s Mechanical Engineering Design
Lognormal Distribution
The probability density function (PDF) for x is derived from that
for y.
 The PDF for the companion distribution is

Shigley’s Mechanical Engineering Design
Example 20–4
Shigley’s Mechanical Engineering Design
Example 20–4
Table 20–5
Shigley’s Mechanical Engineering Design
Example 20–5
Shigley’s Mechanical Engineering Design
Example 20–5
Fig. 20–8
Shigley’s Mechanical Engineering Design
Uniform Distribution

The uniform distribution is a closed-interval distribution that arises
when the chance of an observation is the same as the chance for
any other observation.
The probability density function (PDF) is

The cumulative density function, the integral of f(x), is

Shigley’s Mechanical Engineering Design
Uniform Distribution

The mean for the uniform distribution,

The standard deviation,
Shigley’s Mechanical Engineering Design
Weibull Distribution
The Weibull distribution is a flexible, asymmetrical distribution
with different values for mean and median.
 It contains within it a good approximation of the normal
distribution and an exact representation of the exponential
distribution.
 It is widely used to represent laboratory and field service data.

Shigley’s Mechanical Engineering Design
Weibull Distribution

The reliability given by a three-parameter Weibull distribution is

For the special case when x0 = 0, the two-parameter Weibull is

If a specific reliability is given, solving Eq. (20–24) for x,
Shigley’s Mechanical Engineering Design
Weibull Distribution
The characteristic variate q represents a value of x below which
lie 63.2% of the observations.
 The shape parameter b controls the skewness of the distribution.
 A good approximation to the normal distribution is obtained when
3.3 < b < 3.5
 The distribution is exponential when b = 1

Fig. 20–9
Shigley’s Mechanical Engineering Design
Weibull Distribution

To find the probability function, note that
Shigley’s Mechanical Engineering Design
Weibull Distribution

The mean and standard deviation are given by
G is the gamma function, tabulated in Table A–34.
 The notation for a Weibull distribution is

Shigley’s Mechanical Engineering Design
Example 20–6
Shigley’s Mechanical Engineering Design
Example 20–6
Shigley’s Mechanical Engineering Design
Propagation of Error

In the equation for axial stress

If F and A are random variables, then the stress is also a random
variable,

Errors inherent in F and A are said to be propagated to the stress
variate .
Shigley’s Mechanical Engineering Design
Propagation of Error

If two variates are added,

Similar relations for other arithmetic functions are given in Table
20–6.
Shigley’s Mechanical Engineering Design
Means and Standard Deviations for Algebraic Operations
Table 20–6
Shigley’s Mechanical Engineering Design
Example 20-7
Shigley’s Mechanical Engineering Design
Example 20-7
Shigley’s Mechanical Engineering Design
Linear Regression
A process called regression is used to obtain a curve that best fits a
set of data points.
 The process is called linear regression when the best-fitting
straight line is found.

Fig. 20–10
Shigley’s Mechanical Engineering Design
Linear Regression
Shigley’s Mechanical Engineering Design
Linear Regression

The correlation coefficient r indicates the degree to which a set of
data points correlates with a regression line.

The standard deviations for the slope and intercept are given by
Shigley’s Mechanical Engineering Design
Example 20–8
Shigley’s Mechanical Engineering Design
Example 20–8
Table 20–7
Shigley’s Mechanical Engineering Design
Example 20–8
Shigley’s Mechanical Engineering Design
Example 20–8
Fig. 20–11
Shigley’s Mechanical Engineering Design