Location and Scale Parameters

Location and Scale Parameters
Normal PDF A probability distribution is characterized by location and scale parameters.

Location and scale parameters are typically used in modeling applications.
For example, the following graph is the probability density function for the
standard normal distribution, which has the location parameter equal to zero
and scale parameter equal to one.
Location The next plot shows the probability density function for a normal distribution
Parameter with a location parameter of 10 and a scale parameter of 1.
The effect of the location parameter is to translate the graph, relative to the
standard normal distribution, 10 units to the right on the horizontal axis. A
location parameter of -10 would have shifted the graph 10 units to the left on
the horizontal axis.
That is, a location parameter simply shifts the graph left or right on the
horizontal axis.
Scale Parameter The next plot has a scale parameter of 3 (and a location parameter of zero).
The effect of the scale parameter is to stretch out the graph. The maximum y
value is approximately 0.13 as opposed 0.4 in the previous graphs. The y
value, i.e., the vertical axis value, approaches zero at about (+/-) 9 as opposed
to (+/-) 3 with the first graph.
In contrast, the next graph has a scale parameter of 1/3 (=0.333). The effect
of this scale parameter is to squeeze the pdf. That is, the maximum y value is
approximately 1.2 as opposed to 0.4 and the y value is near zero at (+/-) 1 as
opposed to (+/-) 3.
The effect of a scale parameter greater than one is to stretch the pdf. The
greater the magnitude, the greater the stretching. The effect of a scale
parameter less than one is to compress the pdf. The compressing approaches
a spike as the scale parameter goes to zero. A scale parameter of 1 leaves the
pdf unchanged (if the scale parameter is 1 to begin with) and non-positive
scale parameters are not allowed.
Location andThe following graph shows the effect of both a location and a scale
Scale Together parameter. The plot has been shifted right 10 units and stretched by a factor
of 3.
Standard Form The standard form of any distribution is the form that has location parameter
zero and scale parameter one.
It is common in statistical software packages to only compute the standard
form of the distribution. There are formulas for converting from the standard
form to the form with other location and scale parameters. These formulas
are independent of the particular probability distribution.
Formulas forThe following are the formulas for computing various probability functions
Location andbased on the standard form of the distribution. The parameter a refers to the
Scale Based onlocation parameter and the parameter b refers to the scale parameter. Shape
the Standardparameters are not included.
Form Cumulative Distribution Function F(x;a,b) = F((x-a)/b;0,1)
Probability Density Function f(x;a,b) = (1/b)f((x-a)/b;0,1)
Percent Point Function G(α;a,b) = a + bG(α;0,1)
Hazard Function h(x;a,b) = (1/b)h((x-a)/b;0,1)
Cumulative Hazard Function H(x;a,b) = H((x-a)/b;0,1)
Survival Function S(x;a,b) = S((x-a)/b;0,1)
Inverse Survival Function Z(α;a,b) = a + bZ(α;0,1)
Random Numbers Y(a,b) = a + bY(0,1)

Relationship toFor the normal distribution, the location and scale parameters correspond to
Mean andthe mean and standard deviation, respectively. However, this is not
Standard necessarily true for other distributions. In fact, it is not true for most
Deviation distributions.
What is a Shape Parameter?
A shape parameter, as the name suggests, affects the general shape of a distribution;
they are a family of distributions with different shapes. The parameters are usually known from
prior statistical data or they are sometimes estimated from current data. For example, the Beta
distribution has a shape parameter. Changing this parameter changes the overall shape of the
graph. The exponential distribution does not have a shape parameter, so the general shape
remains the same. Image credit: Skbkekas|Wikimedia Commons. In contrast, several other
distributions do not have these parameters. They include the exponential distribution. Even
though the exponential distribution can be squeezed, stretched, or shifted, the overall shape
remains the same.
The most important thing to grasp about the shape parameter is that it doesn’t
change where the graph lies on the horizontal axis of a Cartesian plane (that’s the job of
the location parameter). Nor does it shrink or squeeze the graph (the job of the scale
parameter). It just defines the general shape of the graph for certain distributions.
In some distributions (like the Weibull distribution), the parameter can help define skewness.
For example:
 Larger parameters tend to result in a left-skewed distribution.
 Smaller parameters tend to result in a right-skewed distribution.
 This is not a universal rule though, just a general guideline.
 Other Parameters that Affect Shapes of Distributions
Some of the other parameters used to define distributions:

 The Location parameter tells you where the distribution is centered on the horizontal
axis.
 The Scale parameter gives you an idea of the scale on the horizontal axis. For example,
the scale parameter on a standard normal distribution is equal to one standard deviation
(σ). It usually stretches or squeezes a graph.
Sampling Unit and Sampling Frame

Sampling unit: The population divided into a finite number of distinct and identifiable units is
called sampling units. OR The individuals whose characteristics are to be measured in the
analysis are called elementary or sampling units. OR Before selecting the sample, the
population must be divided into parts called sampling units or simply sample units.
Sampling Frame: The list of all the sampling units with a proper identification (which represents
the population to be covered is called sampling frame). The frame may consist of either a list of
units or a map of area (in case sample of area is being taken), such that every element in the
population belongs to one and only one unit. The frame should be accurate, free from omission
and duplication (overlapping), adequate, up to data and the units must cover the whole of the
population and should be well identified.
In improving the sampling design, supplementary information for the field covered by the
sampling frame may also be valuable.
Examples: Sampling Frame and Sampling Unit
List of household (and persons) enumerated in population census.
 A map of areas of a country showing the boundaries of area units.
 In sampling an agricultural crop, the unit might be a field, a farm or an area of land
whose shape and dimensions are at out disposal.
 An ideal sampling frame will have the following qualities/characteristics:
 all sampling units have a logical and have numerical identifier
 all sampling units can be found i.e. contact information, map location or other relevant
information about sampling units is present
 the frame is organized in a logical and systematic manner
 the sampling frame has some additional information about the units that allow the use
of more advanced sampling frames
 every element of the population of interest is present in the frame
 every element of the population is present only once in the frame
 no elements from outside the population of interest are present in the frame
 the data is up-to-date
 A sampling frame can be classified subject to several types of defect as follows:
 A frame may be inaccurate: where some of the sampling units of the population are
listed inaccurately or some units which do not actually exist are included in the list.
 A frame may be inadequate: when it does not include all classes of the population which
are to be taken the survey.
 A frame may be incomplete: when some of the sampling units of the population are
either completely omitted or includes more than once.
 A frame may be out of date: when it has not been updated according to the demand of
the occasion, although it was accurate, complete and adequate at the time of
construction.

Location and Scale Parameters

Uploaded by

Copyright:

Available Formats

Location and Scale Parameters

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Location and Scale Parameters

Uploaded by

Copyright:

Available Formats

Location and Scale Parameters

Normal PDF A probability distribution is characterized by location and scale parameters.

Probability Density Function f(x;a,b) = (1/b)f((x-a)/b;0,1)

Percent Point Function G(α;a,b) = a + bG(α;0,1)

Hazard Function h(x;a,b) = (1/b)h((x-a)/b;0,1)

Cumulative Hazard Function H(x;a,b) = H((x-a)/b;0,1)

Survival Function S(x;a,b) = S((x-a)/b;0,1)

Inverse Survival Function Z(α;a,b) = a + bZ(α;0,1)

Random Numbers Y(a,b) = a + bY(0,1)

Some of the other parameters used to define distributions:

Sampling Unit and Sampling Frame

You might also like