Lecture Topic 4: Chapter 7
Sampling and Sampling Distributions
Statistical Inference:
• The aim is to obtain information about a population from
information contained in a sample.
• A population is the set of all the elements of interest under
consideration. (p.258)
• Numerical characteristics of a population, such as the mean
and standard deviation, are called parameters. (p.258)
• A sample is a subset of the population selected for analysis.
(p.258)
• The sample results provide only estimates of the values of the
population characteristics.
• The way in which we select our sample is important
o Keep in mind we typically take a sample from a
population to learn more about the population
o Our sample should be representative of the population
at large
o Knowing whether a sample is representative of the
population is difficult since it is our limited knowledge
of the population that leads us to sample in the first
place
o An approach to gathering our sample must be
developed to safeguard against possible biases
7.2 Simple Random Sampling
From a Finite Population
• A random sample from a finite population of size N is a
sample selected such that each possible sample of size n has
the same probability of being selected. (p.260)
• Replacing each sample element before selecting subsequent
elements is called sampling with replacement.
From an Infinite Population
• A random sample from an infinite population is a sample
selected such that the following conditions are satisfied:
o Each element comes from the same population
o Each element is selected independently
7.3 Point Estimation
• We use the data from the sample to compute a value of a
sample statistic that serves as an estimate of a population
parameter.
o Another way to say this is that we want to infer the
population characteristics (e.g., mean) from the sample
data
• A sample statistic is a real-valued function T = r(X1, X2,
X3,……, Xn) of the random variables. It is a formula showing
how to combine the sample data to form a point estimate of
the population parameter. It is called an estimator.
• We refer to the sample mean x as the point estimator of the
population mean μ. (p.265)
• s is the point estimator of the population standard deviation
. (p.265)
• p is the point estimator of the population proportion p.
Sampling Error
• The absolute difference between an unbiased point estimate
and the corresponding population parameter is called the
sampling error.
• Sampling error is the result of using a subset of the
population, not the entire population.
• The sampling errors are:
|x-μ| for sample mean
|s-| for sample standard deviation
|p–P| for sample proportion
7.4 Introduction to Sampling Distributions
• The sample statistic T is a function of X1, X2, X3,……, Xn and
since X1, X2, X3,……, Xn are random variables, it follows that
T is also a random variable.
o The value of T will vary from sample to sample since
the values assumed by X1, X2, X3,……, Xn will vary from
sample to sample
• The value our sample mean (for example) takes on depends
on the actual sample selected.
• For each different possible sample we could generate a value
of T.
• Just as many different samples can be drawn from a
population, many different sample means can be formed.
• This idea is very important
o It suggests that sample statistics have probability
distributions showing the different possible values the
sample statistic can assume, along with the associated
probability.
o The probability distribution for a sample statistic is
called a sampling distribution.
7.5 Sampling Distribution of x
• The sampling distribution of x is the probability distribution
of all possible values of the sample mean x. (p. 270)
o As with other sampling distributions x has an expected
value, a standard deviation, and a characteristic shape
or form.
• When the expected value of a point estimator equals the
population parameter, we say the point estimator is unbiased.
(p. 270)
• Form of the Sampling Distribution of x
o Population has a normal distribution – In many
situations it is reasonable to assume that the
population from which we are selecting a simple
random sample has a normal or near normal
distribution. (p.272)
o Population does not have a normal distribution –
When the population from which we are selecting a
simple random sample does not have a normal
distribution, the central limit theorem is helpful in
identifying the shape of the sampling distribution.
(p.272)
• The central limit theorem says the sampling distribution of
x can be approximated by a normal probability distribution
when we use a large (n 30) random sample.
7.6 Sampling Distribution of p
• Remember that the sample proportion p is the point estimator
of the population proportion p.
• The sampling distribution of p is the probability distribution
of all possible values of the sample proportion p.
• Standard Deviation of p
o Formula depends on whether the population is finite or
infinite.
• Form of the Sampling Distribution of p
o The sampling distribution of p can be approximated
by a normal distribution whenever np 5 and n(1 –
p) 5. (p. 281)
7.7 Properties of Point Estimators
• Since several different sample statistics can be used as
point estimators of different population parameters general
notation will be used in this section:
= the population parameter of interest
= the sample statistic or point estimator of
• Unbiased
o If the expected value of the sample statistic is equal
to the population parameter being estimated, the
sample statistic is an unbiased estimator of the
population parameter.
• Efficiency
o Given the choice of two unbiased estimators, we
prefer the point estimator with the smaller standard
deviation.
• Consistency
o A point estimator is consistent if the values of the
point estimator become closer to the population
parameter as the sample size becomes larger.