Business Statistics –
Sampling distributions
Dr. Nisha Prakash
Class of 2023-25 (Session 17-18)
What is a sampling distribution?
• Probability distribution of statistics from all possible samples is a sampling distribution
• Sampling distribution could be of:
• Mean/Median/Mode
• Range
• Variance/Standard deviation
• Proportion
Examples
Sampling Error
• Standard deviation of a sampling distribution is standard error (SE) of the statistic
• SE gives an indication of whether statistic can be used to estimate parameter
• Less spread out sample means (low SE) is a good estimator of population mean
Important: Standard deviation of the sampling distribution is not the same as standard
deviation of the population
Notations
Statistics of sampling distribution is indicated by a cap
Population
distribution
Sample frequency
distribution
Sampling
distribution
Central limit theorem
With higher sample size (>30), the sampling distribution
approaches normal distribution
Mean of the sample distribution approaches the
population mean
SEM = standard deviation of population / √n
Diminishing return in sampling
This holds true for both normal and non-normal
population distributions
CLT - Problems
In a normal distribution with mean 56 and standard deviation 21, how large a sample must be
taken so that there will be at least a 90 percent chance that its mean is greater than 52?
In a normal distribution with mean 375 and standard deviation 48, how large a sample must be
taken so that the probability will be at least 0.95 that the sample mean falls between 370 and 380?
CLT - Application
The distribution of annual earnings of all bank tellers with five years’ experience is skewed with a
mean $19,000 and a standard deviation of $2,000. If we draw a random sample of 30 tellers, what
is the probability that their earnings will average more than $19,750 annually?
CLT for finite population
If population size is finite (N), then the standard error of the mean is given as:
The factor is called the finite population multiplier
Example: Suppose we are interested in a population of 20 textile companies of the same size, all
of which are experiencing excessive labor turnover. The standard deviation of annual turnover is
75 employees. What is the standard error for samples of five textile companies?
CLT - Problems
An oil refinery has backup monitors to keep track of the refinery flows continuously and to
prevent machine malfunctions from disrupting the process. One particular monitor has an average
life of 4,300 hours and a standard deviation of 730 hours. In addition to the primary monitor, the
refinery has set up two standby units, which are duplicates of the primary one. In the case of
malfunction of one of the monitors, another will automatically take over in its place. The operating
life of each monitor is independent of the others.
(a) What is the probability that a given set of monitors will last at least 13,000 hours?
(b) At most 12,630 hours?
CLT - Problems
A ferry carries 25 passengers. The weight of each passenger has a normal distribution with mean
168 pounds and variance 361 pounds squared. Safety regulations state that for this particular ferry,
the total weight of passengers on the boat should not exceed 4,250 pounds more than 5 percent of
the time. As a service to the ferry owners, find
(a) The probability that the total weight of passengers on the ferry will exceed 4,250 pounds.
(b) The 95th percentile of the distribution of the total weight of passengers on the ferry.
Is the ferry complying with safety regulations?
CLT - Problems
Indian Oil Company has recently launched a public relation campaign to persuade its subscribers
to reduce the wasteful use of the fuel. The Company’s marketing research director believes that
about 40% of the subscribers are aware of the campaign. He wishes to find out how large a sample
would be needed to be 95% confident that the true proportion is within 3% of the sample
proportion?
Not solved yet
Normal distribution tables
`
