4.

3 NORMAL DISTRIBUTION
A normal distribution known as the Gaussian distribution is a continuous probability
distribution that has a bell-shaped probability density function.
The data near the mean are more frequent in occurrence than data far from the mean.
In graphical form, the normal distribution appears as a "bell curve".

Because the normal distribution is a continuous distribution, we can not calculate exact
probability for an outcome, but instead we calculate a probability for a range of
outcomes ( ex. the probability that a random variable X is greater than 10).
 

Since it is a continuous distribution, the total area under the curve is one. The
parameters of the normal are the mean μ and the standard deviation σ.
 A special normal distribution, called the standard normal distribution is the
distribution of z-scores. Its mean is zero, and its standard deviation is one.

Often times the x values of the standard normal distribution are called z-scores. We
can calculate probabilities using a normal distribution table (z-table). 
note that in these tables, the probabilities are the area to the LEFT of the z-
score.  If you need to find the area to the right of a z-score (Z greater than
some value), you need to subtract the value in the table from one.
Using this table, we can calculate p(-1<z<1). To do so, first look up the probability
that z is less than negative one [p(z)<-1 = 0.1538].  Because the normal distribution
is symmetric, we therefore know that the probability that z is greater than one also
equals 0.1587 [p(z)>1 = 0.1587].  To calculate the probability that z falls between 1
and -1 is

1 – 2(0.1587) = 0.6826. 
The green area in the figure above roughly equals 68% of the area under the curve. 
We can convert any and all normal distributions to the standard normal distribution
using the equation below.  The z-score equals an X minus the population mean (μ)
all divided by the standard deviation (σ).
Ex. 1
We want to determine the probability that a randomly selected blue crab has a
weight (x) greater than 1 kg.  Based on previous research we assume that the
distribution of weights (kg) of adult blue crabs is normally distributed with a
population mean (μ) of  0.8 kg and a standard deviation (σ) of 0.3 kg.  How do we
determine this probability? 

First, we calculate the z score by replacing X with 1, the mean (μ) with 0.8 and
standard deviation (σ) with 0.3. 

We calculate our z-score to be (1-0.8)/0.3=0.6667. 

We can then look in our z table to determine the p(z>0.6667) is roughly 1-0.748
(pulled from the chart, somewhere between 0.7454 and 0.7486) = 0.252.  Therefore,
based on our normality assumption, we conclude that the likelihood that a
randomly selected adult blue crab weighs more than one kilogram is roughly 25.2%
(the area shaded in blue).

Z table
Ex 2.

4.4 NORMAL APPROXIMATION TO BINOMIAL & POISSON DISTRIBUTION

If X is a random variable that follows a binomial distribution with n trials and p probability

of success on a given trial, then we can calculate the mean (μ) and standard deviation
(σ) of X using the following formulas:
It turns out that if n is sufficiently large then we can actually use the normal
distribution to approximate the probabilities related to the binomial distribution. This is
known as the normal approximation to the binomial.
For n to be “sufficiently large” it needs to meet the following criteria:

When both criteria are met, we can use the normal distribution to answer probability
questions related to the binomial distribution.
However, the normal distribution is a continuous probability distribution while the
binomial distribution is a discrete probability distribution, so we must apply a continuity
correction when calculating probabilities.
In simple terms, a continuity correction is the name given to adding or subtracting 0.5 to
a discrete x-value.

The following table shows when you should add or subtract 0.5, based on the type of
probability you’re trying to find:

The following step-by-step example shows how to use the normal distribution to
approximate the binomial distribution.

Example: Normal Approximation to the Binomial

Suppose we want to know the probability that a coin lands on heads less than or equal
to 43 times during 100 flips.

In this situation we have the following values:

  n (number of trials) = 100
 X (number of successes) = 43
 p (probability of success on a given trial) = 0.50

To calculate the probability of the coin landing on heads less than or equal to 43 times,
we can use the following steps:

Step 1: Verify that the sample size is large enough to use the normal
approximation.

First, we must verify that the following criteria are met:

 np ≥ 5
 n(1-p) ≥ 5

In this case, we have:

 np = 100 x 0.5 = 50
 n(1-p) = 100 (1 – 0.5) = 100(0.5) = 50

Both numbers are greater than 5, so we’re safe to use the normal approximation.

Step 2: Determine the continuity correction to apply.

Referring to the table above, we see that we should add 0.5 when we’re working with a
probability in the form of X ≤ 43. Thus, we will be finding P(X< 43.5).
Step 3: Find the mean (μ) and standard deviation (σ) of the binomial distribution.
μ = n*p = 100*0.5 = 50
σ = √n*p*(1-p) = √100*.5*(1-.5) = √25 = 5

Step 4: Find the z-score using the mean and standard deviation found in the previous step.

z = (x – μ) / σ = (43.5 – 50) / 5 = -6.5 / 5 = -1.3.

Step 5: Find the probability associated with the z-score.

We can use the Normal CDF Calculator to find that the area under the standard normal
curve to the left of -1.3 is .0968.

Thus, the probability that a coin lands on heads less than or equal to 43 times during
100 flips is .0968.
This example illustrated the following:

 We had a situation where a random variable followed a binomial distribution.

 We wanted to find the probability of obtaining a certain value for this random
variable.
 Since the sample size (n = 100 trials) was sufficiently large, we were able to use
the normal distribution to approximate the binomial distribution.

Post Comment

4.4 NORMAL APPROXIMATION TO POISSON DISTRIBUTION

Normal approximation to Poisson distribution

Let X be a Poisson distributed random variable with mean λ.
The mean of Poisson random variable is: μ=E(X)=λ 
 
variance  is  σ2=V(X)=λ

The general rule of thumb to use normal approximation to Poisson distribution is

that 
λ is sufficiently large (i.e., λ≥5).
For sufficiently large λ, X∼N(μ,σ2). That is 
Formula for continuity corrections:

Poisson distribution is a discrete distribution, whereas normal distribution is a

continuous distribution. When we are using the normal approximation to Poisson
distribution we need to make correction while calculating various probabilities.
Ex. 1
The annual number of earthquakes registering at least 2.5 on the Richter Scale and
having an epicenter within 40 miles of downtown Memphis follows a Poisson
distribution with mean 6.5. What is the probability that at least 9 such earthquakes
will strike next year?

Ex. 2
The vehicles enter to the entrance at an expressway follow a Poisson distribution
with mean vehicles per hour of 25. Find the probability that in 1 hour the vehicles
are between 23 and 27 inclusive, using Normal approximation to Poisson
distribution

Solution:

Let 
X = number of vehicles enter to the expressway per hour.
λ=25 = The mean number of vehicles enter to the expressway per hour .
Since λ=25 is large enough, we use normal approximation to Poisson distribution.
(We use continuity correction)
The probability that in 1 hour the vehicles are between 23 and 27 (inclusive) is

NORMAL APPROXIMATION TO BINOMIAL DISTRIBUTION

Ex.

Previous studies have found that 75% of adults use the internet on a regular basis. A researcher
believes this percentage has recently increased. He conducts a survey and discovers that 2144
out of 2824 adults surveyed use the internet on a regular basis. Assuming 75 actually is the
correct percentage, what's the probability of seeing at least this many users out of 2824 users?
Does this happening seem to provide evidence that the percentage of adult internet users has
increased?
Ass.
A Boeing 767-300 aircraft has 213 seats. When someone buys a ticket for a flight there is a
0.0995 probability that the person will not show up for the flight. A ticket agent accepts 236
reservations for a flight that uses a Boeing 767-300. Find the probability that not enough seats
will be available. Is this probability low enough so that overbooking is not a real concern? If not,
how many tickets should be sold so that the probability is less than 10% that at least one
person will not have a seat? Show detailed solution.