Normal Distribution
Normal Distribution
If a distribution consists of a very large number of cases and the three measures of averages (mean, median, and
mode) are equal, then the distribution is symmetrical, and the skewness is 0. In statistics, such distribution is called normal
distribution or simply normal curve.
Class Activity 1
Visualizing a Normal Distribution
The following table show score distribution of students in a mathematics quiz.
Task 1:
✓ Sketch the graph of the frequency polygon of each distribution.
✓ Use the Chart Wizard of the MS Excel Program to sketch the graphs if a computer is available.
✓ Answer the questions that follow.
1. Graph the frequency polygon of the scores of five students who took a quiz.
X(score) f
3 1
2 3
1 1
N 5
2. Now, let us increase the number of students to 13. Observe what will happen to the shape of the graph.
X(score) f
5 1
4 3
3 5
2 3
1 1
N 13
3. Let us further increase the number of students. From the first graph to the third graph, observe the transformation of the
figures.
X(score) f
9 1
8 2
7 4
6 7
5 11
4 7
3 4
2 2
1 1
N 39
4. If we continue to increase the number of students, what will be the shape of the graph? Take note also of its skewness.
5. For each distribution, compute the three measures of averages: mean, median, and mode. What do you notice? What
does this imply?
6. Where did you find these measures on the graph?
7. What generalization can you make?
Properties of a Normal Probability Distribution
The normal probability distribution has the following properties:
1. The distribution curve is bell-shaped.
2. The curve is symmetrical about its center.
3. The mean, the median, and the mode coincide at the center.
4. The width of the curve is determined by the standard deviation of the distribution.
5. The tails of the curve flatten out indefinitely along the horizontal axis, always approaching the axis but never touching
it. That is, the curve is asymptotic to the baseline.
6. The area under the curve is 1. Thus, it represents the probability or proportion, or percentage associated with specific
sets of measurement values.
Standard Normal Curve
The standard normal curve is a normal probability that is most commonly used as a model for inferential statistics. The
equation that describes a normal curve is
𝟏 𝐱−𝛍 𝟐
− ( )
𝐞 𝟐 𝛔
𝛄= 𝛔√𝟐𝛑
where:
γ = height of the curve for particular values of X
x = any score in the distribution
𝜎 = standard deviation of the population
μ = mean of the population
𝜋 = 3.1416
𝑒 = 2.7183
Definition:
A standard normal curve is a normal probability distribution that has a mean = 0 and a standard
deviation = 1.
The table of areas under the normal curve is also known as the z-table. The z-score is a measure of relative standing
and calculated by subtracting ̅X or (μ) from the measurement X and then dividing the result by s (or σ). The final result, the
z-score, represents the distance between a given measurement X and the mean, expressed in standard deviation. Wither
the z-score locates X within a sample or within a population.
Four-Step Process in Finding the Areas Under the Normal Curve Given a z-value
Step 1. Express the given z-value as a three-digit number.
Step 2. Using the z-table, find the first two digits on the leftmost column.
Step 3. Match the third digit with the appropriate column on the right.
Step 4. Read the area (or probability) at the intersection of the row and the column, this is the required area.
Examples:
1. Find the area that corresponds to z =1.36.
Steps Solution
1. Express the given z-value as a three-
z = 1.36 (as is)
digit number.
2. In the table, find the row z = 1.3 and
the column with heading .06.
3. Read the area (or probability) at the
This area is 0.4131. Th is the required
intersection of row 1.3 and the
area.
column .06.
2. Find the area that corresponds to z = 1.
Steps Solution
1. Express the given z-value as a three-
digit number.
2. In the table, find the row z = 1.0 and
the column with heading .00.
3. Read the area (or probability) at the
intersection of row 1.0 and the
column .00.
The z-score
The areas under the normal curve are given in terms of z-values or scores. The z-scores locates X either within a
sample or within a population.
The formula for calculating z is
X−μ
z= (z-score for population data)
𝜎
̅
X−X
z= (z-score for sample data)
s
where:
X =given measurement
μ =population mean
𝜎 =population standard deviation
s =sample standard deviation
Raw scores may be composed of large values, but these values cannot be accommodated at the baseline of the
normal curve. So, they have to be transformed into z-scores for convenience without sacrificing the meaning associated with
the raw scores.
For any population, the mean and standard deviation are fixed. Thus, the z formula matches the z-values of one-to-
one with the X values (raw scores). That is, for every S value, there corresponds a z-value and for each z-value, there is
exactly one X value.
The z-values are matched with specific areas under the normal curve in a normal distribution table. Therefore, if we
wish to find the percentage associated with X, we must find its matching z-value using the z-formula. The z-value leads to the
area under the curve found in the normal curve table, which is a probability, and that probability gives the desired percentage
for X.
The following examples illustrate these concepts:
1. Reading Scores
Given the mean μ = 50 and the standard deviation σ = 4 of a population of Reading Scores. Find the z-value
that corresponds to a score X = 58.
Steps Solution
1. Use the computing formula for finding
z-scores of population data.
2. Check the given values. Since these
are population values, the z-score
locates X within a population.
3. Substitute the given values in the
computing formula.
3. Score in PE
Locate the z-value that corresponds to a PE score of 39, given that μ = 45, and σ = 6.
Steps Solution
1. Use the computing formula for finding
z-scores of population data.
2. Check the given values. Since these
are population values, the z-score
locates X within a population.
3. Substitute the given values in the
computing formula.
Exercises
A. State whether the z-score locates the raw score X within a sample or within a population.
̅ = 40
1. X = 50, s = 5, X
2. X = 40, σ = 8, μ = 52
3. X = 36, s = 6, ̅
X = 28
4. X = 74, s = 10, ̅X = 60
5. X = 82, σ = 15, μ = 75
B. From Exercise A, state whether each row score lies below or above the mean.
C. Given ̅ X = 62 and s = 8, find the z-score up to two decimal places that corresponds to each of the following raw
scores.
1. X = 70 2. X = 78
3. X = 82 5. X = 42
4. X = 50
Lesson Three: Identifying Regions of Areas Under the Normal Curve
ENTRY CARD
Determine whether the statement is True (T) or False (F) by checking the appropriate box. If false, modify the statement to
make it true.
Statement T F
1. The expression 68% is equal to 0.68.
2. A probability distribution is a number from 0 and 1.
3. The normal curve is a probability distribution.
4. The normal curve is asymmetrical.
5. Under the normal curve, the areas at the tail are minimal.
6. The scores at the baseline of the normal curve are called z.
7. If μ = 60, σ = 5, and X = 70, then the z-score is 1.
Since the z-table provides the proportions of the area (or probability or percentage) between any two specific values
under the curve, regions under the curve can be describe in terms of area. For example, the area of the region between
𝑧 = 0 and 𝑧 = 1is given in the z-table to be 0.3413. we can do operations with the areas to identify more regions under
the curve. So, to find the area of the region between 𝑧 = 1 and 𝑧 = 2, we subtract 0.3413 from 0.4772 to get 0.1359. it is
graphically shown below.
Similarly, the area of the region between 𝑧 = 0 and 𝑧 = 3 using the z-table is 0.4987. So, the area between 𝑧 =
2 and 𝑧 = 3 is given by 0.4987 – 0.4772 = 0.0215.
If we want to identify the regions under the normal curve in terms of percent, the graph of the distribution would look
like this:
The following notations for a random variable are used in various solutions concerning the normal curve.
Mathematical notations are a convenient form of presenting lengthy expressions.
P(𝑎 < 𝑧 < 𝑏) denotes the probability that the z-score is between a and b.
P(𝑧 > 𝑎) denotes the probability that the z-score is greater than a.
P(𝑧 < 𝑎) denotes the probability that the z-score is less that a.
where 𝑎 and 𝑏 are z-score values.
For example, to denote the area between 𝑧 = 1 and 𝑧 = 2, we use the notation:
P(1 < 𝑧 < 2) = 0.1359
which read as “The probability that z-score falls between 𝑧 = 1 and 𝑧 = 2 is 0.1359.”
With continuous probability distributions like the normal distribution, P(𝑧 = 𝑎) = 0 where 𝑎 is a continuous random
variable. This means that with infinitely many different values, the probability of getting any one exact value is 0. Thus, it
follows that,
P(𝑎 ≤ 𝑧 ≤ 𝑏) = P(𝑎 < 𝑧 < 𝑏).
Illustrative Examples:
Case 1. The required area,
as depicted by the shaded
regions under the curve in
Figure 5 a and b is
greater than z
at least z
more than z
to the right of z
(a) (b)
above Figure 5. Area under the Normal Curve for Case 1 where (a) z is positive and (b) z is negative
(a) (b)
Figure 7. Area under the Normal Curve for Case 3 where the z-values are both (a) negative and (b)
positive
Example 5: Find the area between z = -2 and z = -1.5.
Example 6: Find the area between z = 0.98 and z = 2.58.
Case 4. The area is between -z and +z.
Figure 8. Area Under the Normal Curve for Case 4 where z-value is negative, and the other z-value is positive.
A. Determine each of the following areas and show these graphically. Use probability notation in your final answer.
1. Above z = 1.46
2. Below z = -0.58
3. Between z = -0.78 and -1.95
4. Between z =0.76 and z = 2.88
5. Between z = - 0.92 and z = 1.75
6. To the left of z = 2.78
B. Find the probabilities on a standard normal curve.
1. P(𝑧 > −1.32)
2. P(𝑧 < 0.45)
3. P(−2.76 < 𝑧 < 2)
Lesson FIVE: LOCATING PERCENTILES UNDER THE NORMAL CURVE
For any set of measurements (arranged in ascending or descending order), a percentile (or centile) is a point in the
distribution such that a given number of cases is below it. A percentile is a measure of relative standing. It is a descriptive
measure of the relationship of a measurement to the rest of the data.
Example: Find the 95th percentile of a normal curve.
Analysis: By definition of P95, this means locating an area before (or below) the point. We want to know what the z-value is at
this point.
Steps Solution
1. Draw a normal curve.
1. P99
2. P90
3. P68
4. P40
5. P32
Example: In the same problem, what is the score that divides the distribution such that 99% of the cases is below it?
Example: With μ = 80, and σ=15, what are the scores that bound the middle 95% of the distribution?