Normal Distribution report

VIII - Normal Distribution and Standard Scores
What is a normal distribution?
The normal distribution is a pattern for the distribution of a set of data which follows a
bell-shaped curve. This distribution is sometimes called the Gaussian distribution in honor of
Carl Friedrich Gauss, a famous mathematician. For instance, the histogram below shows the
salaries of a group of individuals which is said to follow a normal distribution. On the vertical
axis are the frequencies and on the horizontal axis are the salaries. A closer look at the graph
reveals that :
a) there are relatively few individuals with low salaries, i.e., $20k (1), $25k (2) and
$30k(3);
b) there are relatively few individuals with high salaries, i.e. $60k (3), $5k (2),$70k (1);
c) there are relative many individuals with salaries closer to the mean (which is $45k).
Although the heights of rectangles equidistant from the center may not necessarily be of
the same height, the point is, the farther away from the center of the rectangle is, the less is the
frequency – that is, there are fewer persons with incomes of $20K, $25K and $30k (low income)
and $60k, $65k and $70k (high income). And the closer to the center a rectangle is, the greater is
its frequency – that is, there are more individuals with salaries closer to the middle or average
value. They are represented by rectangles $35k, $40k, up to $55k.
By connecting the midpoints of the tops of the rectangles of our histogram and extending
the lines slightly on both ends, we form a frequency polygon. The polygon appears to be a
triangle, however, if we use a very large population, the histogram will contain many rectangles
and the corresponding frequency polygon becomes smooth and bell-shaped.
1
.
Importance of the Normal Distribution
Among the many continuous distributions used in statistics, the normal distributions is by
far the most important because it approximates many natural phenomena so well like people’s
IQ scores, heights and weights, dimensions of manufactures products and other measures of
interest to managers and policy planners in both the public and private sectors. Although the
distributions are approximately normal, the approximation is usually quite close.
Another reason why the normal distribution is so important is that a number of statistical
tools are based on the assumption that the data come from normal distribution.
The normal distribution requires that the data be of at least interval scale.
Characteristics of the normal distribution
1. The graph of the normal distribution is bell-shaped and the two tails extend indefinitely
in either directions without touching the horizontal axis (line) as shown in the figure
below.
2. The graph has a single peak at the center of the distribution. The mean, median and
mode are equal and are all located at the peak.
3. The graph is symmetrical about its mean. If you were to fold the distribution along the
center, the 2 halves would be identical.
4. The area under the curve is equal to 1 with 0.5 at the left side of the center and another
0.5 at its right.
5. The normal curve may be subdivided into at least 3 standard scores, each to the left and
to the right of the vertical axis.
6. Along the horizontal line, the distance from one integral standard score to the next
integral standard score is measured by the standard deviation.
Here's another example of a bell shaped curve. This represents a normal distribution with
a mean of 50 and a standard deviation of 10.
2
Notice that most of the area falls between 20 and 80. This means that values smaller than
20 or larger than 80 are extremely rare for this variable. Compare this to a normal distribution
with a mean of 50 and a standard deviation of 2.
Although the picture looks similar, the scale has changed. Almost all of the area is
between 44 and 56. With a smaller standard deviation, the proportion of values (observations) is
much more concentrated. Compare this to a normal distribution with the same standard
deviation, 2, but a larger mean of 70.
Now most of the area is between 64 and 76. The spread of the data is about the same, but
the proportion of values shifted to larger values.
3
The Standard Normal Distribution
The normal distribution with a mean of 0 and a standard deviation of 1 is very important.
The graph of the standard normal distribution appears below.
Let’s look at the numbers at the horizontal axis. The values -4, -3, and so on up to 3, 4,
are called standard scores. A standard score indicates how many standard deviations an
observation is above or below the mean. Standard scores are also called Z-scores. Zero at the
middle is the value of the population mean, denoted by μ. The negative numbers to the left of
zero are values that fall below the mean while the positive numbers are values that are higher
than the mean. These standard scores can be derived using the formula:
Z=X-μ
σ
where Z is the standard score,

X is the raw score
μ is the population mean
σ is the population standard deviation.
A standard score is useful in comparing 2 values from different series, especially when
these 2 series differ with respect to the mean or standard deviation or both are expressed in
different units.
Examples:
1. Joey got a grade of 75% in English and a grade of 90% in History. The mean grade in
English is 65% and the standard deviation is 10%, whereas in History, the mean grade is 80%
and the standard deviation is 20% . In which subject did Joey perform better?
Solution:
Compute the Z-score in English and in History :
English History
X (raw score) 75% 90%

μ 65% 80%
σ 10% 20%
Z (English) = 75 – 65 Z (History) = 90 - 80
10 20
= 10/10 = 10/20
= 1.0 = 0.5
Joey performed better in English because he has a higher standard score in English than in
History.
4
2. The mean grade of students who took Computer Programming is 77.1 and the standard
deviation is equal to 8.03. Carl got a grade of 64 and he was worried because the university has
the policy that a student will fail if he obtains a grade which falls beyond two (2) standard
deviations below the mean. Will Carl fail the course?
Solution :
We need to solve for the Z-score to find out if the raw score of Carl is less than or equal
to -2.
X (or the raw score of Carl) = 64

μ (mean grade) = 77.1
σ = 8.03
Z = X-μ
σ
= 64 – 77.1
8.03
= -13.1/8.03
= -1.63
Thus, Carl will not fail the course.
Addendum
In a normal distribution, approximately

68% of the observations fall within the range μ + 1σ;
95% of the observations fall within the range μ + 2σ; and
99% of the observations fall within the range μ + 3σ; and
Try these:
1. In a Statistics examination, the mean grade is 78 and the standard deviation is 10.
1.1 Find the corresponding Z-scores of two students whose grades are 93 and 62,
respectively.
1.2 Find the grades of two students whose Z-scores are -0.6 and 1.2, respectively.
2. Two men are on a weight-reducing diet. The first belongs to an age/body type group for
which the mean weight is 145 pounds with a standard deviation of 15 pounds. The second
belongs to an age/body type group for which the mean weight is 165 pounds with a standard
deviation of 20 pounds. If their respective weights are 178 and 204 pounds, who is more
definitely overweight for his age/body type group?
3. Mr. Henson works for a company whose employees had an average income of PhP150,000 in
the past year, with standard deviation of PhP3,000. How much did Mr. Henson earn last year if
the z-score is equal to -0.80?

Normal Distribution report

Uploaded by

Copyright:

Available Formats

Normal Distribution report

Uploaded by

Document Information

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

Normal Distribution report

Uploaded by

Copyright:

Available Formats

VIII - Normal Distribution and Standard Scores

What is a normal distribution?

Importance of the Normal Distribution

Characteristics of the normal distribution

where Z is the standard score,

X (raw score) 75% 90%

X (or the raw score of Carl) = 64

Thus, Carl will not fail the course.

In a normal distribution, approximately

You might also like