CHAPTER 3
Normal Probability Distribution
Random Variables and Probability Distribution
Suppose a system administrator monitors two computer servers in a network to check whether each server is
vulnerable to a specific cybersecurity threat. Each server can either be Vulnerable (V) or Not Vulnerable (N).
This simple experiment can have four possible outcomes: VV, VN, NV, and NN. Let the variable X represent
the number of vulnerable servers observed in the experiment. The variable X can take the values 0, 1, or 2. In this
example, X is a random variable because its value depends on the outcome of the system security check.
A probability distribution gives the probability for each value of the random variable. The table below, which
associates each outcome with its probability, is an example of a probability distribution.
No. of Vulnerable Servers (X) 0 1 2
Probability 0.25 0.50 0.25
Activity 1.
1. What does the random variable X represent in this experiment?
2. What is the probability that both servers are vulnerable to the cybersecurity threat?
3. What is the probability that exactly one server is vulnerable?
4. What is the probability that none of the servers are vulnerable?
5. Verify that the total probability in the table is equal to 1.
6. Based on the distribution, which outcome is most likely to occur? Explain briefly.
Types of Random Variables
1. Continuous random variables. Involve measurements on a continuous scale, which can take on infinitely many
values within a given range.
Examples:
Response time of a web server (in milliseconds)
CPU temperature of a computer system
Data transfer speed of a network connection (in Mbps)
Amount of storage space used by files in a server (in GB)
2. Discrete random variables. Have countable outcomes (whole numbers). These variables often represent
counts of occurrences or classifications.
Examples:
Number of users logged into a server at a given time
Number of failed login attempts recorded in a system
Number of packets lost during a network transmission
Number of software bugs detected during program testing
CONTINUOUS PROBABILITY DISTRIBUTION
A continuous probability distribution is a type of probability distribution that describes continuous random
variables, which can take on any value within a given range. Continuous random variables are associated with various
types of distributions.
Some common types of continuous probability distributions include:
1. Normal distribution
2. Gamma distribution
3. Exponential distribution
4. Beta distribution
5. Cauchy distribution
6. Weibull distribution
7. Uniform distribution
In this chapter, we will focus on the normal distribution, as it is the most widely used and important continuous
distribution in statistics.
Activity 2.
A network administrator recorded the response times (in milliseconds) of 9 servers during a system performance
check. The recorded response times were: 42.4, 45.1, 48.3, 50.0, 50.0, 50.0, 51.7, 54.9, 57.6
Part A — Descriptive checks
1. Verify whether mean = median = mode for this dataset. Show your computations.
Part B — Standardization
2. Compute the sample mean and sample standard deviation.
3. Standardize each observation to compute its z-score using the sample mean and the sample standard
deviation.
Z-Score
A Z-score tells us how many standard deviations a value is away from the mean.
Formula:
𝑥 − 𝑥̅
𝑧=
𝑠
• z is the standardized score (Z-score)
• x is the raw score (the observed value)
• 𝑥̅ is the mean of the distribution
• s is the standard deviation
Systolic BP (mmHg) z-score
42.4
45.1
48.3
50.0
50.0
50.0
51.7
54.9
57.6
Part C — Probability density
2
𝑧
1
4. For each z-score computed in (3), compute the probability density 𝑓(𝑧) = 𝑒 −2
.
√2𝜋
z-score Probability density f(z)
Part D — Visualization
5. Draw a figure showing the standard normal curve and mark each z-score on the curve.
Characteristics of a Normal Curve
• It is symmetric with respect to a vertical axis passing through the mean.
• The mean, median, and mode are equal.
• The tails are asymptotic relative to the horizontal line.
• Area under the curve equals 1.
• Normal distributions are defined by two parameters, the mean (μ) and the standard deviation (σ).
• The Empirical Rule (68–95–99.7 Rule)
About 68% of the data fall within 1σ of the mean.
About 95% fall within 2σ of the mean.
About 99.7% fall within 3σ of the mean.
Part E — The Empirical Rule (68–95–99.7 Rule)
6. Using your computed mean and standard deviation, identify the server response time ranges (in
milliseconds) that correspond to:
o Within 1 standard deviation of the mean (≈ 68% of server response times)
o Within 2 standard deviations of the mean (≈ 95% of server response times)
o Within 3 standard deviations of the mean (≈ 99.7% of server response times)
Part F — Probability Applications
7. Find the following probabilities using the Standard Normal Table. For each item, illustrate the
corresponding area under the normal curve by drawing its figure.
a. P(Z > - 0.58)
b. P(Z < 2.4)
c. P(Z > 2.4)
d. P(Z < - 0.58)
e. P(-0.25 < Z < 1.64)
Case Formula Description
1. Area to the left of Z P(Z < z) Read directly from the Z-table
2. Area to the right of Z P(Z > z) = 1 - P(Z < z ) Subtract from 1
3. Area to the left of –Z P(Z < - z) Read directly from the Z-table
4. Area to the right of –Z P(Z > -z) = P(Z < z ) Use the symmetry of the curve
5. Area between two Z- P(a < Z < b) = P(Z < b) - P(Z Subtract the smaller area from the
values <a) larger