UNIT II Statistical Probability

Statistical Probability Distributions for Civil Engineering Applications

Statistical probability distributions –Students’ t, Chi – square and F – distributions – applications

1. Introduction to Probability Distributions

In statistics, a probability distribution describes how the values of a random variable are distributed. It tells us which values a variable is likely to take and how often.

Why Probability Distributions Matter in Civil Engineering?

Civil engineers deal with real-world data such as soil strength, traffic flow, and concrete quality. Since exact values are unpredictable, we use probability distributions to make decisions.

The three important probability distributions used in Civil Engineering are:

• Student’s t-distribution (for small sample sizes)
• Chi-square distribution (for variance and independence testing)
• F-distribution (for comparing two variances)

---

2. Student’s t-Distribution

Definition

The Student’s t-distribution is used when the sample size is small ($n < 30$), and the population standard deviation ($\sigma$) is unknown. It helps in estimating the true mean of a population from a small sample.

Formula

$$t = \frac{\bar{x} - \mu}{s / \sqrt{n}}$$

where:
$\bar{x}$ = Sample mean
$\mu$ = Population mean
$s$ = Sample standard deviation
$n$ = Sample size

Characteristics of t-Distribution

• Bell-shaped and symmetric, like the normal distribution.
• More spread out than the normal distribution (fatter tails).
• As $n$ increases, the t-distribution approaches a normal distribution.

Example Problem 1

A Civil Engineering lab tests the compressive strength of concrete samples ($n = 10$). The sample mean is 40 MPa, and the standard deviation is 5 MPa. Find the t-value if the assumed true mean is 42 MPa.

Solution

Given:
$\bar{x} = 40$, $\mu = 42$, $s = 5$, $n = 10$

$$t = \frac{40 - 42}{5 / \sqrt{10}} = \frac{-2}{5 / 3.16} = \frac{-2}{1.58} = -1.27$$

So, t = -1.27

---

3. Chi-Square ($\chi^2$) Distribution

Definition

The Chi-square distribution is used for testing variance and checking whether observed data fits expected data. It is used for:

1. Testing variance of a sample against a population.
2. Testing independence between two factors (e.g., rainfall and landslides).

Formula for Variance Testing

$$\chi^2 = \frac{(n-1) s^2}{\sigma^2}$$

where:
$s^2$ = Sample variance
$\sigma^2$ = Population variance
$n$ = Sample size

Characteristics of Chi-square Distribution

• Not symmetric, skewed to the right.
• Changes shape with different degrees of freedom ($df = n-1$).
• Always positive, since variance cannot be negative.

Example Problem 2

A Civil Engineer wants to check if the variance of soil moisture measurements (sample size 15) is 4%. The sample variance is 6%. Find the Chi-square value.

Solution

Given:
$s^2 = 6$, $\sigma^2 = 4$, $n = 15$

$$\chi^2 = \frac{(15-1) \times 6}{4} = \frac{14 \times 6}{4} = \frac{84}{4} = 21$$

So, $\chi^2 = 21$

---

4. F-Distribution

Definition

The F-distribution is used to compare two variances to determine if they are significantly different. This is useful in material strength tests or comparing soil sample variances.

Formula

$$F = \frac{s_1^2}{s_2^2}$$

where:
$s_1^2$ = Variance of sample 1
$s_2^2$ = Variance of sample 2

Characteristics of F-Distribution

• Not symmetric, skewed to the right.
• Used only for positive values.
• Changes shape based on degrees of freedom ($df_1, df_2$).

Example Problem 3

Two concrete batches are tested for compressive strength. The variances of the first and second batches are 8 MPa² and 5 MPa² respectively. Find the F-ratio.

Solution

Given:
$s_1^2 = 8$, $s_2^2 = 5$

$$F = \frac{8}{5} = 1.6$$

So, F = 1.6

---

5. Civil Engineering Applications

Student’s t-distribution Applications

• Testing material strengths (Concrete, Steel) with small sample sizes.
• Determining the mean settlement of a building foundation.

Chi-square Distribution Applications

• Checking soil quality variations.
• Analyzing traffic accident data to see if accidents depend on time of day.

F-Distribution Applications

• Comparing strength variations in different concrete mixes.
• Testing differences in earthquake intensities across different locations.

---

6. Quiz Questions

1. When is Student’s t-distribution used?
2. What is the formula for Chi-square variance test?
3. Which distribution is used to compare two variances?
4. If sample size n increases, what happens to the t-distribution?
5. What is the Chi-square test used for in Civil Engineering?
6. Why do we use F-distribution instead of Chi-square sometimes?
7. In a t-test, what happens if the sample standard deviation is 0?
8. What is the minimum sample size required for a Chi-square test to be valid?
9. If two concrete samples have equal variances, what is the F-value?
10. Which test would you use to check whether traffic accidents are independent of time of day?

---

This detailed lecture note covers definitions, formulas, problems, and applications of t, Chi-square, and F-distributions in Civil Engineering. 🚀

Unit II Uniform, normal, log normal, Exponential & Gamma Distributions

Lecture Notes on Probability Distributions for Continuous Random Variables

Probability distributions for continuous random variables – Uniform, normal, log normal, exponential and Gamma distributions – Applications

Introduction

Probability distributions for continuous random variables play a fundamental role in probability and statistics. In this lecture, we will explore five essential continuous distributions:

• Uniform Distribution
• Normal Distribution
• Log-normal Distribution
• Exponential Distribution
• Gamma Distribution

Each of these distributions has important applications in civil engineering, including material strength analysis, reliability assessment, and environmental studies.

---

1. Uniform Distribution

Definition

A random variable $X$ follows a uniform distribution on the interval $(a, b)$ if its probability density function (PDF) is:

$$f(x) = \begin{cases} \frac{1}{b-a}, & a \leq x \leq b \\ 0, & \text{otherwise} \end{cases}$$

Cumulative Distribution Function (CDF)

$$F(x) = \begin{cases} 0, & x < a \\ \frac{x-a}{b-a}, & a \leq x \leq b \\ 1, & x > b \end{cases}$$

Mean and Variance

$$E[X] = \frac{a+b}{2}, \quad Var(X) = \frac{(b-a)^2}{12}$$

Application in Civil Engineering

• Traffic Flow Analysis: Modeling vehicle arrival times at an intersection.
• Construction Materials: Estimating the uniform spread of loads on a beam.

Example Problem

A pedestrian waits for a bus that arrives uniformly between 10:00 and 10:30 AM. What is the probability they wait less than 10 minutes?

Solution: Given $a = 0$ min and $b = 30$ min, the probability of waiting less than 10 minutes is:

$$P(X < 10) = \frac{10 - 0}{30 - 0} = \frac{10}{30} = \frac{1}{3}$$

---

2. Normal Distribution

Definition

A random variable $X$ follows a normal distribution with mean $\mu$ and variance $\sigma^2$, denoted as $X \sim N(\mu, \sigma^2)$, if its PDF is:

$$f(x) = \frac{1}{\sqrt{2\pi \sigma^2}} e^{-\frac{(x-\mu)^2}{2\sigma^2}}, \quad -\infty < x < \infty$$

CDF

There is no closed-form expression, but values are found using normal tables or statistical software.

Mean and Variance

$$E[X] = \mu, \quad Var(X) = \sigma^2$$

Application in Civil Engineering

• Material Strength: Concrete strength follows a normal distribution.
• Bridge Load Analysis: The distribution of vehicle weights on a bridge.

Example Problem

The compressive strength of concrete follows $N(30, 4^2)$. What is the probability that a randomly selected sample has strength above 35 MPa?

Solution: Standardizing:

$$Z = \frac{X - \mu}{\sigma} = \frac{35 - 30}{4} = \frac{5}{4} = 1.25$$

From the normal table: $P(Z > 1.25) = 1 - 0.8944 = 0.1056$. Thus, the probability is 10.56%.

---

3. Log-normal Distribution

Definition

A random variable $X$ follows a log-normal distribution if $Y = \ln(X)$ follows a normal distribution.

PDF:

$$f(x) = \frac{1}{x \sigma \sqrt{2\pi}} e^{-\frac{(\ln x - \mu)^2}{2\sigma^2}}, \quad x > 0$$

Application in Civil Engineering

• Soil Permeability: The distribution of soil permeability measurements.
• Building Service Life: Modeling the lifespan of materials subject to degradation.

Example Problem

If $Y = \ln(X)$ follows $N(2, 0.25)$, find the median of $X$.

Solution: The median of a log-normal distribution is:

$$Median(X) = e^\mu = e^2 = 7.389$$

Thus, the median is 7.39.

---

4. Exponential Distribution

Definition

The exponential distribution models the time until an event occurs. The PDF is:

$$f(x) = \lambda e^{-\lambda x}, \quad x > 0$$

Mean and Variance

$$E[X] = \frac{1}{\lambda}, \quad Var(X) = \frac{1}{\lambda^2}$$

Application in Civil Engineering

• Reliability Analysis: Modeling the time between failures of construction equipment.
• Queueing Theory: Modeling the time between vehicle arrivals at toll booths.

Example Problem

A water pump fails on average once every 10 years. What is the probability it lasts more than 15 years?

Solution: Here, $\lambda = \frac{1}{10}$. The probability is:

$$P(X > 15) = e^{-\lambda x} = e^{-\frac{15}{10}} = e^{-1.5} \approx 0.2231$$

So, the probability is 22.31%.

---

5. Gamma Distribution

Definition

The gamma distribution is a generalization of the exponential distribution. It is given by:

$$f(x) = \frac{\lambda^k x^{k-1} e^{-\lambda x}}{\Gamma(k)}, \quad x > 0$$

where $k$ is the shape parameter and $\lambda$ is the rate parameter.

Mean and Variance

$$E[X] = \frac{k}{\lambda}, \quad Var(X) = \frac{k}{\lambda^2}$$

Application in Civil Engineering

• Flood Risk Analysis: Modeling the time between extreme rainfall events.
• Structural Load Analysis: Modeling the cumulative load effects over time.

Example Problem

If failures in a bridge structure follow a gamma distribution with $k = 2$ and $\lambda = 1/5$, find the probability that failure occurs before 8 years.

Solution: The cumulative probability is obtained using the gamma CDF:

$$P(X \leq 8) = \int_0^8 \frac{(1/5)^2 x e^{-x/5}}{\Gamma(2)} dx$$

Using tables or software, $P(X \leq 8) \approx 0.798$, or 79.8%.

---

Summary Table

Distribution	PDF	Mean	Variance	Civil Engineering Applications
Uniform	$\frac{1}{b-a}$	$\frac{a+b}{2}$	$\frac{(b-a)^2}{12}$	Traffic flow, material loads
Normal	$\frac{1}{\sqrt{2\pi \sigma^2}} e^{-\frac{(x-\mu)^2}{2\sigma^2}}$	$\mu$	$\sigma^2$	Concrete strength, vehicle loads
Log-normal	$\frac{1}{x \sigma \sqrt{2\pi}} e^{-\frac{(\ln x - \mu)^2}{2\sigma^2}}$	$e^{\mu + \sigma^2/2}$	$(e^{\sigma^2} -1)e^{2\mu + \sigma^2}$	Soil permeability, material lifespan
Exponential	$\lambda e^{-\lambda x}$	$1/\lambda$	$1/\lambda^2$	Equipment failure, traffic delays
Gamma	$\frac{\lambda^k x^{k-1} e^{-\lambda x}}{\Gamma(k)}$	$k/\lambda$	$k/\lambda^2$	Flood risk, structural loads

---

Conclusion

Understanding these distributions helps civil engineers make informed decisions in infrastructure design, reliability analysis, and risk management.