Independence and Conditional Probabilities: Core Concepts and Applications

Independence and Conditional Probabilities

General Rules of Probability

This section introduces foundational probability concepts essential for statistical inference, including independent events, conditional probability, and rules for calculating probabilities of combined events. These concepts are widely used in data analysis, diagnostics, and research.

• Independent Events: Events whose outcomes do not affect each other.

• Conditional Probability: The probability of one event occurring given that another has occurred.

• General Addition Rule: Used to find the probability that at least one of several events occurs.

• Multiplication Rule: Used to find the probability that two or more events occur together.

• Tree Diagrams: Visual tools for organizing and calculating probabilities of complex events.

• Diagnostic Tests: Application of probability rules to medical testing and interpretation.

Marginal, Conditional, and Joint Probabilities

Marginal Probability

Marginal probability (also called simple probability) is the probability of a single event occurring, without regard to the outcomes of other events.

• Notation: $P(A)$ is the probability of event A occurring.

• Example: The probability that a randomly selected employee is male.

Conditional Probability

Conditional probability is the probability that an event occurs given that another event has already occurred.

• Notation: $P(A|B)$ is the probability of A given B has occurred.

• Formula: $P(A|B) = \frac{P(A \text{ and } B)}{P(B)}$, provided $P(B) \neq 0$.

• Example: The probability that an employee favors high CEO salaries, given that the employee is male.

Joint Probability

The joint probability of two events is the probability that both events occur simultaneously.

• Notation: $P(A \text{ and } B)$ or $P(A \cap B)$.

• Multiplication Rule: $P(A \text{ and } B) = P(A)P(B|A) = P(B)P(A|B)$.

Example: Marginal and Conditional Probabilities with a Two-Way Table

Suppose all 100 employees of a company were asked whether they are in favor of or against paying high salaries to CEOs. The responses are summarized below:

	In Favor (A)	Against (B)	Total
Male (M)	15	45	60
Female (F)	4	36	40
Total	19	81	100

• Marginal Probability Examples:

  • $P(M) = \frac{60}{100} = 0.60$ (Probability a randomly selected employee is male)

  • $P(A) = \frac{19}{100} = 0.19$ (Probability a randomly selected employee favors high CEO salaries)

• Conditional Probability Examples:

  • $P(\text{In favor} | \text{Male}) = \frac{15}{60} = 0.25$

  • $P(\text{Female} | \text{In favor}) = \frac{4}{19} \approx 0.211$

Calculating Conditional Probability

Conditional probability quantifies the likelihood of an event, given that another event has occurred. The formula is:

• $P(B|A) = \frac{P(A \text{ and } B)}{P(A)}$

• $P(A|B) = \frac{P(A \text{ and } B)}{P(B)}$

• These formulas require that $P(A) \neq 0$ and $P(B) \neq 0$.

Example: College Students

• Let A = student is a senior, B = student is a computer science major.

• $P(A) = 0.20$, $P(A \text{ and } B) = 0.03$

• $P(B|A) = \frac{0.03}{0.20} = 0.15$

• This means that, given a student is a senior, there is a 15% chance they are a computer science major.

Independent Events

Two events are independent if the occurrence of one does not affect the probability of the other. Formally, A and B are independent if:

• $P(A|B) = P(A)$ or $P(B|A) = P(B)$

Example: Dalmatian Dogs

• HI = Dalmatian is hearing impaired, B = Dalmatian is blue-eyed

• $P(HI \text{ and } B) = 0.05$, $P(HI) = 0.28$, $P(B) = 0.11$

• $P(HI|B) = \frac{0.05}{0.11} \approx 0.45$

• Since $P(HI|B) \neq P(HI)$, the events are not independent.

Example: Smoking and Lung Cancer

• 11% of the population smokes ($P(S) = 0.11$)

• $P(\text{Lung cancer} | \text{Smoker}) = 0.34$

• $P(\text{Lung cancer} | \text{Nonsmoker}) = 0.03$

• Since $P(\text{Lung cancer} | \text{Smoker}) \neq P(\text{Lung cancer})$, smoking and lung cancer are not independent.

Multiplication Rule

The multiplication rule allows calculation of the probability that two events both occur.

• General Rule: $P(A \text{ and } B) = P(A)P(B|A)$

• For Independent Events: $P(A \text{ and } B) = P(A)P(B)$

Example: Blood Donation Center

• Probability that two unrelated visitors are both type O blood:

• $P(O \text{ and } O) = P(O) \times P(O) = (0.45)(0.45) = 0.2025$

Diagnostic Tests and Positive Predictive Value

Probability rules are crucial in interpreting diagnostic test results, such as for HIV-AIDS. The positive predictive value (PPV) is the probability that a person who tests positive actually has the disease.

• Sensitivity: Probability the test is positive given disease is present ($0.9985$)

• Specificity: Probability the test is negative given disease is absent ($0.9940$)

• Incidence: Proportion of the population with the disease ($0.01$)

Calculating PPV

• $P(\text{true-positive}) = P(\text{disease}) \times P(\text{positive} | \text{disease}) = (0.01)(0.9985) = 0.009985$

• $P(\text{false-positive}) = P(\text{no disease}) \times P(\text{positive} | \text{no disease}) = (0.99)(0.006) = 0.00594$

• $PPV = P(\text{disease} | \text{positive}) = \frac{P(\text{true-positive})}{P(\text{true-positive}) + P(\text{false-positive})} = \frac{0.009985}{0.009985 + 0.00594} \approx 0.627$

• This means that a random adult who gets a positive test result using this method actually has a ~63% probability of having HIV/AIDS.

Summary Table: Probability Types and Rules

Type	Definition	Formula	Example
Marginal Probability	Probability of a single event	$P(A)$	Probability an employee is male
Conditional Probability	Probability of A given B	$P(A|B) = \frac{P(A \text{ and } B)}{P(B)}$	Probability in favor given male
Joint Probability	Probability both A and B occur	$P(A \text{ and } B)$	Probability employee is male and in favor
Multiplication Rule	Probability both events occur	$P(A \text{ and } B) = P(A)P(B|A)$	Probability both visitors are type O
Independence	Events do not affect each other	$P(A|B) = P(A)$	Blood types of unrelated donors

Additional info: Tree diagrams, while mentioned, are not detailed in the slides. They are visual tools for mapping out sequences of events and their probabilities, especially useful for multi-step problems.