Probability Distributions Study Notes
Introduction to Probability Distributions
- Key types of distributions discussed:
- Binomial Distribution
- Poisson Distribution
- Continuous Distributions
- Importance of distinguishing between discrete and continuous random variables.
Binomial Distribution
- Also referred to as binomial probability distribution.
- Characteristics:
- Discrete Random Variables: Can take values like 0, 1, 2, … (whole numbers only).
- Examples of discrete variables:
- People count
- Whole items count
- No decimal values allowed for random variables.
Definition and Conditions
- Binomial Experiment: An experiment that satisfies the following conditions:
- Fixed number of trials, denoted by n.
- Each trial must be independent: The outcome of one trial does not affect another (e.g., tossing a coin).
- Each trial has exactly two possible outcomes: Success or Failure.
- Random variable X counts the number of successful trials.
Components
- n: Denotes the number of trials.
- X: Possible values range from 0 to n (e.g., X can be 0, 1, 2, …, n).
- Probability of Success (p): This is provided in the problem.
- Probability of Failure (q): Calculated as:
q = 1 - p - Probabilities are calculated using statements such as:
- Probability of X = specific value
- Probability of X > specific value
- Probability of X < specific value
Calculation Steps
- Use Excel for calculations instead of manual methods.
- General command structure in Excel:
- For left-side probabilities (e.g., P(X ≤ x)):
- =BINOM.DIST(x, n, p, TRUE)
- To calculate exact probabilities:
- Use the command with FALSE at the end to indicate exact values.
Understanding Probability Statements
- Probability inequalities need to be carefully structured:
- Less than or equal to: P(X ≤ x)
- Greater than: complement rule is applied to find the left-side probabilities.
- Visual representation of inequalities is important (solid vs. dotted lines to indicate whether endpoints are included).
Statistical Measures
- Mean (Expected Value):
- Calculated as:
ext{Mean} = n imes p
- Calculated as:
- Variance:
- Calculated as:
ext{Variance} = n imes p imes q
- Calculated as:
- Standard Deviation:
- Calculated as:
ext{Standard Deviation} = ext{sqrt}(n imes p imes q)
- Calculated as:
Example of Binomial Calculations
- Provided scenario:
- Number of trials (n): 20 bulbs.
- Probability of success (p): 3%.
- Calculate proportion success (p) from percentage:
- p = 0.03
- q = 1 - 0.03 = 0.97
- Example prompts:
- Identify conditions for binomial experiment
- Define random variable, calculate probabilities, and expected number.
Implementing in Excel
- Input calculations based on the probability statement in Excel using appropriate commands as outlined:
- Exact probability: =BINOM.DIST(3, n, p, FALSE)
- At most probability: =BINOM.DIST(1, n, p, TRUE)
- Expected number calculation: =n imes p .
Poisson Distribution
- Used when mean is given in context (e.g. average rate per time unit).
- Distinct from binomial distribution in setup since it doesn't require the number of trials.
- Key properties of Poisson:
- Mean (μ) indicates the average occurrence in a given time frame.
- Example of Poisson command in Excel for specific calculations:
- Exact value: =POISSON.DIST(x, mean, FALSE)
- Less than: =POISSON.DIST(x, mean, TRUE)
Poisson Probability Scenarios
- Where the random variable X is defined:
- Probability of X = k (exact): P(x = k)
- Probability of X ≤ k (cumulative): P(X ≤ k)
- Probability of X > k (use complement rule): P(X > k) = 1 - P(X ≤ k)
Conclusion and Note on Unusual Events
Definition of Unusual Events: Events with probabilities less than 0.05 are considered unusual based on context and statistical thresholds.
Always confirm if the resulting value falls under the umbrella of unusual probabilities.
Important to keep in mind: when dealing with empirical scenarios, understand the interpretative distinction of the output probabilities whether they are usual or unusual based on the statistical regulations set forth in probability theory.