Study Guide: Regression, Probability, and the Normal Model in Statistics

Chapter 4 – Regression Analysis: Exploring Associations between Variables

Section 4.1 – Visualizing Variability with a Scatterplot

Scatterplots are essential tools for visualizing the relationship between two quantitative variables. They help identify patterns, trends, and possible associations.

• Scatterplot: A graph of paired data points (x, y) for two variables.

• Association or Trend:

  • Positive: As one variable increases, the other tends to increase.

  • Negative: As one variable increases, the other tends to decrease.

  • None: No discernible pattern.

• Form (Shape):

  • Linear: Points roughly follow a straight line.

  • Nonlinear: Points follow a curved or other non-linear pattern.

Example: Plotting students' study hours (x) against exam scores (y) to see if more study time is associated with higher scores.

Section 4.2 – Measuring Strength of Association with Correlation

The correlation coefficient quantifies the strength and direction of a linear relationship between two variables.

• Correlation Coefficient (r):

  • Always look at the scatterplot to interpret correlation.

  • Correlation does not mean causation.

  • $r$ close to 0: No linear association.

  • $r$ close to 1 or -1: Strong linear association (positive or negative).

  • Changing the order of variables does not change $r$.

  • Changing units (multiplying by a positive constant) does not affect $r$.

  • $r$ is unitless (no units attached).

Example: If $r = 0.95$, there is a strong positive linear relationship between the two variables.

Section 4.3 – Modeling Linear Trends

Linear regression models the relationship between an explanatory variable and a response variable using a straight line.

• Regression Line: The best-fit line through the data points in a scatterplot.

• Intercept ($a$): The predicted value of the response variable when the explanatory variable is zero.

• Slope ($b$): Indicates how much the response variable changes for each one-unit increase in the explanatory variable.

• Explanatory Variable: Also called predictor, independent variable, or x-value.

• Response Variable: Also called predicted, dependent variable, or y-value.

Regression Equation:

$y = a + bx$

Example: Predicting house prices (y) based on square footage (x).

Section 4.4 – Evaluating the Linear Model

Evaluating a regression model involves assessing its fit and understanding its limitations.

• Correlation is not causation: A strong correlation does not imply that one variable causes the other.

• Coefficient of Determination ($r^2$): Measures the proportion of variance in the response variable explained by the explanatory variable. (Note: Students are instructed to skip calculation and interpretation of $r^2$ for this course.)

• Goodness of Fit: Indicates how well the regression line represents the data.

Example: A regression model with $r^2 = 0.85$ explains 85% of the variability in the response variable. (For this course, calculation and interpretation of $r^2$ are not required.)

Chapter 5 – Modeling Variation with Probability

Section 5.1 – What is Randomness?

Probability theory models the uncertainty and variation in random phenomena.

• Experiment: A repeatable process with uncertain outcomes.

• Random: Outcomes are unpredictable in the short run but follow a pattern in the long run.

• Simulations: Imitate random processes to estimate probabilities.

• Probability:

  • Theoretical: Based on mathematical reasoning.

  • Empirical: Based on observed data.

Example: Flipping a coin is a random experiment; the probability of heads is 0.5.

Section 5.2 – Finding Theoretical Probabilities

Theoretical probability uses mathematical models to determine the likelihood of events.

• Complement: The probability that an event does not occur.

• Sample Space: The set of all possible outcomes.

• Event: A subset of the sample space.

• OR (Union): Probability that at least one of several events occurs.

• Mutually Exclusive Events: Events that cannot occur together.

• Venn Diagram: Visual tool for representing events and their relationships.

Example: Rolling a die: sample space = {1,2,3,4,5,6}; event = rolling an even number.

Section 5.3 – Associations in Categorical Variables

Probability rules help analyze relationships between categorical variables.

• Conditional Probabilities: Probability of one event given another has occurred.

• Independent Events: Occurrence of one event does not affect the probability of the other.

• Contingency Table: Table showing frequencies for combinations of categorical variables.

• Multiplication Rule: For independent events, $P(A ext{ and } B) = P(A) imes P(B)$.

Example: Probability of drawing two aces in a row from a deck (without replacement).

Section 5.4 – Finding Empirical Probabilities

Empirical probability is based on observed data from experiments or simulations.

• Law of Large Numbers: As the number of trials increases, empirical probability approaches theoretical probability.

• Streaks: Sequences of similar outcomes (e.g., several heads in a row).

Example: Observing the proportion of heads in 1,000 coin tosses.

Chapter 6 – Modeling Random Events: The Normal Model

Section 6.1 – Probability Distributions are Models of Random Phenomena

Probability distributions describe how probabilities are distributed over possible outcomes.

• Probability Model: Mathematical description of a random process.

• Probability Distribution: Lists or functions showing probabilities for all possible outcomes.

• Probability Distribution Function (pdf): Function that assigns probabilities to outcomes.

• Discrete Outcomes: Outcomes that can be counted (e.g., number of heads).

• Continuous Outcomes: Outcomes that can take any value in an interval (e.g., height).

• Probability Density Curve: Curve representing the distribution of a continuous random variable.

• Area Under Curves: Represents probability for continuous distributions.

Example: The probability of a randomly selected person being between 160 and 170 cm tall is the area under the normal curve between those values.

Section 6.2 – The Normal Model

The normal model is a continuous probability distribution that is symmetric and bell-shaped, commonly used in statistics.

• Normal Model: Also called the normal distribution; describes many natural phenomena.

• Normal Curve (Distribution): The graphical representation of the normal model.

• Mean ($bc$): The center of the distribution.

• Standard Deviation ($c3$): Measures the spread of the distribution.

• Percentile: The value below which a given percentage of observations fall.

Normal Distribution Formula:

$P(a < X < b) = \int_a^b \frac{1}{\sigma \sqrt{2\pi}} e^{-\frac{(x-\mu)^2}{2\sigma^2}} dx$

Example: Heights of adult men are approximately normally distributed with mean 70 inches and standard deviation 3 inches.