Statistics Test #2 Review: Correlation, Regression, and Probability

Q1. Does a linear correlation between CO2 concentration and global mean temperature imply causation?

Background

Topic: Correlation vs. Causation

This question tests your understanding of the difference between statistical correlation and causation, a fundamental concept in statistics.

Key Terms:

• Correlation: A statistical measure that describes the extent to which two variables change together.

• Causation: When one variable directly affects another.

• Confounding Variable: An outside influence that can affect both variables being studied.

Step-by-Step Guidance

1. Recall that correlation measures the strength and direction of a linear relationship between two variables, but does not imply that one causes the other.

2. Think about possible confounding variables or other explanations for the observed correlation.

3. Consider what additional evidence would be needed to establish causation (e.g., experimental data, ruling out confounders).

4. Reflect on why statisticians are careful to distinguish between correlation and causation in studies.

Try solving on your own before revealing the answer!

Q2. Cheese and Engineering: Is there a linear correlation between mozzarella cheese consumption and civil engineering PhDs? Does this suggest causation?

Background

Topic: Correlation, Spurious Correlation, and Causation

This question asks you to analyze a real-world data set for correlation and to interpret whether a relationship implies causation.

Key Terms and Formulas:

• Linear Correlation Coefficient (r): Measures the strength and direction of a linear relationship between two variables.

• Spurious Correlation: When two variables appear to be related but are not causally connected.

Step-by-Step Guidance

1. Examine the data for a pattern that suggests a linear relationship between cheese consumption and PhDs awarded.

2. Calculate or estimate the correlation coefficient $r$ using the provided data.

3. Interpret the value of $r$ to determine if there is a strong, weak, or no linear correlation.

4. Discuss whether the observed correlation could be due to coincidence or a lurking variable, rather than a causal relationship.

Try solving on your own before revealing the answer!

Q3. Regression Equation Interpretation

Background

Topic: Simple Linear Regression

This question tests your ability to interpret the components of a regression equation and understand the meaning of slope, intercept, and predictor variables.

Key Terms and Formulas:

• Regression Equation: $\hat{y} = b_0 + b_1x$

• Slope ($b_1$): The change in $\hat{y}$ for a one-unit increase in $x$.

• Intercept ($b_0$): The predicted value of $\hat{y}$ when $x = 0$.

• Predictor Variable: The independent variable ($x$).

Step-by-Step Guidance

1. Identify what $x$ represents in the context of the regression equation provided.

2. State the values of the slope and intercept from the equation $\hat{y} = 58.9 - 0.00749x$.

3. Determine which variable is the predictor (independent) and which is the response (dependent).

4. Set up the calculation for the predicted value of $\hat{y}$ when $x = 3000$ lb, but do not compute the final value yet.

Try solving on your own before revealing the answer!

Q4. Regression Prediction for Small Cars

Background

Topic: Regression Prediction

This question asks you to use a regression equation to predict a response variable for a given value of the predictor variable.

Key Terms and Formulas:

• Regression Equation: $\hat{y} = b_0 + b_1x$

• Prediction: Substitute the given $x$ value into the regression equation to estimate $\hat{y}$.

Step-by-Step Guidance

1. Identify the regression equation provided: $\hat{y} = 53.7 - 0.00505x$.

2. Recognize that $x$ is the car's weight and $\hat{y}$ is the predicted highway fuel consumption.

3. Set up the substitution for $x = 2500$ lb into the regression equation.

4. Prepare to calculate $\hat{y}$, but stop before performing the arithmetic.

Try solving on your own before revealing the answer!

Q5. Bear Measurements: Predicting Weight from Head Width

Background

Topic: Regression Prediction

This question involves using a regression equation to predict the weight of a bear based on its head width.

Key Terms and Formulas:

• Regression Equation: $\hat{y} = b_0 + b_1x$

• Prediction: Substitute the given head width into the equation to estimate weight.

Step-by-Step Guidance

1. Identify the regression equation: $\hat{y} = -212 + 61.9x$.

2. Recognize that $x$ is the head width and $\hat{y}$ is the predicted weight.

3. Set up the substitution for $x = 6.5$ inches into the regression equation.

4. Prepare to calculate $\hat{y}$, but do not compute the final value yet.

Try solving on your own before revealing the answer!

Q6. Probability: ESP Experiment

Background

Topic: Basic Probability

This question tests your understanding of probability as a measure of the likelihood of an event.

Key Terms and Formulas:

• Probability: $P(A) = \frac{\text{Number of favorable outcomes}}{\text{Total number of outcomes}}$

Step-by-Step Guidance

1. Identify the probability of answering a question correctly as given (20%).

2. Express this probability as a decimal or fraction.

Try solving on your own before revealing the answer!

Q7. Probability: Multiple Choice Test

Background

Topic: Probability of Complementary Events

This question asks you to find the probability of a wrong answer when guessing on a multiple-choice question.

Key Terms and Formulas:

• Probability of Correct Answer: $P(\text{correct}) = \frac{1}{n}$ where $n$ is the number of choices.

• Probability of Wrong Answer: $P(\text{wrong}) = 1 - P(\text{correct})$

Step-by-Step Guidance

1. Count the total number of answer choices (a, b, c, d, e = 5).

2. Calculate the probability of a correct answer by random guess.

3. Subtract this probability from 1 to find the probability of a wrong answer.

Try solving on your own before revealing the answer!

Q8. Probability: Birthday Problem

Background

Topic: Probability of a Specific Outcome

This question asks you to calculate the probability of randomly selecting a specific day (the author's birthday) from all days in a year.

Key Terms and Formulas:

• Probability: $P = \frac{1}{365}$ (for a non-leap year)

Step-by-Step Guidance

1. Recognize that there are 365 possible days in a non-leap year.

2. Set up the probability as the ratio of 1 favorable outcome to 365 possible outcomes.

Try solving on your own before revealing the answer!

Q9. Probability: Online Courses

Background

Topic: Probability of Independent Events

This question tests your understanding of the multiplication rule for independent events.

Key Terms and Formulas:

• Probability of Both Events: $P(A \text{ and } B) = P(A) \times P(B)$ if A and B are independent.

Step-by-Step Guidance

1. Identify the probability that one student takes only online courses (10% or 0.10).

2. Multiply this probability by itself to find the probability that both students take only online courses.

Try solving on your own before revealing the answer!

Q10. Probability with Experimental Vaccine Data

Background

Topic: Probability with Contingency Tables

This question asks you to calculate probabilities based on a two-way table of experimental results.

Key Terms and Formulas:

• Probability: $P = \frac{\text{Number of favorable outcomes}}{\text{Total number of outcomes}}$

• Without Replacement: Adjust the denominator for each selection.

Step-by-Step Guidance

1. Identify the total number of subjects and the number in each category (developed flu, did not develop flu, vaccine, placebo).

2. For each probability question, set up the ratio of favorable outcomes to total outcomes.

3. For questions involving "without replacement," remember to reduce the total number of subjects for the second selection.

Try solving on your own before revealing the answer!

Q11. Probability with Left-Handedness Data

Background

Topic: Probability with Categorical Data

This question involves calculating probabilities from a contingency table and interpreting results in context.

Key Terms and Formulas:

• Probability: $P = \frac{\text{Number of favorable outcomes}}{\text{Total number of outcomes}}$

• Complement: $P(A') = 1 - P(A)$

Step-by-Step Guidance

1. Identify the total number of subjects and the counts for each category (male/female, left/right-handed).

2. For each probability, set up the ratio of favorable outcomes to total outcomes.

3. For questions involving "without replacement," adjust the denominator for the second selection.

4. For complement questions, subtract the probability of the event from 1.

Try solving on your own before revealing the answer!

Q12. Bear Weight and Chest Size: Correlation and Prediction

Background

Topic: Correlation and Regression Analysis

This question asks you to interpret correlation results and consider the practical implications for prediction.

Key Terms and Formulas:

• Correlation Coefficient ($r$): Measures the strength and direction of a linear relationship.

• P-value: Used to test the significance of the correlation.

Step-by-Step Guidance

1. Interpret the value of the correlation coefficient ($r$) and compare it to the critical value.

2. Use the p-value to determine if the correlation is statistically significant at $\alpha = 0.05$.

3. Discuss whether chest size can be used to predict weight based on the strength of the correlation.

Try solving on your own before revealing the answer!

Q13. Word Counts and Heights: Linear Correlation Analysis

Background

Topic: Linear Correlation and Regression

This question asks you to interpret output from statistical software and determine if there is a significant linear relationship between two variables.

Key Terms and Formulas:

• Correlation Coefficient ($r$): Indicates the strength and direction of a linear relationship.

• P-value: Used to test the null hypothesis of no correlation.

Step-by-Step Guidance

1. Examine the correlation coefficient and p-value provided in the output.

2. Compare the p-value to the significance level ($\alpha = 0.05$) to determine statistical significance.

3. Interpret the results in the context of the variables (word counts, heights).

Try solving on your own before revealing the answer!

Q14. Calculating the Pearson Correlation Coefficient

Background

Topic: Pearson's Correlation Coefficient

This question asks you to use the formula for Pearson's $r$ to calculate the linear correlation coefficient from data.

Key Formula:

Where:

• $n$ = number of data pairs

• $x$ = values of the first variable

• $y$ = values of the second variable

• $\Sigma$ = summation notation

Step-by-Step Guidance

1. List all $x$ and $y$ values from the data set.

2. Calculate $\Sigma x$, $\Sigma y$, $\Sigma xy$, $\Sigma x^2$, and $\Sigma y^2$.

3. Substitute these sums into the Pearson formula for $r$.

4. Simplify the numerator and denominator, but do not compute the final value yet.

Try solving on your own before revealing the answer!

Q15. Powerball Jackpots and Tickets Sold: Correlation Analysis

Background

Topic: Scatterplots, Correlation, and Statistical Significance

This question asks you to construct a scatterplot, calculate the correlation coefficient, and determine if the correlation is statistically significant.

Key Terms and Formulas:

• Scatterplot: A graph of paired data points ($x$, $y$).

• Correlation Coefficient ($r$): Use the Pearson formula as above.

• Critical Value: Compare $r$ to the critical value for significance at $\alpha = 0.05$.

Step-by-Step Guidance

1. Plot the data pairs on a scatterplot to visually assess the relationship.

2. Calculate the correlation coefficient $r$ using the Pearson formula.

3. Find the critical value for $r$ at $\alpha = 0.05$ for the given sample size.

4. Compare your calculated $r$ to the critical value to assess statistical significance, but do not state the final conclusion yet.

Try solving on your own before revealing the answer!