PracticeBARFree practice exam

BAR · Business Analysis · 6 practice questions

Correlation vs. Causation: Confounding and Selection Bias

A strong correlation or statistically significant regression coefficient does not establish causation. Follow a retailer's coupon-push analysis to check confounding, reverse causality, and selection before recommending action.

The ruleCorrelation and statistically significant regression coefficients establish association, not causation. Random assignment provides stronger evidence of an effect than comparisons based on voluntary choices.

Try one first

Heaton Industries' analyst observes that there is a strong positive correlation (r = 0.92) between the company's quarterly ice cream sales and the quarterly outdoor temperature in degrees Fahrenheit at company headquarters. The analyst concludes that warmer temperatures CAUSE increased ice cream sales, and recommends marketing focus on hotter regions. Is the analyst's reasoning sound?
Hint

Correlation ≠ causation. Strong r doesn't establish causal direction. Alternatives: direct causation, reverse causation, confounding (most common, e.g., season drives both temperature and sales), spurious correlation. Test causality with controls, experiments, domain knowledge.

Step by step

  1. State the observed association

    A retailer finds that stores sending more mobile-app coupon pushes have higher weekly sales, with a positive, statistically significant regression coefficient. This supports an association, not proof that more pushes cause higher sales.

  2. Look for a common cause

    Larger stores can have more app users and higher sales, creating more pushes and more sales without establishing an effect of pushes. Store size is a potential confounder because it can drive both variables.

  3. Check the causal direction

    If strong sales lead managers to schedule more pushes for the following week, sales are helping cause pushes. That is reverse causality, not a common cause.

  4. Check how stores were selected

    If stores chose whether to increase pushes, the groups may differ before the increase. Comparing those groups can reflect selection rather than the effect of additional pushes.

  5. Do not overread regression controls

    Adding store size can address that measured confounder, but it does not automatically resolve reverse causality or selection. A significant push coefficient after controls still does not establish causation.

  6. Prefer a randomized comparison

    Randomly assign similar stores to additional pushes or usual pushes during the same period. This provides a stronger basis for attributing a sales difference to the additional pushes.

  7. Match the conclusion to the design

    For the observational analysis, report that more pushes are associated with higher sales. Do not describe the coefficient as the sales lift management will obtain by requiring more pushes.

Key points

  • Remember: More pushes and higher sales together do not show that requiring more pushes will increase sales.
  • A common cause explains both variables; reverse causality sends the causal direction backward.
  • Controls address measured factors, not every possible explanation.
  • Stores that choose more pushes may differ before any pushes occur.

How the exam traps you

  • Calling a significant push coefficient a proven sales lift. Describe an association unless the study design supports a causal effect.
  • Assuming store-size controls eliminate every alternative explanation. Check reverse causality and selection even after controlling for size.
  • Treating stores that chose more pushes as a comparable treatment group. Prefer random assignment to more pushes or usual pushes during the same period.

5 more, each from a different angle

0 of 5 answered · 0 correct

Question 2

Elara Co. forecasts weekly product demand. Its current regression uses prior-week demand and promotion days. A proposed model adds website click counts. In the training data, click counts have a 0.70 correlation with demand, and training R-squared rises from 0.64 to 0.67. In a holdout sample, RMSE rises from 9.8 units to 10.1 units when clicks are added. Which assessment best addresses whether clicks add predictive value?
Hint

Focus on incremental performance using data not used to fit the model, rather than simple association.

Question 3

A retail chain is evaluating a new shelf layout for snack items. Management wants to know whether the layout itself increases sales. Which approach would give the strongest basis for management's decision?
Hint

Prefer evidence that compares similar groups at the same time while limiting self-selection and timing effects.

Question 4

A company estimates whether customer age predicts subscription cancellation. The file includes only accounts that completed a free trial and became paying subscribers, trial-completion rates vary by age, ages are recorded at signup, cancellations are summarized monthly, and subscription plans are combined. In this file, age has almost no association with later cancellation. Which interpretation best explains why that finding may not hold for all trial users?
Hint

Compare the population of interest with the records used before interpreting the observed relationship.

Question 5

A streaming service compared customers who accepted a loyalty offer with customers who did not. Acceptance was voluntary, and no random assignment was used. A regression controlling for prior usage, account age, and region found a positive $15 coefficient on offer acceptance, statistically significant. The data did not include customers' interest in upcoming releases. Which report sentence is best supported?
Hint

Ask whether the design identifies cause, or only estimates a relationship conditional on included variables.

Question 6

A controller reviews a dashboard showing the correlation between monthly advertising spend and monthly sales. One reported value would indicate the dashboard formula is wrong. Which value is it?
Hint

Check whether the reported statistic can ever be less than the minimum or greater than the maximum possible value.

Drill all 95 Data analytics, regression analysis, and quantitative methods questionsMixed across every rule in the topic, so you have to spot which one applies. That is how the exam does it.

Common questions

Does a statistically significant regression coefficient prove causation?

No. A significant coefficient linking coupon pushes to sales supports an association, but confounding, reverse causality, or selection may explain it.

What is the difference between confounding and reverse causality?

Store size is a confounder if it drives both coupon pushes and sales. Reverse causality occurs if strong sales lead managers to schedule more pushes.

Why is random assignment better than voluntary participation?

Stores choosing more pushes may already differ from other stores. Random assignment creates comparable groups and provides stronger evidence about the effect of additional pushes.

Practice BAR like the real exam

The free ChatCPA simulator: real exam layout, timed testlets, starting with a question on this topic. No account needed to start.

Open the free simulator →

More on Data analytics, regression analysis, and quantitative methods

All Data analytics, regression analysis, and quantitative methods practice →

Questions from the ChatCPA bank of 17,658 CPA exam questions, each with a written reason for every wrong answer. ChatCPA is built by Nicholas Miller, CPA (Oregon #14907). How these pages are made. Spot an error? Tell us.