theonline.mba
← Back to OMBA 102

OMBA 102 · Unit 4 of 7

Statistical Inference

Data, Statistics and Managerial Decisions

Start unit · 5 lessons →

Learning objectives

After completing this unit, you will be able to:

  • Distinguish samples from populations and quantify sampling error
  • Build and interpret confidence intervals for business metrics
  • Conduct hypothesis tests with correct managerial framing
  • Separate statistical significance from business significance
  • Avoid common errors in statistical reasoning (p-hacking, multiple comparisons, etc.)

Why this matters

A/B tests, surveys, and pilots drive billion-dollar decisions. Unit 4 teaches you what inferential statistics can and cannot prove so you do not overreact to noise or underreact to real signal.

Unit overview

Work through the five lessons below in order. Work examples with real or provided sample sizes.

#LessonCore idea
1Samples, Populations, and Sampling ErrorRepresentative data and margin of error
2Confidence IntervalsRange estimates for means and proportions
3Hypothesis TestingNull, alternative, and test logic
4Statistical Significance versus Business SignificancePractical importance vs p-values
5Common Errors in Statistical ReasoningPitfalls managers must catch

Connection to applied work

Design a simple test plan for one project hypothesis: population, sample, metric, and what result would change your decision.

Practice

  1. Explain why a survey of only power users biases inference.
  2. Compute a confidence interval for a proportion (use provided data).
  3. Frame a hypothesis test for a pricing experiment in plain English.
  4. Name one result that is statistically significant but not worth acting on.

Knowledge check

  1. What is sampling error?
  2. How do you interpret a 95% confidence interval?
  3. What does a p-value not tell you?
  4. What is business significance?
  5. What is p-hacking?

Key takeaways

  • Inference generalizes from samples with stated uncertainty.
  • Significance is not the same as importance.
  • Skepticism is part of data literacy.
  • Finish lessons before assessments.

Unit assessment

Complete each section below. Score 80%+ on the quiz to finish this unit's assessment.

40% applied project35% knowledge checks25% reflections

Exercises

Apply what you learned in this unit with structured practice.

ExerciseApplied practice: Statistical Inference45 min
Complete a focused practice exercise on **Statistical Inference**. 1. Choose a real company, product, or situation you know. 2. Apply one core framework from this unit to analyze it. 3. Write your analysis in 300–500 words with a clear recommendation. 4. Cite at least one credible source.

Deliverable

300–500 word analysis document saved to your portfolio under OMBA 102.

Rubric

  • Framework applied correctly (not just named)
  • Specific evidence from a real example
  • Clear recommendation with tradeoffs acknowledged
  • Professional writing with source citation
ExerciseDrill: Statistical Inference30 min
Work through the practice problems in the unit lesson without looking at notes. Then check your work against the lesson and write a short reflection: - What you got right - One mistake you caught - One concept to review before the next unit

Deliverable

Problem solutions + 150-word reflection in your OMBA 102 workbook.

Rubric

  • Attempted all practice items before checking answers
  • Honest reflection on errors
  • Identifies a specific review action

Model / spreadsheet

Build or extend a spreadsheet model tied to this unit.

ModelStructured model: Statistical Inference60 min
Create a structured analytical model for **Statistical Inference**. Document your assumptions, calculations, and conclusions in a format appropriate to OMBA 102 (diagram, table, or written model). Connect outputs to a decision a manager would make.

Deliverable

Structured model document (2+ pages) · One-paragraph summary of key insight from the model · Screenshot or export saved to portfolio

Rubric

  • Assumptions stated explicitly
  • Logic is auditable (formulas or steps visible)
  • Output answers a specific business question
  • Sensitivity or scenario considered

Knowledge quiz

Check your understanding before marking the unit complete.

1. A sample of 400 visitors yields 42 conversions. The population parameter of interest is:

2. A 95% confidence interval for conversion is 3.7% to 4.3%. Which executive read is most appropriate?

3. In a two-sided A/B test of conversion, the null hypothesis H₀ is typically:

4. A p-value of 0.03 in a well-designed test means:

5. Rejecting a true null hypothesis at α = 0.05 is called:

6. A test shows statistically significant 0.1% conversion lift on 2 million users, worth $8,000 annually, while implementation costs $500,000. Best conclusion?

7. Running 20 independent tests at α = 0.05 without adjustment makes false positives:

8. Convenience sampling website visitors on Tuesday morning primarily threatens: