Skip to content
Tutorials Center
My learning

Topics

Lesson 53 of 57 ยท Practice and Review

Practice Set: Descriptive Statistics and Probability

Twelve worked practice problems on mean, median, spread, z-scores, outliers, conditional probability, Bayes' theorem and counting, with solutions you can run.

Reading about statistics is not enough: you learn it by solving problems. This practice set has twelve problems grouped into descriptive statistics and probability. For each one, try it with pencil and paper first, then run the code to compare. The code also shows the formula behind each answer, so you can see how to do the same thing by hand.

Part A: describing data

Problem 1. Eight response times (seconds): 4, 8, 6, 5, 3, 9, 7, 100. Find the mean, median, sample standard deviation and IQR. Which summary would you report, and why?

Problem 2. Using the 1.5 ร— IQR rule, is 100 an outlier? What are the fences?

Problem 3. Exam scores in a class have mean 70 and standard deviation 8. Ann scored 86 and Ben scored 62 on this exam. In another class (mean 60, sd 5) Cara scored 72. Compute the z-scores; who did best relative to their class?

Problem 4. A frequency table: values 1, 2, 3, 4, 5 occurred 4, 7, 10, 5, 4 times. Find the mean and the mode.

Python Solutions for Part A

Press Run (or Ctrl + Enter) to see the result here.

Program input ยท what you'd type while the program runs

Type the answers before you press Run, one per line. Each time the program reads a line (with input()), it gets the next line from this box.

The outlier of 100 drags the mean to about 17.8 while the median stays at 6.5, so the median and IQR describe the typical response time far better. Cara's z-score of 2.4 beats Ann's 2.0, even though Ann's raw score is higher: z-scores compare standing within each group.

Part B: probability

Problem 5. Two fair dice are rolled. What is the probability that the sum is at least 10? That the sum is even and greater than 6?

Problem 6. A box has 5 red and 3 blue balls. Two balls are drawn without replacement. What is the probability that both are red? That they are different colors?

Problem 7. A disease affects 1% of people. A test has 95% sensitivity (positive if sick) and 90% specificity (negative if healthy). If a person tests positive, what is the probability they have the disease?

Problem 8. How many different 4-letter arrangements can be made from the letters of the word MATH if no letter repeats? How many ways to choose a committee of 3 from 10 people? What is the probability that a random 5-card hand contains exactly two aces?

Python Solutions for Part B

Press Run (or Ctrl + Enter) to see the result here.

Program input ยท what you'd type while the program runs

Type the answers before you press Run, one per line. Each time the program reads a line (with input()), it gets the next line from this box.

Problem 7 surprises most people: only about 8.7% of positive tests are real, because the disease is rare and false positives from the 99% healthy majority swamp the true positives. Build the habit of drawing a 2ร—2 table of 10,000 people to see it: 100 sick (95 positive) and 9,900 healthy (990 positive).

Part C: distributions in action

Problem 9. A fair coin is tossed 10 times. Find P(exactly 3 heads) and P(at least 8 heads).

Problem 10. A help desk receives on average 4 calls per hour (Poisson). Find P(exactly 6 calls in an hour) and P(no calls in 30 minutes).

Problem 11. Heights are normal with mean 170 cm and sd 10 cm. What fraction is taller than 185? What height marks the 90th percentile?

Problem 12. A random variable X takes values 0, 1, 2 with probabilities 0.5, 0.3, 0.2. Find E[X], Var(X) and the sd.

Python Solutions for Part C

Press Run (or Ctrl + Enter) to see the result here.

Program input ยท what you'd type while the program runs

Type the answers before you press Run, one per line. Each time the program reads a line (with input()), it gets the next line from this box.

For Problem 10 note the rate scales with the interval: in 30 minutes the mean is 2, not 4. For Problem 11, 185 cm is 1.5 standard deviations above the mean, which leaves about 6.7% in the upper tail.

How to use these problems

  • Re-solve any problem you missed without looking at the solution a few days later.
  • Change the numbers (different prevalence in Problem 7, different p in Problem 9) and predict how the answer moves before running.
  • Explain each solution in one sentence in your own words; if you cannot, revisit the topic.

Check your understanding

Quick check ยท 4 questions

of 4 answered You scored / 4 ยท perfect!

  1. 1. A data set has one extreme outlier. Which pair of summaries is most robust?

    The median and IQR depend only on the middle of the ordered data, so one extreme value barely changes them.
  2. 2. A disease has prevalence 1%, and the test has 95% sensitivity and 90% specificity. Why is P(disease | positive) so low?

    Roughly 990 healthy people test positive versus 95 sick people, so only about 9% of positives are real.
  3. 3. If calls arrive at 4 per hour on average, what is the Poisson mean for a 30-minute window?

    The Poisson rate scales with the length of the interval: 4 per hour is 2 per half hour.
  4. 4. Ann scores z = 2.0 and Cara z = 2.4 in different classes. What does that tell you?

    z-scores measure distance from each group's mean in standard deviations, enabling comparison across groups.

Summary

  • Use the median and IQR when data are skewed or have outliers; z-scores compare standing across different scales.
  • Enumerate small sample spaces to check probability reasoning; use counting formulas for larger ones.
  • Bayes' theorem with a rare condition gives surprisingly low posterior probabilities.
  • Match the problem to a distribution: binomial for counts of successes, Poisson for events per interval, normal for continuous bell-shaped data.

Next: Practice Set: Distributions and Inference