Daily 5 - Feb 2

Class Performance

Students: 106 | Mean: 3.74 | Median: 4 | SD: 0.79

Scores ranged from 2 to 5 out of 5 points.

Score Distribution

Performance by Question

Questions

Q1: Write the formal definition of expected value

E(Y) = Σ p_j y_j — The expected value is the sum of each possible value multiplied by its probability.

  • Missing summation notation — Writing “p·y” without the Σ symbol. The formula requires summation over all values.
  • Wrong operator — Using multiplication (×) instead of summation (Σ) between terms.
  • Conceptual only — Describing “weighted average” without writing the mathematical formula requested.

Q2: Write the formal definition of variance

Var(Y) = Σ p_j(y_j − μ_y)² — The variance is the sum of probability-weighted squared deviations from the mean.

  • Wrote expected value instead — Many students repeated the E(Y) formula. Variance measures spread, not center.
  • Missing squared term — Writing (y_j − μ) without squaring. The squared term is essential to variance.
  • Wrote sample mean formula — Ȳ = (1/n)Σy_i is sample mean, not variance.
  • Conceptual description only — “Average distance from mean” is incomplete; variance uses squared deviations.

Q3: The gender wage gap percentage from the Uber study

7% — The overall gender wage gap documented by the Uber study authors and reported in the Freakonomics podcast.

  • Wrong percentages — Common incorrect answers included 8%, 18%, 19%, 25%, 30%, 35%. The exact figure was 7%.
  • Confusing with other statistics — Some wrote wage gaps from other studies or contexts.
  • Left blank — This was a recall question from the podcast material.

Q4: Explain the filter function without using “filter”

The code keeps/restricts to individuals where age is between 23 and 62 — selecting working-age adults for the “defining a career” analysis.

  • Used prohibited word “filter” — The question specifically asked to explain without using that word. Use “keeps,” “restricts,” or “selects.”
  • Vague about age bounds — Saying “restricts by age” without specifying the exact range (23-62).
  • Wrong age bounds — Some wrote 26 or 40 as the upper bound instead of 62.

Q5: Random sampling — one draw ___ depend on another

does not — The key idea behind random sampling is that one draw from the population does not depend on another (independence).

  • Very few errors — This was the best-performing question with near-perfect scores.
  • Writing “does” instead of “does not” — Random sampling requires observations to be independent.

Key Takeaways

Strengths: Expected value formula, random sampling independence concept, understanding of wage gap research.

Review:

  • Variance formula — Var(Y) = Σp_j(y_j − μ)² requires the squared deviation term
  • Uber wage gap = 7% — From the Freakonomics podcast assigned listening
  • Code interpretation — Be precise about what code does (ages 23-62), and follow question instructions (don’t use prohibited words)