5.12.1: Review Questions
- Page ID
- 58305
\( \newcommand{\vecs}[1]{\overset { \scriptstyle \rightharpoonup} {\mathbf{#1}} } \)
\( \newcommand{\vecd}[1]{\overset{-\!-\!\rightharpoonup}{\vphantom{a}\smash {#1}}} \)
\( \newcommand{\dsum}{\displaystyle\sum\limits} \)
\( \newcommand{\dint}{\displaystyle\int\limits} \)
\( \newcommand{\dlim}{\displaystyle\lim\limits} \)
\( \newcommand{\id}{\mathrm{id}}\) \( \newcommand{\Span}{\mathrm{span}}\)
( \newcommand{\kernel}{\mathrm{null}\,}\) \( \newcommand{\range}{\mathrm{range}\,}\)
\( \newcommand{\RealPart}{\mathrm{Re}}\) \( \newcommand{\ImaginaryPart}{\mathrm{Im}}\)
\( \newcommand{\Argument}{\mathrm{Arg}}\) \( \newcommand{\norm}[1]{\| #1 \|}\)
\( \newcommand{\inner}[2]{\langle #1, #2 \rangle}\)
\( \newcommand{\Span}{\mathrm{span}}\)
\( \newcommand{\id}{\mathrm{id}}\)
\( \newcommand{\Span}{\mathrm{span}}\)
\( \newcommand{\kernel}{\mathrm{null}\,}\)
\( \newcommand{\range}{\mathrm{range}\,}\)
\( \newcommand{\RealPart}{\mathrm{Re}}\)
\( \newcommand{\ImaginaryPart}{\mathrm{Im}}\)
\( \newcommand{\Argument}{\mathrm{Arg}}\)
\( \newcommand{\norm}[1]{\| #1 \|}\)
\( \newcommand{\inner}[2]{\langle #1, #2 \rangle}\)
\( \newcommand{\Span}{\mathrm{span}}\) \( \newcommand{\AA}{\unicode[.8,0]{x212B}}\)
\( \newcommand{\vectorA}[1]{\vec{#1}} % arrow\)
\( \newcommand{\vectorAt}[1]{\vec{\text{#1}}} % arrow\)
\( \newcommand{\vectorB}[1]{\overset { \scriptstyle \rightharpoonup} {\mathbf{#1}} } \)
\( \newcommand{\vectorC}[1]{\textbf{#1}} \)
\( \newcommand{\vectorD}[1]{\overrightarrow{#1}} \)
\( \newcommand{\vectorDt}[1]{\overrightarrow{\text{#1}}} \)
\( \newcommand{\vectE}[1]{\overset{-\!-\!\rightharpoonup}{\vphantom{a}\smash{\mathbf {#1}}}} \)
\( \newcommand{\vecs}[1]{\overset { \scriptstyle \rightharpoonup} {\mathbf{#1}} } \)
\(\newcommand{\longvect}{\overrightarrow}\)
\( \newcommand{\vecd}[1]{\overset{-\!-\!\rightharpoonup}{\vphantom{a}\smash {#1}}} \)
\(\newcommand{\ket}[1]{\left| #1 \right>}\)
\(\newcommand{\bra}[1]{\left< #1 \right|}\)
\(\newcommand{\braket}[2]{\left< #1 \vphantom{#2} \right| \left. #2 \vphantom{#1} \right>}\)
\(\newcommand{\braopket}[3]{\left< #1 \vphantom{#2}\vphantom{#3} \right| #2 \vphantom{#1}\vphantom{#3} \left| #3 \vphantom{#1}\vphantom{#2} \right>}\)
\(\newcommand{\qmvec}[1]{\mathbf{\vec{#1}}}\)
\(\newcommand{\op}[1]{\hat{\mathbf{#1}}}\)
\(\newcommand{\expect}[1]{\langle #1 \rangle}\)
\(\newcommand{\dfn}[1]{\emph{\textbf{#1}}}\)
Review Questions
Multiple Choice
-
In EDA, the "1.5 × IQR rule" is commonly used to:
-
a) Calculate the mean b) Detect outliers c) Normalize data d) Measure correlation
-
-
A right-skewed distribution typically has:
-
a) Mean < Median b) Mean = Median c) Mean > Median d) No defined mean
-
-
Which EDA visualization is best for examining pairwise relationships among many numeric variables at once?
-
a) Pie chart b) Scatter plot matrix (pair plot) c) Bar chart d) Histogram
-
Short Answer
-
Explain the difference between exploratory and confirmatory analysis. Why should EDA come before confirmatory analysis in a project?
-
Describe how you would conduct a univariate analysis of a numeric variable (e.g., customer age). What statistics would you compute and what visualizations would you create?
-
What does a correlation coefficient of r = -0.85 tell you? What does it NOT tell you? Explain why "correlation does not imply causation."
-
You create a scatter plot of total bill vs. tip amount and notice the points "fan out" as bills increase. What is this pattern called, and why does it matter for analysis?
True/False
-
True or False: A box plot can reveal the median, spread, skewness, and outliers of a distribution in a single visualization.
-
True or False: If two variables have a Pearson correlation of 0.02, they definitely have no relationship of any kind.
-
True or False: EDA is only useful for small datasets; large datasets should skip straight to modeling.
Answer Key:
1-b, 2-c, 3-b, 4. Exploratory: open-ended discovery of patterns without hypotheses. Confirmatory: testing specific hypotheses with statistical tests. EDA first ensures you understand data properties, catch quality issues, and form well-grounded hypotheses before confirmatory analysis validates them. 5. Statistics: mean, median, mode, std dev, min/max, quartiles, IQR. Visualizations: histogram (distribution shape), box plot (spread/outliers). Check for skewness, outliers, multimodality. 6. Strong negative linear relationship — as one increases, the other tends to decrease. Does NOT tell you one causes the other; a third variable could drive both (confounding). Correlation measures association, not causation. 7. Heteroscedasticity — variance of residuals increases with the predictor. Matters because it violates assumptions of linear regression and can affect model reliability and confidence intervals. 8. True, 9. False (could have a strong nonlinear relationship), 10. False.