LAISHA
Open Laisha

SAS statistical certifications Exploratory Data Analysis & Statistical Graphics: practice questions

SAS statistical certifications (Statistical Business Analyst, Applied Statistics Associate, Statistics for Machine Learning) · USA / global · SAS Institute

Original practice questions written to the published syllabus · not past papers
10worked here, free
54written to this exam in this subject
9syllabus units

About SAS statistical certifications

SAS statistical certifications (Statistical Business Analyst, Applied Statistics Associate, Statistics for Machine Learning) is a professional certification run by SAS Institute, for candidates worldwide. Proctored online or test-centre exams per credential.

Source: sas.com.

Checked against the exam body's published information. Formats and fees change; confirm the current edition there before you book.

Exploratory Data Analysis & Statistical Graphics in SAS statistical certifications

Looking at data before modelling it: summaries, robust statistics, graphs that show distributions and relationships honestly, outlier detection, and the tidy-data and reporting habits that make an analysis checkable. Deliberately practical and software-based.

Our 54 SAS statistical certifications questions in this subject: 12 easy, 29 medium, 13 hard, across 9 units.

10 practice questions, worked

Choose an answer, then open the working. Each explanation says why the right answer is right and why the others are not.

These 10 were written to SAS statistical certifications and are not shown on any other exam's page.

Question 1 · easy

A yield table has columns Variety, 2021, 2022 and 2023. What is untidy about it?

  1. Variety should be stored as a row, not a column
  2. Yields should be stored as text to avoid rounding
  3. Three years of yields cannot be held in one table
  4. Column headers are values of a hidden variable, year
Answer and working

D. Column headers are values of a hidden variable, year

2021-2023 are values of the variable year. Pivoting longer gives columns Variety, Year and Yield, one row per variety-year.

Question 2 · medium

A farm table (one row per farm, 200 farms) is left-joined to a sampling-weight table, and the result has 214 rows. What is the most likely cause?

  1. Fourteen farms had no weight and were dropped
  2. Farm identifiers are duplicated in the weight table
  3. The left join always adds one extra row for every missing value it encounters
  4. The weight table has 14 fewer farms than the farm table, so rows were padded
Answer and working

B. Farm identifiers are duplicated in the weight table

A left join keeps every left-table row once per matching right-table row. Duplicated keys in the right table multiply rows; unmatched farms would get missing weights, not extra rows.

Question 3 · medium

A robust estimate of the SD of normally distributed data is obtained from the MAD by multiplying it by which constant?

  1. 1.4826
  2. 0.6745
  3. 1.349
  4. 1.96
Answer and working

A. 1.4826

For normal data MAD ≈ 0.6745σ, so σ ≈ MAD/0.6745 = 1.4826 MAD. 1.349 is the ratio IQR/σ for the normal.

Question 4 · medium

Anscombe's quartet consists of four data sets that share which property?

  1. The same means, variances, correlation and least-squares line, despite very different scatterplots
  2. The same scatterplot pattern but very different correlations and means
  3. The same correlation only, with differing means and regression lines
  4. The same sample size of 50 and identical residual plots
Answer and working

A. The same means, variances, correlation and least-squares line, despite very different scatterplots

Each set has x̄ = 9, ȳ = 7.5, r ≈ 0.816 and line ŷ = 3 + 0.5x, yet one is linear, one curved, one has an outlier and one is driven by a single high-leverage point. Hence: always plot.

Question 5 · hard

A regression with an intercept and two predictors is fitted to 40 observations. Above what leverage hᵢᵢ is a point commonly flagged by the 2p/n rule?

  1. 0.15
  2. 0.075
  3. 0.10
  4. 0.50
Answer and working

A. 0.15

p = 3 parameters; average leverage p/n = 0.075; the flag is twice that, 2p/n = 0.15.

Question 6 · medium

Groups of yields show SD proportional to the mean (s ∝ m¹). Using the rule that y^(1 − b) stabilises variance when s ∝ mᵇ, which transformation is indicated?

  1. Square root
  2. Reciprocal
  3. No transformation
  4. Logarithm
Answer and working

D. Logarithm

1 − b = 0, and the zero power in the ladder is the logarithm. b = 0.5 gives the square root; b = 2 the reciprocal.

Question 7 · hard

A plot of log(group SD) against log(group mean) for counts in several treatments has slope about 2. Which transformation does this suggest?

  1. Reciprocal, y⁻¹
  2. Logarithm
  3. Square root
  4. Square, y²
Answer and working

A. Reciprocal, y⁻¹

The slope estimates b; the power is 1 − b = −1, the reciprocal. Slope 1 would suggest log, 0.5 the square root.

Question 8 · hard

On the natural-log scale, the difference between two treatment means is 0.693. What does this mean on the original scale?

  1. The arithmetic means differ by 0.693 units
  2. The geometric mean of one treatment is twice that of the other
  3. The treatments differ by 69.3% in arithmetic means
  4. The variances of the two treatments differ by a factor of 0.693
Answer and working

B. The geometric mean of one treatment is twice that of the other

Differences on the log scale are ratios on the original scale: e^0.693 = 2. Back-transformed means are geometric means, so the ratio applies to them.

Question 9 · hard

A chart shows exports rising from 10 to 20 units, but the drawn bar grows from 1 cm to 4 cm. What is Tufte's lie factor?

  1. 2
  2. 3
  3. 4
  4. 1
Answer and working

B. 3

Effect shown = (4 − 1)/1 = 300% increase; effect in data = (20 − 10)/10 = 100%. Lie factor = 3.00/1.00 = 3. 4 is the ratio of bar lengths, not of changes.

Question 10 · easy

What does Tufte's data-ink ratio recommend?

  1. Graphs should be printed with as little ink as possible, including labels
  2. Each data point should be drawn with a distinct colour
  3. Most of the ink in a graphic should represent data, not decoration
  4. Gridlines should be darker than the data
Answer and working

C. Most of the ink in a graphic should represent data, not decoration

Remove chartjunk (3-D effects, heavy gridlines, background images) but keep essential ink: labels, units, sample sizes and the meaning of error bars.

A study plan for Exploratory Data Analysis & Statistical Graphics in SAS statistical certifications

This plan follows where our questions actually fall, so the time goes where the marks are likely to be. It is our reading of the syllabus, not the exam body's weighting.

  1. First, the heavy units (48% of the 54 questions): Histograms, density estimates and quantile-quantile plots (9, 17%); Scatterplots, smoothing (LOESS) and scatterplot matrices (9, 17%); Graphical perception and honest chart design (8, 15%).

    Read the manual chapters for these first and do every worked question you can find on them.

  2. Then the middle band: Five-number summaries, box plots and robust statistics (median, MAD, trimmed means) (7, 13%); Outliers and influential observations (7, 13%); Transformations to symmetry and constant variance (6, 11%).

    Aim for one sitting per unit, then mixed questions across them.

  3. Then the lighter units: Tidy data: variables, observations and tables (5, 9%); Types of data and measurement scales (2, 4%); Tables for reports and publications (1, 2%).

    Learn the definitions, classifications and standard numbers; these units are more often recalled than worked.

  4. Leave time for the hard ones: Outliers and influential observations (4 hard of 7), Transformations to symmetry and constant variance (2 hard of 6), Five-number summaries, box plots and robust statistics (median, MAD, trimmed means) (2 hard of 7).

    Come back to these after a first pass, untimed, and read every explanation, including for the options you rejected.

  5. Bank the easy marks: Types of data and measurement scales (1 easy of 2); Tidy data: variables, observations and tables (2 easy of 5).

    Do these early in revision so they are fast on the day.

  6. Finish timed. Sit the subject as a timed set without notes, mark it, and send each wrong answer back to its unit above.

Last updated · How Laisha writes and checks its pages · Report a mistake

Ask Laisha about this

Opens Laisha's chat with your question ready to send. Sign in or start free.

Unlock every question — SAS statistical certifications Exploratory Data Analysis & Statistical Graphics

US$10 a month · one price worldwide · cancel any time

  • Every practice question in this subject, with full working
  • Timed exam papers and progress by unit
  • Ask Laisha to explain any answer — up to 1,000 questions a month
Free or Smarter
FreeSmarter
Grow guides, pest pages, articlesRead allRead all
Ask Laisha5 a dayUp to 1,000 a month
Exam practiceThe sample on each pageEvery question, timed papers
Crop calendar and pest alerts—For your own fields
Calculators and tools—All
Uploads and reports—100 a month, real files
10 days free for every new account, no card.