LAISHA
Open Laisha

UK Government Statistician Group (GSG) badging

United Kingdom · Government Statistical Service / Office for National Statistics

24practice questions written to this syllabus
2subjects

What UK Government Statistician Group badging is

UK Government Statistician Group (GSG) badging is a government recruitment exam run by Government Statistical Service / Office for National Statistics, for candidates in United Kingdom.

Format

Badging exercise for statisticians and data scientists entering government (assessment of qualifications and competence; recruitment centres include tests and interviews).

Sections

How it has changed

Read on the Government Analysis Function page: GSG members are statisticians who have passed the GSG badging exercise. Defra statisticians produce UK agricultural statistics.

How to prepare for UK Government Statistician Group badging

Where our 24 questions for it fall

Our reading of the syllabus, from the questions we have written to this exam; the exam body's own weighting, where published, is under Format above.

  1. Heaviest (54% of the questions): Exploratory Data Analysis & Statistical Graphics (13).

    Start here: read these subjects' manuals first and work their questions until the reasoning is automatic.

  2. Middle band: Index Numbers, National Accounts & Agricultural Economic Statistics (11).

    One pass per subject, then mixed sets across them.

  3. Hardest share: Index Numbers, National Accounts & Agricultural Economic Statistics (1 hard of 11).

    Leave untimed time for these and read every explanation, including for the options you rejected.

Official source: analysisfunction.civilservice.gov.uk

8 practice questions, worked

Original questions written to this exam's published syllabus and pattern. Not past papers.

1. A histogram of cow weights from a household survey shows tall spikes at every multiple of 5 kg. What does this indicate?

  1. The weights follow a Poisson distribution
  2. Heaping: many weights were estimated or rounded to 5 kg
  3. The bin width is too wide for the data and should be increased further
  4. The weights follow a Poisson distribution, which produces regular spikes
Answer and working

B. Heaping: many weights were estimated or rounded to 5 kg

Spikes at round numbers are digit preference or heaping, a measurement feature. It affects precision and must be noted before modelling; narrower bins reveal it rather than cause it.

Exploratory Data Analysis & Statistical Graphics · Histograms, density estimates and quantile-quantile plots

2. A bar chart shows treatment means with error bars, but the caption does not say what the bars are. Why is this a serious omission?

  1. Error bars must always be standard deviations, so the caption would be redundant
  2. Readers can always work out the type of bar from its length relative to the mean
  3. Error bars are decorative and should simply be omitted from published charts
  4. SD, SE, CI and LSD bars differ in length, so overlap means nothing
Answer and working

D. SD, SE, CI and LSD bars differ in length, so overlap means nothing

The SE is the SD divided by √r, and a 95% interval is roughly twice the SE; an LSD is longer again. Without the caption, readers cannot tell what overlap means.

Exploratory Data Analysis & Statistical Graphics · Graphics for designed experiments: interaction plots and residual plots

3. Between two years the value of sales of a farm product group rose by 40% and the Fisher price index is 125. Using the factor reversal property, what is the Fisher quantity index?

  1. 115
  2. 175
  3. 88
  4. 112
Answer and working

D. 112

Fisher satisfies factor reversal: P x Q = V, so Q = 1.40/1.25 = 1.12, i.e. 112. 115 subtracts percentages (140 - 125 + 100); 175 multiplies; 88 is 1.10/1.25 from a misreading of the value change.

Index Numbers, National Accounts & Agricultural Economic Statistics · Tests of index numbers: time reversal, factor reversal and circularity

4. Production doubles, and a pictogram shows this by doubling both the height and width of a grain sack. By what factor does the sack's area grow?

  1. 2
  2. 8
  3. √2
  4. 4
Answer and working

D. 4

Doubling both dimensions multiplies the area by 2 × 2 = 4, giving a lie factor of 2. If drawn as a solid in perspective, perceived volume can suggest 8.

Exploratory Data Analysis & Statistical Graphics · Graphical perception and honest chart design

5. A table reports 'percentage of farmers adopting' without stating the base. Why is this a problem?

  1. Percentages must always be reported to two decimal places
  2. Adoption should be reported as a ratio and never as a percentage
  3. Readers cannot tell what group or how many respondents it covers
  4. Percentages above 50 cannot be interpreted at all without a base
Answer and working

C. Readers cannot tell what group or how many respondents it covers

A percentage needs its denominator (all farmers, or only those who heard of the technology) and the unweighted number of respondents, which determines its precision.

Exploratory Data Analysis & Statistical Graphics · Tables for reports and publications

6. A value index between periods 0 and 1 is defined as

  1. sum p1 q0 / sum p0 q0 x 100
  2. sum p1 q1 / sum p0 q0 x 100
  3. sum p1 q1 / sum p0 q1 x 100
  4. sum q1 p0 / sum q0 p0 x 100
Answer and working

B. sum p1 q1 / sum p0 q0 x 100

A value index compares total expenditure, so both prices and quantities change. sum p1 q0 / sum p0 q0 is the Laspeyres price index, sum p1 q1 / sum p0 q1 the Paasche price index and sum q1 p0 / sum q0 p0 the Laspeyres quantity index.

Index Numbers, National Accounts & Agricultural Economic Statistics · Index numbers: Laspeyres, Paasche, Fisher and Marshall-Edgeworth

7. Quintile shares of income, from poorest to richest, are 6%, 10%, 14%, 22% and 48%. Using the trapezoidal formula, what is the Gini coefficient?

  1. 0.616
  2. 0.420
  3. 0.384
  4. 0.480
Answer and working

C. 0.384

Cumulative shares are 0.06, 0.16, 0.30, 0.52, 1.00. G = 1 - 0.2 x (0.06 + 0.22 + 0.46 + 0.82 + 1.52) = 1 - 0.2 x 3.08 = 0.384. 0.616 is the area term itself, not the Gini; 0.480 is the top share.

Index Numbers, National Accounts & Agricultural Economic Statistics · Inequality measures: Lorenz curve and Gini coefficient

8. Two commodities: A has p0 = 10, q0 = 5, p1 = 12, q1 = 6; B has p0 = 8, q0 = 10, p1 = 10, q1 = 8. Computing the Laspeyres index forward (0 to 1) and backward (1 to 0, using period-1 quantities as base weights), what is the product of the two ratios?

  1. 1.0000
  2. 1.2308
  3. 1.0040
  4. 1.5087
Answer and working

C. 1.0040

Forward: sum p1 q0 / sum p0 q0 = 160/130 = 1.2308. Backward: sum p0 q1 / sum p1 q1 = 124/152 = 0.8158. Product = 1.0040, not 1, so Laspeyres fails time reversal. 1.0000 is what Fisher would give.

Index Numbers, National Accounts & Agricultural Economic Statistics · Tests of index numbers: time reversal, factor reversal and circularity

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 all 24 questions — UK Government Statistician Group (GSG) badging

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

  • Every practice question for this course, with explanations
  • Timed papers for the exams this course leads to
  • Ask Laisha to explain any topic — 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.