UN Statistical Institute for Asia and the Pacific (SIAP) training

Asia-Pacific · United Nations ESCAP - SIAP · professional · unverified source

68practice questions written to this syllabus
5subjects

Format

Courses and e-learning for national statistical office staff; certificates on completion.

Sections

Over the years

Built from Laisha's knowledge because the official page could not be opened or was not found during research (web search quota exhausted); confirm against the body's current notification before relying on it.

Official source: https://www.unsiap.or.jp/

Subjects this exam draws on

Agriculture for Statisticians14 questionsAgricultural Statistics System, Census & Official Statistics21 questionsIndex Numbers, National Accounts & Agricultural Economic Statistics17 questionsStatistical & Machine Learning for Agriculture11 questionsDatabases, Big Data & Agricultural Information Systems5 questions

Five practice questions, worked

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

1. Which statement about world aquatic animal production is consistent with FAO's fisheries reports?

  1. Aquaculture has grown fast and now supplies about half, while capture has been roughly flat
  2. Capture fisheries have roughly doubled since 2000, while aquaculture output has declined sharply
  3. Aquaculture supplies under 5% of aquatic animal food, almost all of it farmed in Europe
  4. Capture fisheries and aquaculture have both fallen steadily every year since about 1990
Answer and working

A. Aquaculture has grown fast and now supplies about half, while capture has been roughly flat

Capture production has been broadly stable for decades; aquaculture, mostly in Asia, has expanded rapidly and now provides about half of aquatic animal production.

Agriculture for Statisticians · Importance of agriculture, forestry, livestock and fisheries in national economies

2. In FAO land-use statistics, cropland consists of:

  1. Forest land plus permanent crops
  2. Arable land plus permanent crops
  3. Arable land plus permanent pastures
  4. Net sown area plus current fallows only
Answer and working

B. Arable land plus permanent crops

Agricultural land = cropland (arable + permanent crops) + permanent meadows and pastures.

Agricultural Statistics System, Census & Official Statistics · Land-use statistics and the nine-fold classification

3. By the Bortkiewicz relation, the Paasche price index falls below the Laspeyres price index when which condition holds?

  1. Price relatives and quantity relatives are negatively correlated
  2. Price relatives and quantity relatives are positively correlated
  3. All price relatives are equal across commodities
  4. Base-period expenditure shares are all equal
Answer and working

A. Price relatives and quantity relatives are negatively correlated

P/L - 1 equals the weighted covariance of price and quantity relatives divided by the product of the Laspeyres price and quantity indices; a negative covariance (buyers substitute away from goods whose prices rise most) gives P < L. If all price relatives are equal, P = L exactly.

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

4. Predictors are standardised using the mean and standard deviation of the whole data set before it is split into training and test sets. What is the problem?

  1. Information from the test set leaks into training
  2. The test set becomes larger than the training set
  3. Standardised predictors cannot be used for prediction
  4. Standardisation is never allowed for regression models
Answer and working

A. Information from the test set leaks into training

Any step that learns from data, including standardisation, imputation and feature selection, must be fitted on training data only and then applied to test data; otherwise test performance is optimistic.

Statistical & Machine Learning for Agriculture · Supervised learning and the bias-variance trade-off

5. The international standard for exchanging statistical data and metadata between agencies is:

  1. HTML
  2. SDMX
  3. ISO 9001
  4. MQTT
Answer and working

B. SDMX

It is sponsored by FAO, IMF, OECD, World Bank and Eurostat, among others.

Databases, Big Data & Agricultural Information Systems · APIs, open-data portals and data standards (e.g. FAOSTAT, national portals)

Practise it, and prove it

These notes are free to read here, with no account.

What the Laisha app adds:

Free for ten days, then a subscription. We would rather write that here than have you find it later.

Open Laisha →