Skip to content
ContentLora

    Tip: press / anywhere to search.

    Explainer

    How official statistics are produced: surveys, rules and revisions

    Official statistics are figures such as GDP, unemployment and income that government statistical agencies compile from surveys and administrative records, choosing sources by quality, timeliness, cost and the burden on respondents.[1] UN principles endorsed by the General Assembly in 2014 say agencies should work impartially, choose methods on professional grounds and keep individual data confidential.[2][3][4][5] In the US, a 2024 federal rule requires recognized statistical agencies to publish release calendars in advance and to stay functionally separate from policymaking and enforcement work.[6][7][8]

    Editor reviewedUpdated Explainer20 claims · 100% primaryStatistics and evidence, Economy and trade

    This page describes the general principles and US rules behind official statistics. Individual surveys, such as the CPI or the jobs report, have their own methods; follow the links for those.

    Official statistics are the numbers governments publish about the economy, population, society and environment: GDP, inflation, unemployment, household income and many more. UN principles say official statistics that meet the test of practical utility should be made available impartially, to honour citizens’ entitlement to public information.[3] This page explains where the numbers come from, the rules agencies follow, and why figures change after they are first published.

    Where the data come from

    The UN Fundamental Principles of Official Statistics say data for statistical purposes may come from all types of sources, whether statistical surveys or administrative records, and that agencies should choose the source with regard to quality, timeliness, cost and the burden on respondents.[1]

    • Surveys ask a sample of households or businesses for information. In the US, approved federal surveys carry an official OMB control number, shown on the form or available from the interviewer.[9] How a sample can represent a whole population is covered in how opinion polls work and how surveys are weighted.
    • Administrative records are the other main type of source the UN principles name alongside surveys.[1]

    Agencies also follow shared definitions. The UN principles say using international concepts, classifications and methods promotes consistency between countries’ statistical systems.[10]

    The principles agencies work to

    The UN principles were endorsed by the UN General Assembly in resolution 68/261 of 29 January 2014.[2] Among them:

    • Professional independence. Agencies should decide their methods for collecting, processing, storing and presenting data on strictly professional grounds, including scientific principles and professional ethics.[4]
    • Transparency and misuse. Agencies should publish information on their sources, methods and procedures, and are entitled to comment on erroneous interpretation and misuse of their statistics.[11]
    • Confidentiality. Individual data collected by statistical agencies are to be strictly confidential and used only for statistical purposes.[5]

    Countries turn these ideas into their own rules. In the UK, the Code of Practice for Statistics sets the standards that producers of official statistics should commit to, covering public value, quality and trustworthiness.[12]

    The US rules

    In the US, a federal rule, 5 CFR part 1321, sets out the fundamental responsibilities of the recognized statistical agencies and units. From December 10, 2024 it supersedes any guidance or Statistical Policy Directives that conflict with it.[6] Each agency must produce relevant and timely statistics, conduct credible, accurate and objective statistical activities, and ensure that confidential statistical data are kept confidential and used only for statistical purposes.[13] The rule defines objective as accurate, clear, complete and unbiased.[14]

    Several of its requirements are visible to the public:

    • Release calendars. Each agency must publicly announce and keep to a release schedule, publishing the dates of its regular releases for the next calendar year before that year begins.[7]
    • Separation from policy. Agencies must keep functional separation from administrative, regulatory, law enforcement and policymaking functions, including exclusive authority over who can access their confidential data.[8]
    • Quality information. Agencies are expected to provide indicators of data quality so users can judge whether the data are fit for their own purposes.[15]

    Estimates, uncertainty and revisions

    Most official figures are estimates. UK government guidance describes uncertainty as coming from measurement or sampling error in surveys and from other sources of bias and variance in a data source.[16] UK guidance on communicating uncertainty recommends showing confidence intervals where applicable, and warns that changes between periods can fall within survey error and random variation.[17]

    Figures also change after first publication. The same guidance distinguishes scheduled revisions, which add data that were not available at first publication, from unscheduled corrections of errors found afterwards.[18] US GDP is a clear example: BEA estimates each quarter’s GDP three times, starting with an advance estimate about a month after the quarter ends, and the second and third estimates add source data that were not available earlier.[19] Seasonally adjusted figures for the most recent periods can also be revised, because the filters used have too little data at the end of a series; see the seasonal adjustment explainer.[20]

    How to use official statistics well

    • Check the release calendar and the date of the figure you are quoting.[7]
    • Read the methods and quality notes that agencies publish alongside the numbers.[11][15]
    • Expect revisions to the latest periods, especially for early estimates such as advance GDP.[18][19]
    • Look for the uncertainty before treating a small change as a trend.[17]

    Next in the crash course

    Questions readers ask

    Where does the data for official statistics come from?

    The UN principles say it may come from statistical surveys or administrative records, and agencies should choose the source with regard to quality, timeliness, cost and the burden on respondents.[1]

    Are my answers to a government survey kept confidential?

    The UN principles say individual data collected by statistical agencies are to be strictly confidential and used only for statistical purposes. US rules require recognized statistical agencies to keep functional separation from administrative, regulatory, law enforcement and policymaking functions, including exclusive authority over access to their confidential data.[5][8]

    How can I tell if a US federal survey is genuine?

    Approved federal surveys carry an official OMB control number, which must be shown on the survey form or be available by asking the interviewer.[9]

    Why are release dates announced so far ahead?

    US rules require each recognized statistical agency to publicly announce and keep to a release schedule, publishing the dates of its regular releases for the next calendar year before that year begins.[7]

    Why do official figures get revised?

    Scheduled revisions add data that were not available for the first publication, while unscheduled corrections fix errors found later. BEA, for example, estimates each quarter's GDP three times as more source data arrive.[18][19]

    Sources

    · 20 claims from 7 publishers

    Each numbered claim is a statement we checked against the sources listed with it. Tap a number in the text to see its sources in place.

    1. [1]

      The UN principles say data for official statistics may come from statistical surveys or administrative records, chosen with regard to quality, timeliness, cost and the burden on respondents. confirmedas of 2026-11-14

    2. [2]

      The UN Fundamental Principles of Official Statistics were endorsed by the UN General Assembly in resolution 68/261 of 29 January 2014. confirmedas of 2026-11-14

    3. [3]

      The first UN principle says official statistics that meet the test of practical utility are to be compiled and made available impartially, to honour citizens' entitlement to public information. confirmedas of 2026-11-14

    4. [4]

      The UN principles say statistical agencies should choose their methods for collecting, processing, storing and presenting data on strictly professional grounds, including scientific principles and professional ethics. confirmedas of 2026-11-14

    5. [5]

      The UN principles say individual data collected by statistical agencies are to be strictly confidential and used only for statistical purposes. confirmedas of 2026-11-14

    6. [6]

      A federal rule, 5 CFR part 1321, sets out the fundamental responsibilities of recognized US statistical agencies and units; from December 10, 2024 it supersedes any guidance or Statistical Policy Directives to the extent that they conflict with it. confirmedas of 2026-11-14

    7. [7]

      Each recognized US statistical agency must publicly announce and keep to a release schedule, publishing the dates of its regular releases for the next calendar year before that year begins. confirmedas of 2026-11-14

    8. [8]

      The rule requires a recognized statistical agency to keep functional separation from administrative, regulatory, law enforcement and policymaking functions, including by keeping exclusive authority over access to its confidential data. confirmedas of 2026-11-14

    9. [9]

      Approved federal surveys carry an official OMB control number, which must be shown on the survey form or be available from the interviewer. confirmedas of 2026-11-14

    10. [10]

      The UN principles say using international concepts, classifications and methods promotes consistency between statistical systems. confirmedas of 2026-11-14

    11. [11]

      Under the UN principles, agencies should publish information on their sources, methods and procedures, and are entitled to comment on erroneous interpretation and misuse of their statistics. confirmedas of 2026-11-14

    12. [12]

      In the UK, the Code of Practice for Statistics sets the standards that producers of official statistics should commit to, covering public value, quality and trustworthiness. confirmedas of 2026-11-14

    13. [13]

      Under 5 CFR part 1321, each recognized US statistical agency must produce relevant and timely statistics, conduct credible, accurate and objective statistical activities, and protect the trust of information providers by ensuring the confidentiality and exclusive statistical use of confidential statistical data. confirmedas of 2026-11-14

    14. [14]

      The rule defines objective, for statistical activities, as accurate, clear, complete and unbiased. confirmedas of 2026-11-14

    15. [15]

      The rule expects statistical agencies to provide indicators of data quality that let users judge whether the data are fit for their own purposes. confirmedas of 2026-11-14

    16. [16]

      The same guidance describes uncertainty in a statistic as coming from measurement or sampling error in surveys and from other sources of bias and variance in a data source. confirmedas of 2026-11-14

    17. [17]

      UK government guidance on communicating uncertainty recommends showing confidence intervals around estimates where applicable, and warns that changes between periods can fall within survey error and random variation, especially in weekly, monthly or quarterly series. confirmedas of 2026-11-14

    18. [18]

      UK government guidance distinguishes scheduled revisions, which add data unavailable at first publication, from unscheduled corrections of errors found after publication. confirmedas of 2026-11-14

    19. [19]

      BEA estimates each quarter's GDP three times; the advance estimate comes about a month after the quarter ends, and the second and third estimates add source data that were not available earlier. confirmedas of 2026-11-14

    20. [20]

      Moving-average filters lack enough data at the end of a series (the end-point problem), and extending the series with ARIMA forecasts helps reduce later revisions to the seasonally adjusted figures. confirmedas of 2026-11-14

    Revision history (1)
    1. Page created.

    Created Nov 14, 2026. Last reviewed by an editor on Nov 14, 2026. Next scheduled review: Aug 11, 2027.

    Cite this page

    "How official statistics are produced: surveys, rules and revisions." ContentLora, updated Nov 14, 2026. https://contentlora.com/explain/how-official-statistics-are-produced

    Spotted an error? Suggest a correction or emailcorrections@contentlora.com.