1. Output information

 National Statistic   
 Survey name   Labour Force Survey
 Data collection   Labour Force Survey data
 Frequency   Annual
 How compiled   Based on respondent data
 Geographic coverage   UK
 Related publications   Internet access – households and individuals

Back to table of contents

2. About this Quality and Methodology Information report

This quality and methodology report contains information on the quality characteristics of the data (including the European Statistical System five dimensions of quality) as well as the methods used to create it.

The information in this report will help you to:

  • understand the strengths and limitations of the data
  • learn about existing uses and users of the data
  • understand the methods used to create the data
  • help you to decide suitable uses for the data
  • reduce the risk of misusing data
Back to table of contents

3. Important points

The Internet access – households and individuals statistical bulletin provides more information on the range of activities carried out on the internet but the estimates are derived from the Opinions and Lifestyle Survey, which has a much smaller sample size than the Labour Force Survey (LFS) from which internet users is derived. Comparisons made between the estimates of these two publications should be undertaken with caution.

Back to table of contents

4. Quality summary


This report relates to the internet users statistical bulletin, which aims to provide information on adults’ internet use. These estimates were published quarterly in the Internet access quarterly update statistical bulletin between Quarter 1 (Jan to Mar) 2011 and Quarter 1 2014. The Internet access quarterly update was then superseded by the annual Internet users statistical bulletin, which was first published on 22 May 2015. The source of the estimates for both releases is the Labour Force Survey (LFS) and results are comparable between the two publications.

The Internet access quarterly update was discontinued following a consultation on statistical products that took place in 2013. Our response to the consultation on statistical products explained that in future, the estimates of internet users would be published on an annual basis. Following a review of the collection and publication of all the quarterly periods for each year, the estimates showed little change on a quarter-by-quarter basis. Therefore, from 2015 onwards, we have published estimates relating to Quarter 1 only from each year.

From Quarter 1 2011, a new question was added to the LFS: “When did you last use the internet?” The response options for this question are “Within the last three months”, “Between three months and a year ago”, “More than one year ago”, and “Never used it”. When the Internet access quarterly update was first published in 2011, the results from the first three response options were aggregated to produce estimates for those who had ever used the internet. From 2015, estimates of adults who had ever used the internet were split into those who were recent internet users (within the last three months) and those who were lapsed internet users (more than three months ago).

Uses and users

Within the UK there is wide interest in estimates of internet users and non-users from researchers, public bodies, the media, charities and academics. In recent years there has been particular interest in statistics about adults who do not use the internet, as part of the debate about social and digital exclusion.

The organisation Race Online 2012 was established to help more people get online for the first time by 2012. This organisation needed more frequent statistics on people who had never used the internet, but this could not be met by the annual Internet access – households and individuals statistical bulletin. To fill this information gap, we started publishing the Internet access quarterly update on internet users and non-users.

In 2012, Race Online 2012 was replaced by a new partnership organisation, Go ON UK, and then on 1 April 2016 Go ON UK merged with Doteveryone, continuing Go ON UK’s work to bring basic digital skills to the adults in the UK who lack them. They are now moving beyond basic skills to define social, political and personal attitudes towards the internet.

The UK government has been working towards achieving the “digital by default” policy, making the internet the preferred method for the delivery of a range of public services. The “Digital Inclusion Strategy” aims to reduce the number of people who are offline by 25% every two years, from 2014 until 2020. The statistics in the internet users release make it possible to monitor the number of people who are not recent internet users and therefore less able to access public services that are delivered online. These statistics may also be used to help inform the wider debate about digital and social exclusion.

LFS quarterly datasets are provided to government departments and are available to approved researchers via our Secure Research Service (SRS) and the UK Data Archive, Essex University. The UK Data Archive also provides non-disclosive data for public access.

Strengths and limitations

The main strengths of the survey include:

  • the LFS has the largest sample size of any UK household survey and can generate statistics for small geographical areas
  • the large sample size of the LFS allows for more detailed breakdowns of the data

The main limitations of the survey include:

  • the sample coverage of the LFS omits communal establishments, except NHS housing and students in boarding schools and halls of residence; members of the armed forces are only included if they live in private accommodation
  • individuals aged under 16 years are not covered; these individuals are of particular interest to policymakers as they are being brought up in an era when the internet is being put forward as a vitally important tool for business and social purposes
  • as space on the LFS is limited, it is not possible for more detailed questions to be asked about internet access and use
  • the voluntary nature of the survey means that people who do not wish to take part in the survey can refuse to do so, therefore increasing the risk of non-response bias

Recent improvements

There has been growing user interest in information about how many adults have in the past been internet users, but who have not used the internet recently. Since the publication of our Internet users 2015 statistical bulletin, we responded to this growing interest by replacing the estimates of adults who have ever used the internet, with estimates of those who had used it within the last three months (recent users), and those who last used it more than three months ago (lapsed users). This was possible because the internet use question, “When did you last use the internet?”, has the following response options: “Within the last three months”, “Between three months and a year ago”, “More than one year ago”, and “Never used it”. Responses for “Between three months and a year ago” and “More than one year ago” are aggregated to provide the estimates of adults who last used the internet more than three months ago.

From 2015 onwards, we have published estimates relating to Quarter 1 (Jan to Mar) only. This is because, following a review of the collection and publication of all the quarterly periods for each year, the estimates showed little change on a quarter by quarter basis.

Back to table of contents

5. Quality characteristics of the internet users data

This section provides a range of information that describes the quality and characteristics of the data and identifies issues that should be noted when using the output.


The internet use question, included as part of the Labour Force Survey (LFS), is used to provide estimates of adults (aged 16 years or over) who have ever or never used the internet. These are referred to in the Internet users statistical bulletin as recent and lapsed internet users and those who have never used the internet. The LFS covers a large range of employment-related variables and non-employment related variables, allowing cross-linking analyses to be undertaken (for example, internet use against disability or age).

Accuracy and reliability

The internet users results, as with other sample surveys, are subject to error consisting of two elements: the sampling error and the non-sampling error.

Sampling error

The LFS is a sample survey and therefore estimates are subject to sampling variability. Sampling variability is dependent on several factors, including the size of the sample, clustering and the effect of weighting on the variable of interest. Standard errors and confidence intervals, which give an indication of the amount that a given estimate deviates from a true population value, are supplied for some important internet user’s variables.

Confidence intervals are an indication of the reliability of the estimate; the smaller the interval, the more reliable the estimate is likely to be. With regards to “95% confidence intervals”, which are produced for some estimates, if the survey were repeated 100 times, 95 times out of 100, the true population value would fall within the range of the confidence interval.

The detailed regional estimates are based on smaller sample sizes than the higher level regional estimates and are therefore subject to a greater degree of sampling variability, so should be treated with caution. In addition, in the more detailed regional estimates, the categories of "last used the internet more than three months ago" and "never used" have been combined due to the small number of responses at this level of geography.

The LFS is also subject to sampling errors such as non-response bias. The survey population is all UK adults with a postal address. The risk of the survey not being representative is likely to increase with every refusal or non-contact with a sampled household (survey non-response). The voluntary nature of the survey means that people who do not wish to take part in the survey can refuse to do so. However, the calibration weighting process should account for non-response bias.

Non-sampling error

Non-sampling errors cover all errors unrelated to sampling methodology. These can be difficult to quantify and relate to errors in coverage, measurement, processing and non-response.

Coherence and comparability

Since the internet use question was added to the LFS in 2011, it has been asked on a regular and consistent basis. Hence, all results from this question are directly comparable.

The estimates published in the Internet users statistical bulletin focus on recent and lapsed internet users and those who have never used the internet. These estimates are not directly comparable with the estimates published as part of our annual bulletin, Internet access – households and individuals. This bulletin contains a wide range of information about internet access and use, but from a smaller sample than the LFS. The 2018 Internet access – households and individuals bulletin, for example, was compiled from approximately 2,750 interviews conducted for the Opinions and Lifestyles Survey, whereas approximately 41,000 households respond each quarter to the LFS. The larger sample size in the LFS allows for more detailed and accurate socio-demographic analysis than is possible with the Opinions and Lifestyles Survey dataset.

It is also important to note that the Internet users estimates are on a UK basis, whereas the Internet access – households and individuals results relate to Great Britain only and therefore do not include estimates for Northern Ireland.

Estimates of adults with a disability, as defined by the Equality Act 2010, are presented from 2014. The term “disabled” is used to refer to those who self-assess that they have a disability in line with the Equality Act. These should not be compared directly with the estimates for 2011 to 2013, which are defined by the Disability Discrimination Act (DDA) 1995.

Accessibility and clarity

Our recommended format for accessible content is a combination of HTML web pages for narrative, charts and graphs, with data being provided in usable formats such as CSV and Excel. Our website also offers users the option to download the output in PDF format. In some instances, other formats may be used, or may be available on request. For further information, please refer to the contact details at the beginning of this report.

For information regarding conditions of access to data, please refer to the following links:

Timeliness and punctuality

Internet users is published approximately eight weeks after the end of the Quarter 1 (Jan to Mar) survey period.

Publication takes place strictly in accordance with published release dates, following the Code of Practice for Statistics. The publication date has never been missed.

For more details, the Release Calendar is available online and provides 12 months’ advance notice of release dates. If there are any changes to the pre-announced release schedule, public attention will be drawn to the change and the reasons for the change will be explained fully at the same time, as set out in the Code of Practice for Statistics.

Concepts and definitions (including list of changes to definitions)

The internet use question is also used in the annual Internet access – households and individuals publication. The question was originally developed by Eurostat, and other EU member states, for inclusion in the model questionnaire that defines the annual Internet Access survey data requirements, to meet the requirements of the EU Regulation 808/2004 and its related Implementing Regulations.

Geography (including list of changes to boundaries)

The Internet users’ datasets contain estimates at three levels of geography, consistent with the Nomenclature of Territorial Units for Statistics (NUTS) 1, 2 and 3 classifications. The NUTS classification is a hierarchical system dividing up economic territory of the EU for the purpose of regional statistics. Estimates for 2018 are based on the 2016 NUTS boundaries. The low-level geographical estimates based on NUTS level 3, in tables 6A and 6B, are based on much smaller sample sizes than the higher-level estimates based on NUTS level 2, in tables 5A and 5B. The estimates in tables 6A and 6B will therefore have larger sampling variability and we therefore advise that these estimates should be treated with caution. For the periods up to 2016, these tables are presented at NUTS level 3, based on the 1998 NUTS boundaries. Estimates for 2017 are based on the 2013 NUTS level 3 boundaries. Estimates for 2018 are based on the 2016 NUTS level 3 boundaries.

Why you can trust our data

Office for National Statistics (ONS) is the UK’s largest independent producer of statistics and is its national statistics institute. The Data Policies and Information Charter detail how data are collected, secured and used in the publication of statistics. We treat the data that we hold with respect, keeping it secure and confidential, and we use statistical methods that are professional, ethical and transparent.

Back to table of contents

6. Methods used to produce the internet users data

How the output is created

The Labour Force Survey (LFS) covers private households, including persons who are temporarily absent. The resident population comprises persons who regard the sample address as their main address, and also those who have lived in the dwelling for more than six consecutive months, even if they do not regard this as their principal dwelling. Persons absent for more than six months are not regarded as members of the resident population. A private household comprises one or more persons whose main residence is the same dwelling and/or who share at least one meal per day. Students living in boarding schools and halls of residence are sampled via the private households of their parents. In Great Britain, an additional sample is drawn from persons living in National Health Service accommodation.

The sample is made up of approximately 40,000 responding UK households and 100,000 individuals per quarter. Respondents are interviewed for five successive waves at three-monthly intervals and 20% of the sample is replaced every quarter.

The LFS uses calibration weighting to assign a calibration weight wk to each responding individual k. These calibration weights are set to sum to a set of calibration totals within calibration groups – for example, the weights of all 18-year-old males in an LFS dataset (a calibration group) will sum to the population total of eligible 18-year-old males in the UK (a calibration total) at the time the survey was taken. Calibration weighting typically involves calculating a design weight, making adjustments for non-response and finally calibration to population totals.

The LFS assigns a calibration weight to all responding or imputed individuals, but does not assign a weight to individuals whose economic activity is unknown (so non-responders do not get a weight). Standard LFS practice in the case of individuals dropping out between waves is to roll their data forward by Quarter 1 (Jan to Mar); this is a form of imputation and these individuals receive a weight.

For more details about the LFS, please refer to the LFS Quality and Methodology Information report. This includes a full explanation of the survey as well as:

  • details about imputation
  • methods of calculating sampling variability
  • the method of weighting used
  • how the survey deals with proxy response
  • details about attrition and disclosure

How we disseminate the data

The internet users data are disseminated primarily through publication of statistical bulletins and ad-hoc releases. The publication schedule is detailed under Timeliness and punctuality.

Back to table of contents