Short-Term International Migration Estimates: Frequently Asked Questions

1.1. Which are the latest available Short-Term International Migration estimates?

The latest available Short-Term International Migration (STIM) estimates, released on 25 May 2017, are final estimates for the year ending June 2014 and provisional estimates for the year ending June 2015. For more information about the differences between provisional and final STIM data, please refer to section 1.3. Estimates of short-term international inflows, outflows, instocks, outstocks and mean lengths of stay are available for England and Wales. The Short-Term International Migration Annual Report (STIMAR) presents the latest estimates.

1.2. What other information is available about Short-Term International Migration?

Statistics on the number of short-term entry clearance visas issued are also released by the Home Office and are included in the STIMAR. The Home Office have also produced a short article on Entry clearance visas by length. The 2011 Census collected information about short-term residents in England and Wales, the findings of which are available in the release 2011 Census, Short-term Residents for Local Authorities in England and Wales. There are a number of definitional differences between these data sources which should be considered when comparing trends in short-term international migration.

1.3. How different are provisional and final estimates?

Short-term international migrants are interviewed as they leave the UK, and thus it takes 8 quarters (2 years) of International Passenger Survey (IPS) data to capture all migrants who have arrived in the reference year (as migrants could stay for up to 12 months). To increase the timeliness of STIM estimates, a provisional dataset is released 23 months after the reference period. Therefore the latest estimates contain 18 months of final IPS data and six months of provisional IPS data. IPS data are only finalised when a full calendar year's interview data can be calibrated against annual passenger figures supplied to the IPS by the Civil Aviation Authority and the British Ports Authority. For the final estimate, all data included are final IPS data. Provisional estimates are replaced with final estimates when the data are republished in the following year; for example, final mid-2011 estimates were published on 29 May 2014, having been published as provisional estimates on 23 May 2013. Provisional estimates are marked ‘p’ in STIM data tables.

In practice, there are generally very small differences between provisional and final STIM estimates. This is because only a very small percentage of the interviews used to build the estimates for the most recently published mid-year will have been collected in the most recent calendar year. There were minimal differences between the published provisional and final STIM estimates for England and Wales and at local authority level for mid-2012.

However for mid-2011, at local authority level, there were some larger differences between provisional and final STIM estimates, specifically for the study and overall estimates. Quality assurance on the processing from provisional to final data for this year resulted in an improvement applied to the processing of mid-2011 study data. This means that there are some differences between previously published provisional estimates and the latest final estimates for mid-2011. The differences are most noticeable in local authorities that have larger proportions of short-term migrants who are studying.

1.4. When will the next year of short-term international migration data be released?

Provisional STIM estimates for mid-2016 (that is the year 1 July 2015 to 30 June 2016) and the next edition of the STIMAR are provisionally scheduled for publication in May 2018. Please note that publication details, although correct at time of writing, are subject to change.

2.1. What are the key findings from the latest short-term international migration estimates?

Estimates published in the STIMAR on 25 May 2017 showed that:

• There are three measures of short-term migration. Those that migrate between 1 to 12 months for all reasons, 3 to 12 months for all reasons and the narrower United Nations (UN) definition of those that migrate for 3 to 12 months for work and study. All estimates in this report are for short-term international migration to and from England and Wales.

• In year ending (YE) June 2015 short-term immigration for 3 to12 months, for all reasons stood at 304,000, of these 39% (118,000) were for the reason “other”; short-term emigration of 3 to 12 months for all reasons was 390,000.

• Using the UN definition in the YE June 2015 there were 160,000 short-term immigrants and 39,000 visits away, both similar to YE June 2014.

• Short-term immigration of 1 to 12 months for all reasons in YE June 2015 was 1.2 million, (where 3 out of 4 of these left within three months); short-term emigration of 1 to 12 months for all reasons was 2.7 million, a statistically significant increase of 265,000 compared with the previous year.

• There were more than twice as many visits (1 to 12 months) abroad than to England and Wales and this pattern has been similar since YE June 2004; there is a similar pattern for the 3 to 12 month migrants but the gap is smaller and the opposite is true when using the UN definition of short-term migration.

• “Other reasons” (includes holidays and travelling; visiting or accompanying family and friends; and working holidays) are the most common main reason for short-term international migration both to and from England and Wales.

• Home Office data for 2016 show that entry clearance visas for non-EEA nationals were issued as follows: 58,000 short-term work visas (of which 60% were for less than 6 months), 55,000 short-term sponsored study visas (46% for up to 6 months) and 87,000 short-term study visas (91% for up to 6 months).

2.2. What is the difference between a flow and a stock?

Short-term migrants are interviewed by the IPS at the end of their visit (when a short-term emigrant returns to the UK and when a short-term immigrant leaves the UK). Flow estimates are aggregated based upon the date when the visit started. Inflow estimates refer to non-UK residents estimated to have arrived in the UK to commence a visit in the relevant time period. Outflow estimates refer to UK residents estimated to have left the UK to commence a visit abroad in the relevant time period.

Flow estimates refer to the number of migrations commenced (migrant moves) as opposed to the number of people who commence migrations (migrants). This distinction is important when estimating short-term international migration annually because a person could migrate more than once in the same period. For example, a single person migrating twice in a year for three months on each occasion would appear in the flow estimates as two (migrant moves), not as one (migrant).

Stock estimates are calculated by summing the number of nights each short-term migration lasts and dividing by 365 to create a long-term migration equivalent. Where a short-term migration spans two time periods, the stays are split between the two time periods.

Stock estimates can be used to estimate the impact of short-term international migration on the overall population ‘stock’. For example, if four migrants each stayed in England and Wales for three months, this would be the equivalent of one person for one year, and so the stock count would be 1. Likewise two migrants staying for 6 months would give the equivalent of one person staying for one year. In the second example the number of arrivals is half that of the first example, but results in the same stock estimate. Stocks are calculated from the number of stays and the length of stay, so an increase in either can lead to an increase in stocks. ‘Instocks’ give an average number of short-term immigrants in England and Wales on an average day, while ‘outstocks’ give an average number of England and Wales residents who are abroad as short-term emigrants on an average day.

STIM stock estimates can be found in the following data tables: STIM.02 Stocks and Mean Lengths of Stay by Main Reason for Migration, STIM.05 Age by Sex - Stocks and STIM.08 Top 10 countries, flows and stocks.

2.3. Why are outflows and outstocks higher than inflows and instocks?

To be included in STIM inflow estimates, a person must have been living outside the UK for 12 months or more prior to becoming a short-term immigrant to the UK. These tend to be foreign citizens, but can include British citizens. To be included in STIM outflow estimates, a person must have been living in the UK for 12 months or more prior to becoming a short-term emigrant from the UK. These tend to be British citizens, but include other residents. It is much more common for British citizens to leave for short periods than arrive for short periods.

Therefore, when a British citizen leaves for 1 to 12 months or 3 to 12 months they are counted in the outflow estimate. However, when they arrive back, they have not been living outside the UK for 12 months or more and are intending to return home for more than 12 months, so are not included in the STIM inflow estimate. Stocks are derived from the flows figures and so higher outstock reflects the higher outflow.

2.4. Why are there no net migration estimates for short-term international migration?

Unlike for Long-Term International Migration (LTIM) estimates, there are no estimates of short-term international net migration flows. Short-term migrants do not stay for more than 12 months; therefore, they do not become ‘usually resident’. This means they are not included in population estimates, so calculating a net migration figure for short-term migrants does not have the value that it does for LTIM. In addition, short-term migrants coming to England and Wales are counted in as short-term migrants but not out as short-term migrants, because to be counted out as a short-term migrant, a person needs to have been resident in England and Wales for 12 months or more. Short-term international outflows from the UK are higher than short-term international inflows to the UK, so the net difference would be negative if it were possible to calculate.

The most appropriate estimates to use in order to estimate the impact of short-term international migration on the overall population are short-term international migration stocks. Stocks estimates are more meaningful because they estimate the average number of short-term migrants in the country on an average day in a 12 month period. For information about stocks, please refer to section 2.2.

3.1. How is a short-term international migrant defined?

According to the United Nations definition, an international short-term migrant is defined as:

"A person who moves to a country other than that of his or her usual residence for a period of at least 3 months but less than a year except in cases where the movement to that country is for purposes of recreation, holiday, visits to friends and relatives, business, medical treatment or religious pilgrimage"

Following consultation with users, STIM estimates have been published on the basis of the following three definitions:

1. Moves made for between 3 and 12 months for employment or study (UN definition).

2. Moves made for between 3 and 12 months for any reason.

3. Moves made for between 1 and 12 months for any reason.

To be included as a short-term international immigrant to England and Wales under any of these definitions, a person arriving must have been living outside the UK for 12 months or more (these tend to be foreign citizens, but can include British citizens). A short-term international emigrant from England and Wales must have been living in the UK for 12 months or more prior to leaving (these tend to be British citizens, but include other residents). All three definitions refer to the mid-year, which is 1 July to 30 June. Each of the England and Wales level STIM data tables (STIM.01 to STIM.06 and STIM.08) includes a separate tab showing estimates on the basis of each of these definitions.

The UN definition (a) is used to allow international comparisons and is also the only available definition for local authority level estimates of STIM (shown in data table STIM.07). This is because of the methodology used to distribute national level estimates to local authorities (for more information, please refer to section 3.5). The UN definition of ‘work’ refers to working for a UK based employer and excludes business trips where a short-term migrant is paid by an organisation in their country of origin. The UN definition of ‘study’ refers to Higher and Further Education courses and excludes evening classes and informal tuition.

The IPS samples all visitors arriving in the UK. Some visitors will visit Scotland or Northern Ireland in addition to England or Wales. Where this has happened, those spending the majority of their time in England and Wales are selected for inclusion in STIM estimates. For the length of stay variable, migrants cannot always accurately record the precise length of stay in each area that they have visited. Therefore, for those who have spent most of their stay in England and Wales, the total length of stay includes any days spent in Scotland or Northern Ireland. Length of stay estimates are shown in the following data tables: STIM.03 Stays by Citizenship by Main Reason for Migration and STIM.06 Stays by Age and Sex.

Asylum seekers are not included in STIM estimates as no suitable adjustment can currently be made to account for them. In order to produce LTIM estimates, ONS obtains Home Office data on principal applicant asylum seekers and their dependants. However, the STIM methodology does not attempt to make adjustments as they are considered too complex for the small number of migrants who would be affected.

It should also be noted that the IPS does not sample passengers who cross the land border between the UK (Northern Ireland) and the Republic of Ireland. In addition, until 2009 no ports in Northern Ireland were surveyed in the IPS. Belfast International Airport has been included in the sample since 2009. No adjustments are made to England and Wales STIM estimates to allow for this and therefore any short-term migrants who move from Northern Ireland to England or Wales during their stay are not included in the estimates. However, this number is thought to be relatively low. Family doctor registration data are the most complete source that can be used to estimate international immigration to Northern Ireland. This source is used to estimate LTIM but there is currently no way to count short-term migrants who go on to enter England or Wales using this source.

For more information about how England and Wales level STIM estimates are calculated, please refer to the Short-Term International Migration methodology – national estimates.

3.2. Why are Short-Term International Migration estimates only available for England and Wales?

The STIM estimates were developed as part of the Improving Migration and Population Statistics programme. This programme was set up to improve our understanding of population and migration and in particular the Local Authority Population Estimates for England and Wales. Hence, the focus of STIM estimates at this time was for England and Wales.

In addition, to produce STIM estimates for the UK there was a lack of relevant data sources, particularly for Northern Ireland where health card data are used to determine moves to and from Northern Ireland in LTIM estimates. It is not possible to identify short-term international migrants in Northern Ireland health card data and there is no alternative source to calculate short-term migration to or from Northern Ireland. Also, for the distribution to local authority level, ONS does not have access to a full range of data sources that would enable a distribution to be calculated for all local authorities in the UK.

Moving forward we will assess our user requirements for STIM estimates and investigate if any new data sources are now available.

3.3. How are England and Wales level estimates of short-term international migration calculated?

STIM flows estimates are produced directly from the IPS, using data collected at the end of the short-term migrants’ stay in or out of the UK (so when a short-term emigrant returns and a short-term immigrant leaves). This is different to the method used for estimating LTIM, for which long-term migrants are interviewed at the start of their stay and are defined as long-term migrants by their intended length of stay. Data for short-term migrants are only available for the reporting period after all short-term migrants have either left or returned to the UK. This is necessary for accuracy as migrants are often unsure on details of their stay at the start of the visit. However, waiting until short-term migrants have either left or returned to the UK does delay the publication of the statistics. To improve timeliness, provisional STIM estimates are published, which use 18 months of final IPS data and 6 months of provisional data. These provisional estimates are updated the following year when final IPS data are available. For more information about the differences between provisional and final STIM estimates, please refer to section 1.3.

For a detailed explanation of how England and Wales level estimates of short-term international migration are calculated, please refer to the Short-Term International Migration methodology – national estimates.

3.4. What improvements have been made to the International Passenger Survey?

Fundamental changes were introduced to the IPS sample design at the beginning of 2009 to make the survey more focused on identifying migrants. In addition, IPS interviewer resource was rebalanced away from Heathrow and towards other routes. Research was undertaken using 2006 IPS data to determine the distribution of IPS shifts by route that would be expected to deliver the most statistically robust sample. Finally, a new IPS processing system was completed early in 2009, which has enabled improvements to be made to the IPS weighting methodology.

Further information on these changes can be found on the Migration Statistics Improvement Programme web pages.

3.5. How are local authority level estimates of short-term international migration calculated?

The local authority estimates are calculated by distributing England and Wales level IPS estimate of short-term international immigration for 3 to 12 months for work or study (the UN definition), to local authorities. A number of administrative sources are used to distribute workers and students respectively to local authorities.

Administrative sources used to distribute short-term international migration estimates to local authority level

Migrant Workers Scan (MWS)

A Department for Work and Pensions (DWP) dataset that contains all migrants who have registered for and been allocated a National Insurance Number (NINo).

Student Record

The Higher Education Statistics Agency (HESA) student record contains all students studying at a Higher Education provider that is funded via the Higher Education Funding Councils for England and Wales.

Certificate of Sponsorship (CoS)

Home Office data on the sponsorship of visa applications by work institutions.

Confirmation of Acceptance to Study (CaS)

Home Office data on the sponsorship of visa applications by study institutions.

Extensions of leave to remain (Extensions)

Chapter 9 holds Home Office data on successful applications for visa extensions of leave to remain in the UK.

Individualised Learner Records

Skills Funding Agency data on Government funded learners at Further Education level in England, including those studying English as a second language.

Lifelong Learning Wales Record

Welsh Government (WG) data on Government funded learners at Further Education level in Wales, including those studying English as a second language.

Local authority level STIM estimates are only produced for inflows of short-term immigrants. There are currently no available data sources to enable short-term emigrants to be distributed in a similar way. For more information about how local authority level STIM estimates are calculated, please refer to the Short-Term International Migration methodology – local authority estimate.

3.6. What about migrants who stay for 12 months or more?

Migrants who stay for 12 months or more are included in estimates of LTIM, which are reported on in the Migration Statistics Quarterly Report.

3.7. Why do estimates of long-term international migration differ from the number of National Insurance Numbers allocated?

On 12 May 2016 we published an information note explaining the reasons why long-term international immigration figures from the IPS could differ from the number of National Insurance Number (NINo) registrations. It noted that the two series are likely to differ because of short-term immigration and timing differences between arriving in the UK and registering for a NINo. It emphasised that the estimates derived from the IPS are the most appropriate for measuring long-term immigration. NINo registrations data are not a good measure of LTIM, but they do provide a valuable source of information to highlight emerging changes in patterns of migration.

The analysis used 1 to 12 month short-term migration estimates for employment, study and work (other) to help explain the gap as this group was most likely to contain people who might register for a NINo. In YE June 2015 there were 290,000 EU citizens immigrating to England and Wales for 1 to 12 months for the reason of employment, study or work (other) compared with 251,000 the previous year. This is not the total level of short-term international migration but the most appropriate to help explain the gap. An ad hoc analysis was also run to estimate the number of short-term international migrants in 2015 using ‘intentions’ data. Two estimates were included to reflect the uncertainty and the fact that they can be estimated in different ways. The paper provides more information on this. The mid-2015 ‘actual’ STIM estimates were published in May 2017.

Adding together LTIM and STIM estimates does not provide a reliable measure of all immigration to the UK within a specific time period. Short-term immigration flows are based on journeys, not people, and have methodological differences from LTIM flows. In addition, it is possible for someone to be both a long-term and short-term migrant in the same period, and STIM estimates are based on actual flows whereas LTIM covers migrants' intentions.

However, although they cannot be added together to provide one single, accurate measure of international migration, LTIM and STIM estimates of immigration and emigration should be considered alongside and in the context of each other. As these estimates represent different people immigrating for different reasons but they can help to provide an overall picture of international migration. Historical data on short-term and long-term international migrants are published on the ONS website, and there is a summary of the definitional differences between these data. For more detail on the NINo and IPS comparison, users are encouraged to read the report.

4.1. How accurate are England and Wales level estimates of short-term international migration?

England and Wales level STIM estimates are derived from the IPS, which is a sample survey and therefore subject to some uncertainty. There is evidence to suggest that an inadequate sampling design and coverage of the IPS meant that a substantial amount of long-term migration, particularly of EU8 citizens, was missed during the years 2004 to 2008, prior to improvements made to the IPS from 2009 (for more information about these improvements, please refer to section 3.4). This inadequate coverage of some routes will also have caused some short-term migrants to be missed in the mid-years 2004 to 2008. However, due to a lack of comparative data sources, it is not possible to quantify the scale of the difference. For more information, please refer to the Quality of Long-Term International Migration estimates from 2001 to 2011 full report.

In general, STIM estimates obtained from the IPS are subject to both sampling and non-sampling errors.

Sampling error

Sampling error arises due to the variability that occurs by chance because a sample, rather than an entire population, is surveyed; that is, sampling error results because not every short-term migrant who enters or leaves the UK is interviewed. Sampling errors are determined both by the sample design and the sample size. Sampling error may sometimes present misleading changes as a result of the random selection of those included in the sample.

Confidence intervals (CI) are provided with IPS based estimates and are a statistical method by which sampling error can be measured. They provide a range within which the true value of an estimate is likely to fall. The confidence intervals used for the IPS are 95% confidence intervals; this means that the range is expected to contain the true value of the number of migrants around 95% of the time. Table 2 shows STIM inflow and outflow estimates alongside the associated 95% confidence intervals and ranges for mid-2015. The range represents the 95% confidence interval and shows the range within which there is a 95% chance the true value of the estimate would fall (had all short-term migrants been surveyed).

When STIM estimates are broken down to lower levels of detail, greater care must be taken with their interpretation. This is because these estimates will be based on a smaller number of survey contacts, which increase the uncertainty around the estimate. For example, it is not possible to produce estimates for most individual citizenships within a single year, because of the small number of survey contacts that comprise each estimate.

Even where the sample size allows individual country estimates to be produced, it is often not possible to say that a change in the estimate from one year to the next is real or not. This is because smaller estimates often have proportionately larger confidence intervals than larger estimates. However, in a few instances where the estimates are based on large enough sample sizes, we can be at least 95% certain that the change in the estimate represents a statistically significant change. For more information about statistically significant changes, please refer to section 4.2.

Non-sampling error

Non-sampling error is all error that is not sampling error. The challenge with non-sampling error is that it is difficult to directly calculate a numerical measure of its effect. This, therefore, makes it hard to incorporate when analysing results. Non-sampling error is best understood by referring to examples that apply to the IPS.

The first non-sampling error may be due to non-response. Bias will occur when passengers who do not respond to the survey have different characteristics to those who do respond. Possible low levels of response that might be expected due to the respondent not speaking English have been reduced in recent years by the introduction of separate sampling arrangements in certain ports. This improvement is at least partly because interviewers can more easily enlist the help of relatives or interpreters to translate for contacts who do not speak English.

A further source of bias may arise from contacts deliberately concealing their migration intentions and characteristics from the interviewers.

For those contacts identified by the IPS as migrants, the level of non-response is very low for most characteristics. Further information about IPS non-response is available in Appendix D of the report Travel Trends, 2015. In addition, the paper International Passenger Survey: Quality Information in Relation to Migration Flows provides an overview of the quality and reliability of the International Passenger Survey (IPS) in relation to producing estimates of long-term migration flows.

4.2. What does it mean if a change is statistically significant?

As outlined in section 4.1, the IPS interviews a sample of passengers passing through ports within the UK. As with all sample surveys, the estimates produced from these interviews are based upon one of a number of different samples that could have been drawn at that point in time, meaning that there is a degree of variability around the estimates produced. This variability may sometimes present misleading changes as a result of the random selection of those included in the sample. If a change or a difference between estimates is described as 'statistically significant', it means that statistical tests have been carried out to reject the possibility that the change has occurred by chance. Therefore statistically significant changes are very likely to reflect real changes in migration patterns.

4.3. How do you determine if a change is statistically significant?

A quick method of identifying if the difference between two estimates is statistically significant is to determine if there is an overlap of their confidence intervals (for more information about confidence intervals, please refer to section 4.1). If the confidence intervals do not overlap, then the differences can be described as statistically significant. For example, the increase between an estimate of 100,000 with a confidence interval of +/- 10,000 and an estimate of 150,000 with a confidence interval of +/- 15,000 would be statistically significant, because 100,000 plus 10,000 is still lower than 150,000 minus 15,000. However, if the confidence intervals do overlap, a t test should be performed to determine statistical significance.

4.4. What is a t test?

A t test ascertains if the difference between two estimates is statistically significant, that is, if it were repeated with a different sample, the difference would occur 19 out of 20 times. This test divides the difference of the estimates by the square root of the sum of the squared standard errors. The resulting t value needs to be greater than 1.96 to be 95% certain that the estimates are different. It can also be used to create a confidence interval around the difference. It calculates the standard error of the difference directly from using the difference between the two individual standard errors. All main statistical software packages have the functionality required to perform a t test. If you need assistance with identifying whether the difference between two international migration estimates is statistically significant then please contact migstatsunit@ons.gov.uk.

4.5. How accurate are local authority level estimates of short-term international migration?

Local authority level STIM estimates are derived by distributing the England and Wales level STIM estimates for employment and study to local authorities on the basis of information collected from a number of different administrative data sources (for more information, please refer to section 3.5). Therefore, local authority STIM estimates are subject to the same aspects of uncertainty as England and Wales level estimates, as described in section 4.1. The data sources are not based upon the same definitions of short-term migration used in the IPS so may include some migrants that are not included in the IPS. Finally, local authority level estimates are provided to the nearest unit to enable and encourage further calculations and analysis. However, the estimates must not be assumed to be as exact as the level of detail implied by unit level data. The individual estimates in this table are derived from overall flow estimates for England and Wales which are sample survey based and which have quite large confidence intervals.

4.6. Can I request more detailed information on short-term international migrants?

STIM estimates are based on a comparatively small number of interviews. Therefore, many variables can only be disaggregated to a certain level before being subject to unacceptable margins of error. Specific data requests can be discussed with the Migration Statistics Unit via: migstatsunit@ons.gov.uk

4.7. What quality assurance has ONS undertaken on these estimates?

STIM estimates are subject to extensive quality assurance. The Social Survey division within ONS are responsible for carrying out the IPS and producing IPS estimates. They have carried out quality assurance on the data collected, focusing particularly on the relationship between short-term migrant contacts, visitor contacts and weighted estimates. This includes investigating any anomalies and checking the data provided by the Civil Aviation Authority which are used to weight the estimates.

IPS data have been examined in relation to estimates for previous years. The focus of this quality checking has been on any statistically significant increases or decreases and the contributing factors for these changes.

The estimates are quality assured at every stage of the processing.

4.8. How good are these estimates of short-term international migration?

STIM estimates are:

• the best estimates available at this time

• produced in accordance with the National Statistics Code of Practice

To see how STIM estimates measure against the National Statistics Code of Practice dimensions of quality, please see the Quality and Methodology Information Report for Short-Term International Migration and Quality and Methodology Information Report for Short-Term International Migration estimates for Local Authorities.

5.1. Short-Term International Migration Links

STIMAR

STIM data tables

Quality and Methodology Information Report for Short-Term International Migration

Quality and Methodology Information Report for Short-term International Migration estimates for Local Authorities

Short-Term International Migration methodology – national estimates

Short-Term International Migration methodology – local authority estimate

5.2. Long-Term International Migration Links

Long-Term International Migration (LTIM) statistics

Long-term International Migration methodology

Migration Statistics Quarterly Report

International Migration Timeline

Quality of Long-Term International Migration estimates from 2001 to 2011 full report

5.3. Other Links

Population by Country of Birth and Nationality

Local Area Migration Indicators

Internal Migration Estimates

Improving Migration and Population Statistics

'Population Estimates for UK, England and Wales, Scotland and Northern Ireland