‘Outlines’ set out the ‘concern’ to which a Monitoring Review relates, describe the issues to be explored in the Review, the geographic coverage of the Review, a broad timetable, and the broad methodology that we expect to follow in conducting the Review. Outlines are prepared before the main work on a Review is undertaken. They serve both as a guide for the team doing the research and as an indication of work in hand for others who might wish to make a contribution to the Review.

The concern

Results from the International Passenger Survey (IPS) are used in the production of various sets of official statistics, including estimates relating to: international migration; population; the Travel Account of the Balance of Payments, and travel and tourism. Given the nature of the survey, involving interviews with members of the travelling public at ports, there are concerns about its robustness as a basis for the different purposes to which it is put; and whether its strengths and limitations are currently explained sufficiently clearly in those contexts when the statistics are published. This Review will examine these points, the views of users and the steps taken by ONS to address the limitations of the survey.

Background

IPS is a continuous survey carried out by ONS. It involves face to face interviews with a random sample of passengers as they enter or leave the UK by the principal air, sea and tunnel ports. All interviews are voluntary. Each year around 800,000 passengers are asked if they are migrating to or from the UK (i.e. intending to move for at least a year). Around one in ten passengers is contacted as they pass through the port; if the person is a migrant they are asked the migration questions. Around one in thirty passengers – every third person screened for migration – is additionally asked the travel and tourism questions, resulting in between 250,000 and 300,000 interviews a year.

ONS achieves a sample of between 4,000 and 5,000 migrants each year, which suggests that around one in 200 travellers is a migrant. The small sample size places limits on the level of disaggregation by characteristics of the migrants or the geographic destination of immigrants. ONS combines the IPS estimates with data from other sources to provide more complete estimates that it calls Long Term International Migration (LTIM). Adjustments are also made for changes in the migration intention of passengers. The IPS component accounts for around 90 per cent of LTIM.

As a sample survey, IPS is subject to some uncertainty, both sampling error and non-sampling error. ONS provides measures of the accuracy of the survey estimates that indicate the scale of variability due to chance (sampling error). But IPS estimates have the potential to be biased due to non-sampling issues such as non-response, for example, if passengers who choose not to participate in the survey have different characteristics to those who do respond, or if passengers deliberately conceal their intention to migrate.
ONS has made improvements to the sample design and data processing of the IPS to better optimise the survey for measuring migration, following a Port Survey Review in 2006. It undertook further improvements through the Migration Statistics Improvement Programme which closed in March 2012.

Process and methods

The Authority’s Monitoring and Assessment team will review the nature of reporting about the quality of the IPS statistics and explanations of strengths and limitations, such as:

• The nature of uncertainty around the IPS estimates and the extent to which the resulting uncertainty is communicated to users;
• For international migration, the quality of information about:
o destinations of immigrants;
o reasons for migration and intentions to stay;
• The accessibility of quality information.

The team is seeking views about the fitness for purpose of the statistics based on the IPS, as well as regarding the steps taken to improve the statistics and of possible areas for further development.
The team’s work on this Review will gather information from:

• ONS statistical teams involved in the IPS and preparation of statistics using the survey data
• Other producers of relevant statistics and central government stakeholders
• Key users and experts (for example: in universities, local government, business, and other external bodies such as Eurostat)

Relevant aspects of the Code

Principle 1.1: Engage effectively with users of statistics to promote trust and maximise public value, in accordance with Protocol 1

Principle 1.2: Investigate and document the needs of users of official statistics, the use made of existing statistics and the types of decision they inform

Principle 1.5: Publish information about users’ experiences of statistical services, data quality, and the format and timing of reports

Principle 4.1: Ensure that official statistics are produced according to scientific principles. Publish details of the methods adopted, including explanations of why particular choices were made

Principle 4.2: Ensure that official statistics are produced to a level of quality that meets users’ needs, and that users are informed about the quality of statistical outputs, including estimates of the main sources of bias and other errors, and other aspects of the European Statistical System definition of quality

Principle 8.1: Provide information on the quality and reliability of statistics in relation to the range of potential uses, and on methods, procedures, and classifications

Principle 8.2: Prepare and disseminate commentary and analysis that aid interpretation, and provide factual information about the policy or operational context of official statistics. Adopt formats for the presentation of statistics in graphs, tables and maps that enhance clarity, interpretability and consistency

Timetable

We are currently gathering and reviewing evidence, and plan to report to the Authority Board in spring 2013.

Your views

We would welcome your views on any of the issues to be covered in this review. Please send any comments to: assessment@statistics.gsi.gov.uk by 25 January 2013 if possible but late responses would still be welcome. We would also welcome any comments that are informing responses to the Public Administrations Select Committee’s study on migration statistics (part of its programme of work on statistics), if that would be more convenient.