Scottish household survey 2018: methodology and fieldwork outcomes

Methodology of the Scottish household survey 2018 and information on fieldwork targets and outcomes.





4. Further information on the sample designs and the methodology used is available here:

5. This must be a person in whose name the accommodation is owned or rented or who is otherwise responsible for the accommodation. The Highest Income Householder (HIH) is taken as the household reference person for the first part of the interview. In households with more than one householder, the person with the highest income is taken as the household reference person. If householders have exactly the same income, the older or oldest is taken as the household reference person.

6. The selection of the random adult is slightly more complex than this. The random adult needs to be one of the adult household members who is aged 16 years or over, is normally resident during term time (if a student) or has not been living outside of the household for 6 months or more.

7. The target population of the old SHCS excludes "dwellings without foundations". So, for example, mobile homes would not be eligible for the physical survey. However, these dwellings are eligible for the social survey. In order to work around this, such dwellings are still included in the social interview but are then streamed past questions on surveyor appointments, thus avoiding surveyors being called out to static caravans or houseboats.

8. Scottish Government Survey Harmonisation (Core Questions):


10. The random school child may be the same as, or different from, the random child.

11. Adults who are household members but have been living away for the previous six months are excluded from the selection of the random adult. Children and students living away during term time are counted as household members but are excluded from the random adult and random school child selection.

12. Where the same person completes both parts one and two (i.e. they are both the household respondent and selected as the random adult) the CAPI (Computer Assisted Personal Interviewing) script does not repeat the questions common to both sections. This means that these respondents are not asked for the same information twice.

13. Scottish house condition survey: 2018 key findings:


15. NS-SEC can also be automatically assigned to SEG codes, which allow a degree of backward compatibility with Socio-economic Group.

16. For Other Adults the questionnaire made no distinction between main and other jobs. Furthermore, if the respondent was unable to provide an estimate of the exact amount of earnings they were asked if they could provide a banded estimate.

17. It is worth noting that the list of benefits asked about was substantially revised in 2018. Overall, 40 benefits and other sources of income such as welfare loans were included in four sets.

18. Lynn, Peter, Beerten, Roeland, Laiho, Johanna and Martin, Jean (October 2001) 'Recommended Standard Final Outcome Categories and Standard Definitions of Response Rate for Social Surveys', Working Papers of the Institute for Social and Economic Research, paper 2001-23. Colchester: University of Essex.

19. These are highlighted in red in Table 6.3.



22. These are highlighted in red in Table 6.4.

23. A report on the development of the weighting procedures is available here:

24. NRS, Mid-2017 population estimates Scotland:

25. NRS, Estimates of Households and Dwellings in Scotland, 2017:

26. NRS, Estimates of Households and Dwellings in Scotland, 2018:

27. NRS, Mid-2017 population estimates Scotland:

28. Scotland's Census 2011: Census Data Explorer (Data warehouse)

29. John D'Souza, HM Treasury; Patten Smith and Kevin Pickering, Ipsos MORI; Kathryn Gallop, KSG Research; and Angela Thompson, Royal College of Occupational Therapists Does reissuing unproductive cases in a face-to-face survey reduce non-response bias? Evidence from the Citizenship Survey 'Social Research Practice' - the SRA journal Volume 4, Summer 2017

30. Scottish Household Survey: Analysis of changes to response rate (2017) Unpublished. Due to publish in 2020. Chris Martin and Jamie Robertson presented the information to the Social Research Association conference in December 2018.

31. Total Survey Error: Past, Present, and Future Robert M. Groves, Lars Lyberg. Public Opinion Quarterly, Volume 74, Issue 5, 1 January 2010, Pages 849–879,
Published: 01 January 2010



Back to top