Typology of issues relating to H2S groups in poverty research Ides - - PowerPoint PPT Presentation

This project has received funding from the European Union’s Seventh Programme for Research, Technological Development and Demonstration under Grant Agreement No 312691

Typology of issues relating to H2S groups in poverty research

Ides Nicaise KU Leuven

www.inclusivegrowth.be www.inclusivegrowth.be 2

What are hard-to-survey (H2S) groups?

Tourangeau (2014)

• Hard-to-sample: e.g. homeless people (unknown populations, small

numbers…)

• Hard-to-identify: e.g. Roma, migrants (variety of definitions,

fluctuating states…)

• Hard-to-contact: e.g. migrants, displaced groups (language / cultural

barriers…)

• Hard-to-persuade: e.g. undocumented immigrants (hidden groups,

stigma…)

• Hard-to-interview: e.g. low-literate people, children, people with

mental illness / disorders (complexity of surveys, complexity of living conditions… )

Title/date

www.inclusivegrowth.be www.inclusivegrowth.be 3

Hard-to-sample

• Causes

– Rare (<10%, <1%): e.g. homeless – Hidden (e.g. undocumented migrants)

• Problems

– Absence of sampling frame – High cost of screening

• Solutions

– Non-random sampling (indirect sampling, RDS…) – Stratification (with oversampling of high-prevalence strata) – Dual frame approach (one general-purpose sample with high coverage of overall population but low prevalence of the rare group, and one with low coverage & high prevalence)

Title/date

www.inclusivegrowth.be www.inclusivegrowth.be 4

Hard-to-identify

• Causes:

– Vague / variable definitions; invisible characteristics (e.g. poor, Roma) – Hidden populations (e.g. undocumented immigrants)

• Problems:

– High cost of screening + imperfect screening – False negative cases => undercoverage – Motivated misreporting

• Solutions:

– Use of conventional / official definitions – Full-roster categorisation – Network-based sampling: snowball, RDS

Title/date

www.inclusivegrowth.be www.inclusivegrowth.be 5

Hard-to-reach

• Causes:

– Elusive populations (e.g. travellers, homeless, refugees)

• Problems:

– Undercoverage (short-term members escape) – Stock sampling bias – Tracking costs / attrition (in panel surveys)

• Solutions:

– Location sampling – Flow sampling (at inflow) – Panels: anticipate mobility; remunerate respondents

Title/date

www.inclusivegrowth.be www.inclusivegrowth.be 6

Hard-to-persuade

• Causes:

– Hostility towards public services, bureaucracy (e.g. people excluded from benefits, sanctioned / traumatised groups)

• Problems:

– Refusal rates – Response bias

• Solutions:

– Sensitisation (of gatekeepers as well as respondents) – Participatory (community-based) research – Feedback about research findings and impact – (Financial) incentives

Title/date

www.inclusivegrowth.be www.inclusivegrowth.be 7

Hard-to-interview

• Causes:

– Language barriers (e.g. migrants) – Vulnerability (e.g. children, disabled people) – Low literacy / cognitive or communication impairments / mental illness / distress

• Problems:

– Interrupted interviews – Item non-response – Unreliable answers

• Solutions:

– Proxies / mediators – Simplified questionnaires – audio computer-assisted self interviews (ACASI)

Title/date

www.inclusivegrowth.be www.inclusivegrowth.be 8

To conclude

Challenges:

– Under-representation in general-population surveys – Bias in response, even more in specific surveys – Cost of survey ⇒Need for innovative survey methodologies

Groups often combine several challenges Indicators

– Metadata: % contact failure / attrition, % refusals, % interrupted interviews, item non-response – Cost indicators: screening cost, average unit cost per effective interview…

Title/date

www.inclusivegrowth.be www.inclusivegrowth.be 9

Issues to be addressed in this course

• (Definitions: e.g. typology of homelessness, Roma…)
• Sampling techniques: e.g. dual sampling frames, indirect

sampling, capture-recapture, respondent-driven sampling etc.

• Questionnaire design
• Data collection procedures: e.g. mobilising populations,

tracking, mediation, participative methods, ethical issues

• Anthropological issues: e.g. how to contact hidden

populations, how to overcome cultural barriers

• Statistical analysis: estimating population size of

undercounts, selection bias, imputation, attrition etc.

Title/date

www.inclusivegrowth.be www.inclusivegrowth.be 10

• TOURANGEAU R.

EDWARDS B., JOHNSON T., WOLTER K., BATES N. (eds., 2014), Hard-to-survey populations, Cambridge University Press, Chapter 1

• SCHEPERS W.,

JUCHTMANS G., NICAISE

• I. (2016), Reaching out to

hard-to-survey groups among the poor. Survey protocols, statistical issues and research design, Leuven: HIVA, Chapter 1

Title/date

TÁRKI Social Research Institute Inc. (HU) Amsterdam Institute for Advanced labour Studies, Universiteit van Amsterdam (NL) The Swedish Institute for Social Research, Stockholms Universitet (SE) Fachbereich IV, Wirtschafts- und Sozialstatistik, Universität Trier (DE) Centre d’Etudis Demogràfics, Campus de la Universitat Autònoma de Barcelona (ES) Centre d’Etudes de Population, de Pauvreté et de Politiques Socio-Economiques (LU) Centre for Social Policy, Universiteit Antwerpen (BE) Institute for Social & Economic Research, University of Essex (UK) Bremen International Graduate School of Social Sciences, Universität Bremen (DE) Department of Dynamics of Organisations of Work, Centre d’Etudes de l’Emploi (FR) The Centre for European Policy Studies (BE) Dipartimento di Economica e Menagement, Università di Pisa (IT) Social Statistics Division, University of Southampton (UK) Luxembourg Income Study, asbl (LU) WageIndicator Foundation (NL) School of Social Sciences, The University of Manchester (UK)

Partners Co-ordinator

Inclusive Growth Research Infrastructure Diffusion Contract No 312691 For further information about the InGRID project, please contact inclusive.growth@kuleuven.be www.inclusivegrowth.be p/a HIVA – Research Institute for Work and Society Parkstraat 47 box 5300 3000 Leuven Belgium

Guy Van Gyes Monique Ramioul

InGRID