
Hard-to-Survey Populations at rebro University Statistics Sweden
Explore the challenges of surveying hard-to-reach populations presented at the Baltic-Nordic Conference on Survey Statistics held at rebro University. Understand the definition, current situation in Sweden, and strategies for surveying these populations effectively.
Download Presentation

Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Hard-to-Survey Populations Baltic-Nordic Conference on Survey Statistics, rebro University Johan L fgren, Statistics Sweden
Outline Introduction Definition of hard-to-survey populations Present situation at Statistics Sweden Discussion
Introduction Negative trend in individual surveys with increasing non-response Accelerated even more in hard-to-survey populations Young people, vulnerable people and new arrivals to Sweden Growing public interest in statistics for these kind of populations Several surveys where the may be doubts about survey quality
Definition of hard-to-survey populations Hard-to-survey populations are populations presenting challenges, which makes them harder to survey than a general population 2012 the International Conference on Methods for Surveying and Enumerating Hard-to-Reach Populations was held in New Orleans, USA The conference led to the book Hard-to-Survey Populations compiled by Tourangeau et al. (2014)
Definition of hard-to-survey populations Population Hard-to -Sample Challenge Those who are difficult to include in a statistical sample Those who are difficult to identify as eligible survey respondents Those who are difficult to find and to make contact with for purposes of engaging in a survey -Identify -Reach -Persuade Those who are difficult to convince to take part in a survey, once located Those who are willing to be interviewed, but who are difficult to successfully interview -Interview
Present situation at Statistics Sweden Increased demand in surveys directed towards hard-to-survey populations Young people People who have recently immigrated to Sweden Combination of young and recently immigrated Mainly populations that are hard to reach, hard to persuade and/or hard to interview Sampling and identifying these populations usually not the main issue
Present situation at Statistics Sweden Surveys directed at hard-to-survey populations are mainly surveys done on commission work for researchers, government agencies and other organizations Standardized survey design Sampling: stratified random sample from a sampling frame Data collection: web/paper questionnaire and/or telephone interviews Weighting: adjustment of design weights by use of a standard set of auxiliary variables
Present situation at Statistics Sweden Examples of hard-to-survey groups in surveys done by Statistics Sweden Reasons for Hard-To-Survey Response rate Population People born in 1991- 1994, without exam from secondary education People in the age 16-29 Topic Why young people do not finish secondary education Health H2 Reach H2 Persuade H2 Interview Data collection Web questionnaire + telephone interviews Language: Swedish Web + paper questionnaire Language: Swedish Web questionnaire Language: Swedish X X X 28.0 Young population X 26.3 Children and youth, in the age 12-18 Contacts with government agencies X X 31.5 People in the age 16-29, born in Syria or Iraq, immigrated to Sweden 2008 or later People born in Syria 1952-88, immigrated to Sweden 2011-2013 Newly arrived children and youth, in the age 12- 18, born in Syria, Iraq or Afghanistan Health Paper questionnaire Languages:Swedish, Arabic X X 17.3 / 9.3 Newly arrived Health Paper questionnaire Language: Arabic X X 30.4 Health Paper questionnaire Languages:Swedish, Arabic, Persian X X 25.7
Present situation at Statistics Sweden Standardized strategies do not work well for hard-to-survey populations Response rates usually <30 % Today, Statistics Sweden has limited possibilities to offer alternative strategies to the client
Discussion Some initial work has been done regarding this issue: Project with the aim to identify strategies for getting in touch with people who we suspect are not fluent in the Swedish language (2018) Presentation for Statistic Sweden s Advisory Scientific Board (April 2019) Systematic competence building for hard-to-survey populations is planned for (autumn 2019)
Discussion Areas that Statistics Sweden has identified and would need to work more on: - Extend the use of auxiliary data for analyzing non-response and for weight adjustments - Provide better support for respondents who do not understand Swedish - Information campaigns to the respondents - Non-probability based methods (e.g. key-informant sampling, time-location sampling) - Qualitative studies - Indirect interviews - Incentives
Discussion Need to test and evaluate new methods Surveys directed towards hard-to-survey populations need to be more flexible Allocate more resources to surveys directed towards hard-to-survey populations What successful strategies is your organization using for hard-to-survey populations?