Download presentation
Presentation is loading. Please wait.
Published byDoris Dalton Modified over 9 years ago
1
Do Response Rates Matter in Online Panels? Representativity at Different Levels of Cumulative Response Rates Johan Martinsson University of Gothenburg www.lore.gu.se
2
About response rates RR used to be the main indicator of data quality Perhaps today more questionable (e.g. Groves & Peytcheva 2008) Moving to online surveys and panels, even more so Are participation rates for online panels meaningful?
3
www.mod.gu.se Yeager et al. 2011, pp. 731
4
www.mod.gu.se Participation rates in 163 surveys from the Citizen Panel at the University of Gothenburg The most important predictor is the demographic composition of the invited sample
5
www.mod.gu.se Moving to more controlled comparison: the probability based part of the Citizen Panel The emerging indicator is now Cumulative Response Rate for probability based panels CRR = Recr.Rate * Profile rate * Participation rate Both recruitment rates and CRRs are usually low And it is not clear how important they are
6
www.mod.gu.se Briefly about the Citizen Panel and LORE Started in 2010 with support from the University of Gothenburg The Citizen Panel has approx. 9,000 members from probability based recruitments from population samples And approximately 57,000 members from opt-in recruitments You can read more at www.lore.gu.sewww.lore.gu.se
7
www.mod.gu.se Response rates in web panels In 2012 LORE conducted a large probability recruitment with an experimental design This results in variation in recruitment rates
8
www.mod.gu.se Recruitment rates in 9 different treatment groups
9
www.mod.gu.se Questions What happens to response rates and CRR over time in a panel? How are they related to accuracy/representativity?
10
www.mod.gu.se How to examine representativeness/accuracy We calculate average absolute deviations from a good benchmark 6 demographic indicators –Gender, age, country of birth, marital status, education, labour market situation –These benchmarks come from Statistics Sweden –Four of these also register data in the sample
11
www.mod.gu.se How to examine representativeness/accuracy 2 political indicators (quasi benchmarks) –Interest in politics (from the SOM Institute survey, mail, n=6000) –Vote intention (Statistics Sweden, RDD, n=9000)
12
www.mod.gu.se
13
1. What happens to CRR over time in a panel?
14
www.mod.gu.se
15
Initial span 8.4 pct After two yrs 2.7 pct Higher RR => higher attrition Incentives recruitment => higher attrition
16
www.mod.gu.se 2. How are RR and CRR related to accuracy/representativity? First, we examine the accuracy at the recruitment Next, accuracy over time in the panel
17
www.mod.gu.se 2. How are RR and CRR related to accuracy/representativity? At recruitment we have 11 treatment groups with different recruitment rates between 6 and 21 percent We examine the average the AAD for the 8 indicators
18
www.mod.gu.se All 8 indicators r=-.61
19
www.mod.gu.se r=-.30 All 8 indicators
20
www.mod.gu.se Vote intention (8 parties) r=-.44
21
www.mod.gu.se Vote intention (8 parties) r=-.14
22
www.mod.gu.se 2. How are RR and CRR related to accuracy/representativity? We observe a weak correlation at the recruitment stage But what about later on? For that purpose we have a smaller set of groups that allow strict comparisons We examine representativeness 2 years later (8 panel waves later)
23
www.mod.gu.se Standard postcards: all 8 indicators Standard card no reminder Standard card 1 reminder CRRAADCRRAAD Wave 0 5.89.8 Wave 1 4.77.3 Wave 8 2.74.8
24
www.mod.gu.se Standard postcards: all 8 indicators Standard card no reminder Standard card 1 reminder CRRAADCRRAAD Wave 0 5.87.29.86.9 Wave 1 4.77.57.36.6 Wave 8 2.78.44.88.2
25
www.mod.gu.se Standard postcards: 2 political indicators Standard card no reminder Standard card 1 reminder CRRAADCRRAAD Wave 0 5.86.69.86.0 Wave 1 4.77.67.36.4 Wave 8 2.710.14.88.5
26
www.mod.gu.se Incentive postcards: all 8 indicators Incentive card no reminder Incentive card 1 reminder CRRAADCRRAAD Wave 0 9.314.2 Wave 1 6.49.5 Wave 8 3.65.2
27
www.mod.gu.se Incentive postcards: all 8 indicators Incentive card no reminder Incentive card 1 reminder CRRAADCRRAAD Wave 0 9.36.514.26.9 Wave 1 6.47.79.57.4 Wave 8 3.69.25.28.6
28
www.mod.gu.se Incentive postcards: 2 political indicators Incentive card no reminder Incentive card 1 reminder CRRAADCRRAAD Wave 0 9.34.314.25.9 Wave 1 6.44.89.56.4 Wave 8 3.67.05.29.7
29
www.mod.gu.se Did you notice something peculiar? Standard card no reminder Standard card 1 reminder CRRAADCRRAAD Wave 0 5.87.29.86.9 Wave 1 4.77.57.36.6 Wave 8 2.78.44.88.2
30
www.mod.gu.se Incentive card no reminder Incentive card 1 reminder CRRAADCRRAAD Wave 0 9.36.514.26.9 Wave 1 6.47.79.57.4 Wave 8 3.69.25.28.6 Did you notice something peculiar?
31
www.mod.gu.se Summing up High initial recruitment rates deteriorate substantially over time and differences diminish Higher cumulative response rates consistently yield lower average errors... –... when comparing over time within a recruitment cohort –... and when comparing between cohorts at same wave / panel age But panel attrition seems to play a part independent of cumulative response rates (because not at random) Overall, correlations btw CRR and accuracy seem low Caveats: small samples for accuracy, unweighted data, limited variation in recruitment rates and CRRs
32
www.mod.gu.se Read more at www.lore.gu.se Laboratory of Opinion Research (LORE) www.lore.gu.se
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.