Conducting Surveys in the Era of Cellphones: Review of the Use of Online Panels in the Medical Literature
Bibliographic record
Abstract
The number of surveys conducted online is growing as people gain Internet access and the barriers to the use of random digit dialling (RDD) as a survey tool increase. One method of recruiting respondents is via sampling of online panels. The main issues with the use online panels are selection bias and external validity. Response rate (RR) reflects external validity and is the most commonly reported measure of a survey's quality and generalisability. The purpose of this structured review on online panels in the medical literature was to summarise: What proportion of studies used stratified sampling; What proportion of studies were weighted by demographic or propensity weights; What proportion of studies reported RR and how it was calculated; Which limitations of online surveying were discussed. Medline and Embase were searched from Jan 2005 to May 2007 for English-language clinical or epidemiologic surveys about healthcare that recruited respondents from online panels. Inclusion and exclusion criteria were specified a priori. Of the 2,289 unique citations identified, 34 met the inclusion criteria. As part of their mandate to promote standards of professional conduct and ethics for surveys and public opinion research, the American Association for Public Opinion Research (AAPOR) provides standard definitions for calculating RR, which they define as the number of complete interviews with reporting units divided by the number of eligible reporting units in the sample. Nine studies stratified the sample to which invitations were sent and 9 weighted the results. Five studies did not discuss any limitations associated with the use of online panels. Eighteen studies mentioned selection bias and 27 mentioned external validity. Fifteen studies reported RR, ranging from 8% - 95%. The formula used to calculate RR for 14 of these was: (number of responses received)/(number of invitations sent). Six of these studies included enough information to allow recalculation of the RR as per the American Association for Public Opinion Research (AAPOR). The recalculation resulted in lower RRs for five studies and remained the same for the sixth study. Sampling of online panels for research purposes has not reached the sophistication of more traditional methods, and hence it is important for studies to transparently state what has been done to overcome the barriers and report the RRs. This structured review, however, demonstrated that a number of studies either did not employ stratified sampling or weighting or did not clearly state whether or not they did. Less than half of the studies reported an RR, but this was often not calculated as per AAPOR guidelines.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.031 | 0.125 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.003 |
| Bibliometrics | 0.024 | 0.034 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".