How Couples Meet and Stay Together 2017 (HCMST 2017)
- This new survey, How Couples Meet and Stay Together 2017, features a fresh set of 3,510 survey respondents, with no overlap in subjects from the original HCMST survey which was first fielded in 2009. The 2017 subjects were followed up in 2020 (2,107 subjects) and in 2022 (1,722) subjects.
- HCMST 2017 featured new questions about subjects' use of phone apps like Tinder and Grindr for dating and meeting partners.
- HCMST 2020 and 2022 featured the usual HCMST relationship questions plus a lot of new questions about the impacts of the coronavirus pandemic.
Michael J. Rosenfeld
Reuben J. Thomas
United Parcel Service Endowment at Stanford University
US National Science Foundation
How to Cite this Dataset:
Rosenfeld, Michael J., Reuben J. Thomas, and Sonia Hausen. 2023. How Couples Meet and Stay Together 2017-2020-2022 combined dataset. [Computer files]. Stanford, CA: Stanford University Libraries. https://data.stanford.edu/hcmst2017
- Text answers and geographic variables below region level are withheld from the public data, but will eventually be available in edited form as restricted data.
- The public data include codes of the open-text answers for how couples meet. How-met stories were coded by Sonia Hausen and Michael Rosenfeld, according to the rubric developed from the original How Couples Meet and Stay Together survey.
- Unlike the original HCMST survey, HCMST 2017 asked a full battery of questions to subjects with current partners (N=2862) and also to subjects with no current partner, but who had a past partner (N=541). See the variable "w1_partnership_status."
- Surveys were performed by online survey company Ipsos.
- The data are nationally representative, as the Ipsos KnowledgePanel recruits subjects into the panel by by Address Based Sampling, and subjects without Internet access at home are given Internet access.
- Self-identified Lesbian, Gay, and Bisexual respondents were oversampled.
- The question numbering in HCMST 2017 replicates, where possible, the question numbering for HCMST 2009 for the same questions. This means that some numbers appear to be skipped in the HCMST 2017 survey instrument, but nothing is missing; it simply means that those missing number questions (e.g., Q30, Q31, Q33) were asked in HCMST 2009 but not repeated in HCMST 2017.
- These data and documentation will also eventually be deposited to ICPSR, but changes and updates appear here first.
Funding for HCMST 2017 comes from Stanford's United Parcel Service Endowment, and this funding is gratefully acknowledged. HCMST 2017 surveyed a new cohort of subjects, building on the prior work around HCMST 2009. HCMST 2009 was generously supported by the National Science Foundation, grants SES-0751977 and SES-1153867. HCMST 2020 and 2022 were funded by National Science Foundation grant SES- 2030593.
English literate adults in the United States
Unit of Analysis:
Type of data collection:
Time of data collection:
July 13, 2017-August 1, 2017; September-October 2020; March-April 2022
Smallest geographic unit:
Census Region is the smallest geographic unit in the public data
Sample response rate:
Response rate was 3510/6753=52% in 2017, 2107/2431= 87% in 2020, and 1722/2073=83% in 2022. The Denominators in 2020 and 2022 include only subjects who remained in the KnowledgePanel, as they were the only subjects eligible to be contacted. To account for the response rates of prior inclusion into Ipsos' KnowledgePanel, see Callegaro, Mario, and Charles DiSogra. 2008. "Computing Response Metrics for Online Panels." Public Opinion Quarterly 72 (5):1008-1032.
- variable "w1_weight_combo" combines the weights for the general population respondents and the LGB oversample, with mean=1, for 2017.
- "w1_weight_combo_freqwt" weights the subjects up to the CPS marginals, mean=69,410 (meaning the survey is approximately a 1-in-69,000 survey of American adults).
- See the user's guide for information
Read the short user's guide first!
Data Use Agreement
- The data I download from the Data Archive will not be used to identify individuals.
- I will not charge a fee for the data if I distribute it to others.
- I will inform the contact person for each dataset about work I do using their dataset.
(This helps us keep an accurate bibliography. See each data page for its contact email.)
- I will cite the data appropriately.
(See each data page for its bibliographic citation.)
Data Download Links
- Stata version 2.2
- SPSS version 2.2
- Rdata version 2.2 Note: the value labels are part of the R dataset but you have to deploy some tools to make use of the labels (for instance the 'labeled' package, the 'to_labeled' function, and tabular output from the tidyverse packages but your mileage may vary)
- Data supplements: Coded pandemic relationship effects 2020 and 2022, Stata version, SPSS version, RData version
Papers from HCMST 2017:
- M Rosenfeld 2018. "How Tinder and the Dating Apps are and are Not Changing Dating and Mating in the U.S., published book chapter found here.
- M Rosenfeld, RJ Thomas, and Sonia Hausen, 2019. "Disintermediating your Friends," in the Proceedings of the National Academy of Sciences.
- Thomas, Reuben J. 2019. "Online Exogamy Reconsidered: Estimated the Internet's Effect on Racial, Educational, Religious, Political, and Age Assortative Mating." Social Forces. Published version here.
- M Rosenfeld and Sonia Hausen, "Resilience and Stress in Romantic Relationships in the US during the COVID-19 Pandemic," forthcoming in Sociological Science, see also the appendix tables and a replication package.