Specification curve analysis shows that social media use is linked to poor mental health, especially among girls
[ABSTRACT READ IN FULL at the Europe PMC core record, PMID 35101738; author order confirmed at api.crossref.org, Twenge sequence 'first'. CC-BY. FULL TEXT NOT READ, AND THE SPECIFICATION TABLES WERE NOT REACHED ON THIS PASS, so only the published abstract's coefficient range is held and no table value is reported here] Twenge, J. M., Haidt, J., Lozano, J., & Cummins, K. M. (2022). 'Specification curve analysis shows that social media use is linked to poor mental health, especially among girls.' Acta Psychologica, 224, 103512. doi:10.1016/j.actpsy.2022.103512. THE OTHER SIDE OF THE SAME METHOD ON THE SAME DATA, AND THE REASON THIS ARTICLE EXISTS. Design: re-ran specification curve analysis on THE SAME THREE community datasets used by Orben and Przybylski 2019, under four altered specification constraints, namely social media separated out from lumped total screen time, boys and girls analysed separately, potential mediators excluded from the control set, and scales weighted equally. RESULT: under the original configuration they REPRODUCED the original result, median betas of about minus 0.01 to minus 0.04; under the revised constraints, AMONG GIRLS, median betas of about minus 0.11 to minus 0.24. They report these associations as stronger than those for binge drinking, sexual assault, obesity and hard drug use and conclude they 'may have substantial practical significance'. THE CORRECTION THIS BATCH EXISTS TO CARRY: the seed book's endnotes report this paper's result as a single correlation coefficient, and the published paper contains no such figure. CITE THE MEDIAN BETA RANGE, in anyone's voice, and do not print the single coefficient. THE LIMIT: same data, same correlational design, different specification. It demonstrates that the headline size is a function of analytic choices, which is a finding about the literature rather than about children, and it adds no causal evidence.
[ABSTRACT READ IN FULL at the Europe PMC core record, PMID 35101738; author order confirmed at api.crossref.org, Twenge sequence 'first'. CC-BY. FULL TEXT NOT READ, AND THE SPECIFICATION TABLES WERE NOT REACHED ON THIS PASS, so only the published abstract's coefficient range is held and no table value is reported here] Twenge, J. M., Haidt, J., Lozano, J., & Cummins, K. M. (2022). 'Specification curve analysis shows that social media use is linked to poor mental health, especially among girls.' Acta Psychologica, 224, 103512. doi:10.1016/j.actpsy.2022.103512. THE OTHER SIDE OF THE SAME METHOD ON THE SAME DATA, AND THE REASON THIS ARTICLE EXISTS. Design: re-ran specification curve analysis on THE SAME THREE community datasets used by Orben and Przybylski 2019, under four altered specification constraints, namely social media separated out from lumped total screen time, boys and girls analysed separately, potential mediators excluded from the control set, and scales weighted equally. RESULT: under the original configuration they REPRODUCED the original result, median betas of about minus 0.01 to minus 0.04; under the revised constraints, AMONG GIRLS, median betas of about minus 0.11 to minus 0.24. They report these associations as stronger than those for binge drinking, sexual assault, obesity and hard drug use and conclude they 'may have substantial practical significance'. THE CORRECTION THIS BATCH EXISTS TO CARRY: the seed book's endnotes report this paper's result as a single correlation coefficient, and the published paper contains no such figure. CITE THE MEDIAN BETA RANGE, in anyone's voice, and do not print the single coefficient. THE LIMIT: same data, same correlational design, different specification. It demonstrates that the headline size is a function of analytic choices, which is a finding about the literature rather than about children, and it adds no causal evidence.
Written from the aBSTRACT READ IN FULL at the Europe PMC core record, PMID 35101738; author order confirmed at api.crossref.org, Twenge sequence 'first'. CC-BY. FULL TEXT NOT READ, AND THE SPECIFICATION TABLES WERE NOT REACHED ON THIS PASS, so only the published abstract's coefficient range is held and no table value is reported here.
What our sources record
Recorded when this source was checked, figures included, with page references and quotation marks removed.
Twenge, J. M., Haidt, J., Lozano, J., & Cummins, K. M. (2022). Specification curve analysis shows that social media use is linked to poor mental health, especially among girls. Acta Psychologica, 224, 103512. doi:10.1016/j.actpsy.2022.103512