Carl Bonander1, Anton Nilsson2, Jonas Björk3, Göran M L Bergström4, Ulf Strömberg5. 1. Health Metrics Unit, Institute of Medicine, The Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden. Electronic address: carl.bonander@gu.se. 2. Division of Occupational and Environmental Medicine, Lund University, Lund, Sweden; Centre for Economic Demography, Lund University, Lund, Sweden. 3. Division of Occupational and Environmental Medicine, Lund University, Lund, Sweden; Clinical Studies Sweden, Forum South, Skåne University Hospital, Lund, Sweden. 4. Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, Sahlgrenska University Hospital, University of Gothenburg, Gothenburg, Sweden. 5. Health Metrics Unit, Institute of Medicine, The Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden; Research and Development, Region Halland, Halmstad, Sweden.
Abstract
OBJECTIVE: To investigate whether inverse probability of participation weighting (IPPW) using register data on sociodemographic and disease history variables can improve external validity in a cohort study with selective participation. STUDY DESIGN AND SETTING: We fitted various IPPW models by logistic regression using register data for the participants (n = 1,111) and nonparticipants (n = 1,132) of a Swedish cohort study. For each of six diagnostic groups, we then estimated (1) weighted disease prevalence proportions and (2) weighted cross-sectional associations (odds ratios) between sociodemographic variables and disease prevalence. Using register data on the remaining individuals of the entire study population of men and women aged 50-64 years (n = 22,259), we addressed how the choice of variables used for IPPW influenced estimation errors. RESULTS: Disease prevalence proportions were generally underestimated in the absence of IPPW but became markedly closer to population values after IPPW using sociodemographic variables. We found limited evidence of selective participation bias in association estimates, but IPPW improved external validity when bias was present. CONCLUSIONS: IPPW using sociodemographic register data can improve the external validity of disease prevalence estimates in cohort studies with selective participation. The performance of IPPW for association estimates merits further investigations in longitudinal settings and larger cohorts.
OBJECTIVE: To investigate whether inverse probability of participation weighting (IPPW) using register data on sociodemographic and disease history variables can improve external validity in a cohort study with selective participation. STUDY DESIGN AND SETTING: We fitted various IPPW models by logistic regression using register data for the participants (n = 1,111) and nonparticipants (n = 1,132) of a Swedish cohort study. For each of six diagnostic groups, we then estimated (1) weighted disease prevalence proportions and (2) weighted cross-sectional associations (odds ratios) between sociodemographic variables and disease prevalence. Using register data on the remaining individuals of the entire study population of men and women aged 50-64 years (n = 22,259), we addressed how the choice of variables used for IPPW influenced estimation errors. RESULTS: Disease prevalence proportions were generally underestimated in the absence of IPPW but became markedly closer to population values after IPPW using sociodemographic variables. We found limited evidence of selective participation bias in association estimates, but IPPW improved external validity when bias was present. CONCLUSIONS: IPPW using sociodemographic register data can improve the external validity of disease prevalence estimates in cohort studies with selective participation. The performance of IPPW for association estimates merits further investigations in longitudinal settings and larger cohorts.
Authors: Göran Bergström; Margaretha Persson; Martin Adiels; Elias Björnson; Carl Bonander; Håkan Ahlström; Joakim Alfredsson; Oskar Angerås; Göran Berglund; Anders Blomberg; John Brandberg; Mats Börjesson; Kerstin Cederlund; Ulf de Faire; Olov Duvernoy; Örjan Ekblom; Gunnar Engström; Jan E Engvall; Erika Fagman; Mats Eriksson; David Erlinge; Björn Fagerberg; Agneta Flinck; Isabel Gonçalves; Emil Hagström; Ola Hjelmgren; Lars Lind; Eva Lindberg; Per Lindqvist; Johan Ljungberg; Martin Magnusson; Maria Mannila; Hanna Markstad; Moman A Mohammad; Fredrik H Nystrom; Ellen Ostenfeld; Anders Persson; Annika Rosengren; Anette Sandström; Anders Själander; Magnus C Sköld; Johan Sundström; Eva Swahn; Stefan Söderberg; Kjell Torén; Carl Johan Östgren; Tomas Jernberg Journal: Circulation Date: 2021-09-20 Impact factor: 29.690
Authors: Carl Bonander; Anton Nilsson; Jonas Björk; Anders Blomberg; Gunnar Engström; Tomas Jernberg; Johan Sundström; Carl Johan Östgren; Göran Bergström; Ulf Strömberg Journal: PLoS One Date: 2022-03-08 Impact factor: 3.240
Authors: Megan E Marziali; Taylor McLinden; Kiffer G Card; Kalysha Closson; Lu Wang; Jason Trigg; Kate Salters; Viviane D Lima; Surita Parashar; Robert S Hogg Journal: AIDS Behav Date: 2021-02
Authors: Lars Barregard; Gerd Sallsten; Florencia Harari; Eva M Andersson; Niklas Forsgard; Ola Hjelmgren; Oskar Angerås; Erika Fagman; Margaretha Persson; Thomas Lundh; Yan Borné; Björn Fagerberg; Gunnar Engström; Göran Bergström Journal: Environ Health Perspect Date: 2021-06-23 Impact factor: 9.031