PloS one · 2026
Indirect state-level estimation of sexual minority adolescent populations by sex, age, and race/ethnicity using random forests.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Alves-Maciel Bruno, Pampati Sanjana, Fodeman Ari, Van Handel Michelle, Zheng Lijia, Ye Ziping, Yaesoubi Reza, Salomon Joshua A
Аннотация
PURPOSE: Estimating population sizes of adolescents who identify as lesbian, gay, or bisexual (LGB) is important for addressing health needs and disparities. Most states have Youth Risk Behavior Surveys (YRBS) among high school students, but not all include an item about sexual identity. This study's aim was to estimate the percentages of students identifying as LGB stratified by sex, age, and race and ethnicity where state data is incomplete. States where 2021 YRBS data are not available are outside the scope of this study.
METHODS: We developed two random forests trained separately for each sex and evaluated the models' performance in predicting percentages of respondents identifying as LGB by state and demographic strata. We then estimated percentages for states that did not include or have responses to the LGB identity question available in 2021.
RESULTS: The random forests outperformed benchmark comparison models based on a simple logistic regression approach. Estimates of students who identify as LGB across demographic strata and states ranged 5%-30%. The estimated percentages for states that did not ask students about sexual identity fell within the same range.
CONCLUSION: Our approach to deriving state-level estimates of LGB students by sex, race and ethnicity, and age performs well and can be used to inform efforts to improve health and well-being of LGB youth.
METHODS: We developed two random forests trained separately for each sex and evaluated the models' performance in predicting percentages of respondents identifying as LGB by state and demographic strata. We then estimated percentages for states that did not include or have responses to the LGB identity question available in 2021.
RESULTS: The random forests outperformed benchmark comparison models based on a simple logistic regression approach. Estimates of students who identify as LGB across demographic strata and states ranged 5%-30%. The estimated percentages for states that did not ask students about sexual identity fell within the same range.
CONCLUSION: Our approach to deriving state-level estimates of LGB students by sex, race and ethnicity, and age performs well and can be used to inform efforts to improve health and well-being of LGB youth.