Search

Psychological researchers often use standard linear regression to identify relevant predictors of an outcome of interest, but challenges emerge with incomplete data and growing numbers of candidate predictors. Regularization methods like the LASSO can reduce the risk of overfitting, increase model interpretability, and improve prediction in future samples; however, handling missing data when using regularization-based variable selection methods is complicated. Using listwise deletion or an ad hoc imputation strategy to deal with missing data when using regularization methods can lead to loss of precision, substantial bias, and a reduction in predictive ability. In this tutorial, we describe three approaches for fitting a LASSO when using multiple imputation to handle missing data and illustrate how to implement these approaches in practice with an applied example. We discuss implications of each approach and describe additional research that would help solidify recommendations for best practices. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Health-science researchers often measure psychological constructs using multi-item scales and encounter missing items on some participants. Multiple imputation (MI) has emerged as an alternative to ad-hoc methods (e.g., mean substitution) for handling incomplete data on multi-item scales, appealingly reflecting available information while accounting for uncertainty due to missing values in a unified inferential framework. However, MI can be implemented in a variety of ways. When the number of variables to impute gets large, some strategies yield unstable estimates of quantities of interest while others are not technically feasible to implement. These considerations raise pragmatic questions about the extent to which ad-hoc procedures would yield statistical properties that are competitive with theoretically motivated methods. Drawing on an HIV study where depression and anxiety symptoms are measured with multi-item scales, this empirical investigation contrasts ad-hoc methods for handling missing items with various MI implementations that differ as to whether imputation is at the item-level or scale-level and how auxiliary variables are incorporated. While the findings are consistent with previous reports favoring item-level imputation when feasible to implement, we found only subtle differences in statistical properties across procedures, suggesting that weaknesses of ad-hoc procedures may be muted when missing data percentages are modest.

Youth at-risk for HIV are also at-risk for mental health disorders and psychiatric hospitalization. Understanding the association between engagement in HIV prevention, concurrent risk behaviors, and psychiatric hospitalization may lead to improvements in integrated prevention and mental health treatment efforts. Youth at-risk for HIV, aged 14-24 years old, predominantly Black/African American and Latinx (75%) were recruited through youth-serving clinics and community sites in Los Angeles (n = 839) and New Orleans (n = 647). We compared youth with and without histories of psychiatric hospitalization on engagement in HIV prevention, concurrent risk behaviors, and demographic characteristics. We examined predictors of hospitalization using multiple imputations for missing data. Hospitalized youth (30%) were more involved in HIV programs, but were less likely to use PrEP/PEP or condoms than non-hospitalized youth. The odds of hospitalization were higher for transgender/gender nonconforming youth relative to cisgender youth; the OR was increased after adjustment for concurrent risk behaviors. Hospitalization was associated with homelessness, trauma, incarceration, substance use, and involvement in substance abuse treatment programs. There is a continuing need to integrate the diagnosis and treatment of mental health disorders into HIV prevention programs to better address multiple challenges faced by vulnerable youth.

BackgroundHome visits by paraprofessional community health workers (CHWs) has been shown to improve maternal and child health outcomes in research studies in many countries. Yet, when these are scaled or replicated, efficacy disappears. An effective CHW home visiting program in peri-urban Cape Town found maternal and child health benefits over the 5 years point but this study examines if these benefits occur in deeply rural communities.MethodsA non-randomized, two-group comparison study evaluated the impact of CHW in the rural Eastern Cape from August 2014 to May 2017, with 1310 mother-infant pairs recruited in pregnancy and 89% were reassessed at 6 months post-birth.ResultsHome visiting had limited, but important effects on child health, maternal wellbeing and health behaviors. Mothers reported fewer depressive symptoms, attended more antenatal visits and had better baby-feeding practices. Intervention mothers were significantly more likely to exclusively breastfeed for 6 months (OR: 1.8; 95% CI: 1.1, 2.9), had lower odds of mixing formula with baby porridge (regarded as detrimental) (OR: 0.4; 95% CI: 0.2, 0.8) and were less likely to consult traditional healers. Mothers living with HIV were more adherent with co-trimoxazole prophylaxis (p

ObjectiveThe consequences of maternal depressed mood on children's growth, health, and cognitive and language development are examined over the first 3 years of life.MethodPregnant women in 24 periurban township neighborhoods in Cape Town, South Africa (N = 1,238 mothers) were randomized by neighborhood to a home visiting intervention or a standard care condition. Reassessments were conducted for 93%-85% of mothers at 2-weeks, 6-, 18-, and 36-months postbirth. Regressions were conducted on measures of children's growth, behavior, language, and cognition to examine the impact of four patterns of depressed mood: antenatal only (n = 154, 13.8%), postnatal only (n = 272, 24.3%), antenatal and postnatal (n = 220, 19.7%), and no depressed mood on any assessment (n = 473, 42.3%).ResultsPatterns of depressed mood were similar across intervention conditions. Depressed mothers were significantly less educated, had lower incomes, were less likely to be employed or to have electricity; were more likely to report problematic drinking of alcohol, experience food insecurity, interpersonal partner violence, and to be HIV seropositive. At 36 months, the pattern of maternal depressed mood over time was significantly associated with children's compromised physical growth, both in weight and height, and more internalizing and externalizing symptoms of behavior problems. Measures of language and cognition were similar across maternal patterns of depressed mood.ConclusionsMothers who report depressed mood face significantly more life challenges, both environmental stressors related to poverty and other problematic behaviors. More proximal, postnatal depressed mood appears to have a larger influence on their children, compared with antenatal depressed mood. (PsycINFO Database Record

Background To slow the spread of the COVID-19 virus, governments across the globe instituted stay-at-home orders leading to increased stress and social isolation. Not surprisingly, alcohol sales increased during this period. While most studies primarily focused on alcohol consumption among college students or adults, this study investigates alcohol misuse among marginalized youth in the USA. We examined risk factors associated with hazardous alcohol use and binge drinking including risk behaviors, life stressors and demographic characteristics. Methods In October 2020, youth living with or at high risk for acquiring human immunodeficiency virus (HIV), participating in community-based research to improve HIV prevention and care, were invited to complete an online survey to assess the impact of the stay-at-home orders on multiple aspects of their daily life. Results Respondents (n  = 478) were on average 23 years old; cisgender (84%), not-heterosexual (86.6%), Latino or Black/African American (73%) and assigned male at birth (83%); 52% reported being employed and 14% reported living with HIV. White participants and those who use drugs had higher odds of hazardous alcohol use and binge drinking, compared with other race categories and non-drug users, respectively. Conclusion Contrary to findings from adult studies, we did not observe an increase in hazardous or binge drinking among youth at risk for HIV. Hazardous alcohol use and binge drinking was more likely among White participants, those who use drugs and those who were hazardous/binge drinkers prior to the COVID-19 lockdown, which points to the importance of identifying and treating youth who misuse alcohol early to prevent future alcohol misuse. [ABSTRACT FROM AUTHOR]

Multiple imputation (MI) is a powerful statistical method for handling missing data. Standard implementations of MI are valid under the unverifiable assumption of missing at random (MAR), which is often implausible in practice. The delta-adjustment method, implemented within the MI framework, can be used to perform sensitivity analyses that assess the impact of departures from the MAR assumption on the final inference. This method requires specification of unknown sensitivity parameter(s) (termed as delta(s)). We illustrate the application of the delta-adjustment method using data from the Longitudinal Study of Australian Children, where the epidemiological question is to estimate the association between exposure to maternal emotional distress at age 4.5 years and total (social, emotional, and behavioural) difficulties at age 8.9 years. We elicited the sensitivity parameters for the outcome (Y) and exposure (X) variables from a panel of experts. The elicited quantile judgements from each expert were converted into a suitable parametric probability distribution and combined using the linear pooling method. We then applied MI under MAR followed by sensitivity analyses under missing not at random (MNAR) using the delta-adjustment method. We present results from sensitivity analyses that used different percentile values of the pooled distributions for the delta parameters for Y and X, and demonstrate that twofold increases in the magnitude of the association between maternal distress and total difficulties are only observed for large departures from MAR. [ABSTRACT FROM AUTHOR]

Background: Differences between early-onset and late-onset adult asthma have not been comprehensively described using prospective data.Aims: To characterise the differences between early-onset and late-onset asthma in a longitudinal cohort study.Methods: The Tasmanian Longitudinal Health Study (TAHS) is a population-based cohort. Respiratory histories and spirometry were first performed in 1968 when participants were aged 7 (n=8583). The cohort was traced and resurveyed from 2002 to 2005 (n=5729 responses) and a sample, enriched for asthma and bronchitis participated in a clinical study when aged 44 (n=1389).Results: Of the entire TAHS cohort, 7.7% (95% CI 6.6% to 9.0%) had early-onset and 7.8% (95% CI 6.4% to 9.4%) late-onset asthma. Atopy and family history were more common in early-onset asthma while female gender, current smoking and low socioeconomic status were more common in late-onset asthma. The impact on lung function of early-onset asthma was significantly greater than for late-onset asthma (mean difference prebronchodilator (BD) FEV1/FVC -2.8% predicted (-5.3 to -0.3); post-BD FEV1FVC -2.6% predicted (-5.0 to -0.1)). However, asthma severity and asthma score did not significantly differ between groups. An interaction between asthma and smoking was identified and found to be associated with greater fixed airflow obstruction in adults with late-onset asthma. This interaction was not evident in adults with early-onset disease.Conclusions: Early-onset and late-onset adult asthma are equally prevalent in the middle-aged population. Major phenotypic differences occur with asthma age-of-onset; while both share similar clinical manifestations, the impact on adult lung function of early-onset asthma is greater than for late-onset asthma. [ABSTRACT FROM AUTHOR]

Background: Multiple imputation (MI) is a well-recognised statistical technique for handling missing data. As usually implemented in standard statistical software, MI assumes that data are 'Missing at random' (MAR); an assumption that in many settings is implausible. It is not possible to distinguish whether data are MAR or 'Missing not at random' (MNAR) using the observed data, so it is desirable to discover the impact of departures from the MAR assumption on the MI results by conducting sensitivity analyses. A weighting approach based on a selection model has been proposed for performing MNAR analyses to assess the robustness of results obtained under standard MI to departures from MAR.Methods: In this article, we use simulation to evaluate the weighting approach as a method for exploring possible departures from MAR, with missingness in a single variable, where the parameters of interest are the marginal mean (and probability) of a partially observed outcome variable and a measure of association between the outcome and a fully observed exposure. The simulation studies compare the weighting-based MNAR estimates for various numbers of imputations in small and large samples, for moderate to large magnitudes of departure from MAR, where the degree of departure from MAR was assumed known. Further, we evaluated a proposed graphical method, which uses the dataset with missing data, for obtaining a plausible range of values for the parameter that quantifies the magnitude of departure from MAR.Results: Our simulation studies confirm that the weighting approach outperformed the MAR approach, but it still suffered from bias. In particular, our findings demonstrate that the weighting approach provides biased parameter estimates, even when a large number of imputations is performed. In the examples presented, the graphical approach for selecting a range of values for the possible departures from MAR did not capture the true parameter value of departure used in generating the data.Conclusions: Overall, the weighting approach is not recommended for sensitivity analyses following MI, and further research is required to develop more appropriate methods to perform such sensitivity analyses. [ABSTRACT FROM AUTHOR]

Background: Missing data are common in medical research, which can lead to a loss in statistical power and potentially biased results if not handled appropriately. Multiple imputation (MI) is a statistical method, widely adopted in practice, for dealing with missing data. Many academic journals now emphasise the importance of reporting information regarding missing data and proposed guidelines for documenting the application of MI have been published. This review evaluated the reporting of missing data, the application of MI including the details provided regarding the imputation model, and the frequency of sensitivity analyses within the MI framework in medical research articles. Methods: A systematic review of articles published in the Lancet and New England Journal of Medicine between January 2008 and December 2013 in which MI was implemented was carried out. Results: We identified 103 papers that used MI, with the number of papers increasing from 11 in 2008 to 26 in 2013. Nearly half of the papers specified the proportion of complete cases or the proportion with missing data by each variable. In the majority of the articles (86%) the imputed variables were specified. Of the 38 papers (37%) that stated the method of imputation, 20 used chained equations, 8 used multivariate normal imputation, and 10 used alternative methods. Very few articles (9%) detailed how they handled non-normally distributed variables during imputation. Thirty-nine papers (38%) stated the variables included in the imputation model. Less than half of the papers (46%) reported the number of imputations, and only two papers compared the distribution of imputed and observed data. Sixty-six papers presented the results from MI as a secondary analysis. Only three articles carried out a sensitivity analysis following MI to assess departures from the missing at random assumption, with details of the sensitivity analyses only provided by one article. Conclusions: This review outlined deficiencies in the documenting of missing data and the details provided about imputation. Furthermore, only a few articles performed sensitivity analyses following MI even though this is strongly recommended in guidelines. Authors are encouraged to follow the available guidelines and provide information on missing data and the imputation process. [ABSTRACT FROM AUTHOR]