1. Age as the time dimension:
Title: Longitudinal Trends in Sexual Behaviors with Advancing Age and Menopause Among Women With and Without HIV-1 Infection available from AIDS Behav. 19(5): 931–940. doi: 10.1007/s10461-014-0901-1 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4370800/
- Research question: What is the relationship between aging, sexual activity and unprotected anal or vaginal intercourse among women with and without HIV-1 infection participating in the Women’s Interagency HIV Study (WIHS), in the United States?
- Study sample:
- WIHS participants in this analysis were drawn from six consortia (Washington, DC; San Francisco, CA Bay Area; Los Angeles, CA; Brooklyn, NY; Bronx, NY; and Chicago, IL).
- The WIHS enrolled women in 1994–95 and 2001–02. Women recruited in the first cohort (1994–95 )were either at-risk HIV-uninfected or HIV-infected women. In the second wave of recruitment (2001–02), HIV-infected women with an AIDS-related clinical condition or who acquired HIV perinatally were excluded.
- Study participants were recruited from HIV primary care clinics, hospital-based programs, research programs, community outreach sites, women's support groups, drug rehabilitation programs, HIV testing sites, and referrals from enrolled participants. To be eligible to participate in the WIHS, women had to be at least 13 years of age, give informed consent, be tested for HIV and participate in an English or Spanish interview, travel to and from the research site and provide blood for laboratory testing at baseline
- The investigatorsexamined data from 66,055 WIHS person-visits representing 3,847 women over 13 years of follow-up. They retained 39,812 person-visits, contributed by 1,927 HIV-infected and 742 HIV-uninfected women over 13 years of follow up.
- Longitudinal design: Follow up was done every 6 months for 13 years and comprised of a structured, face-to-face interview lasting, physical and gynecologic examinations, oral examination, tuberculin and skin testing, laboratory specimen collection, and medical record abstraction for all hospitalizations and AIDS- defining and other HIV-related conditions. A subset of the baseline visit data were collected at follow-up visits.
- Analysis approach. Specifically regarding age: They constructed generalized mixed linear models using age as a linear predictor The outcomes were modeled as Bernoulli-distributed (discrete distribution having two possible outcomes); a logit link-function was applied. Autocorrelation among observations coming from the same subject on successive visits was modeled as a first-order autoregressive, first-order moving average (ARMA 1, 1) process (the moving average basically specifies that the output variable depends linearly on the current and various past values of a stochastic (imperfectly predictable) term). Satterthwaite adjustments were made to denominator degrees of freedom. Seven plausible covariates (race, education, heavy drinking, current drug use, depression, physical function and follow-up duration) were added to the model. Analyses were conducted using SAS 9.2 (SAS Institute, Cary, NC).
- Time since study enrollment as the time dimension
Title: Long-Term Impact of Malaria Chemoprophylaxis on Cognitive Abilities and Educational Attainment: Follow-Up of a Controlled Trial PLOS clinical trials available from http://journals.plos.org/plosclinicaltrials/article?id=10.1371/journal.pctr.0010019
- Research question: What is the long-term educational and cognitive effect of malaria chemoprophylaxis in early childhood.
- Study sample: children aged 3–59 months of age living in 15 villages situated between 32 km to the east and 22 km to the west of the town of Farafenni, the Gambia, on the north bank of the River Gambia, approximately 100 km from the coast
- Longitudinal design: children aged 3–59 months participated in a malaria chemoprophylaxis (dapsone/pyrimethamine) (vs placebo) trial for between one and three malaria transmission seasons from 1985 to 1987 and were followed up after 10 years in 2001 when their median age was 17 y 1 month (range 14 y 9 months to 19 y 6 months).
- Analysis approach: The investigators looked at intervention effects according to the number of years of post-trial prophylaxis received. They first grouped the participants into four categories according to the number of years for which they were eligible for post-trial prophylaxis: 0 y, 0 to 1 y, 1 to 2 y, and 2 y or more. They then did regression analyses of cognitive function. They also tested for interaction between intervention group and duration of post-trial prophylaxis in their effects on cognitive function and interaction between the intervention and gender was explored.
- one other possible time dimension (i.e, not age or time since study enrollment).
Title: Longitudinal changes in engagement in care and viral suppression for HIV-infected injection drug users AIDS. 2013; 27(16): 2559–2566. doi: 10.1097/QAD.0b013e328363bff2 Available from https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3795966/
- Research question: What are the temporal trends and predictors of linkage to HIV care, longitudinal retention in care and viral suppression among injection drug users (IDUs) infected with HIV?
- Study sample: 790 HIV-infected injection drug users (IDUs) participating in the AIDS Linked to the Intravenous Experience (ALIVE) study from 1998 through 2011. Participants are predominantly low-income, African–American, inner-city residents, characteristics that are representative of the population of individuals who inject drugs in Baltimore and similar cities in the Northeastern and Mid-Atlantic United States
- Longitudinal design: This was a community-based, longitudinal cohort study that followed IDUs in Baltimore from 1988. Participants provide information about socio-demographic characteristics, drug injecting and other HIV risk behaviors, and general medical history as well as information on receipt of HIV-oriented outpatient clinical care and utilization of antiretroviral medications at baseline and semiannually.
- analysis approach:
The investigators looked at
1. temporal trends in engagement in care across the entire cohort: Here, they calculated the proportion of participants reporting HIV care visits in each calendar year. They then used a linear trend time-series model with a first-order auto-regressive covariance. They determined whether there were significant improvements from 1998 to 2011 in the annual proportion of the cohort that was fully engaged in care (in care all at both ALIVE visits during the year), was partially engaged in care (in care at 1 of 2 study visits) and achieved an undetectable HIV RNA level.
2. Time-varying factors associated with the two main negative outcomes, lapses in HIV care and virologic failure. The outcomes were assessed at every follow-up study visit and thus could be experienced multiple times during the study. A lapse in care was defined as reporting that no HIV care visits were attended in the prior 6 months after being in care at the previous study visit. Virologic failure was evaluated using the same framework: study visits at which a participant was noted to have viral suppression were analyzed to determine whether the viral load remained suppressed at the subsequent visit (success) or had increased above the limit of detection (failure). Analysis: To identify significant predictors of the outcomes while accounting for intra-subject correlation resulting from repeated measures per participant, they used logistic regression models with generalized estimating equations (GEE) with robust variance estimates. An alpha level of 0.10 and 0.05 were used for model entry and retention, respectively. To account for the potential confounding effects of secular trends favoring improved engagement in care over time and differential loss to follow-up among higher-risk IDUs, they forced into the adjusted models variables for calendar year and total follow-up time, respectively.