Week 4 discussion

Week 4 discussion

by Emily -

This was more difficulty than I thought it would be because it seems like sometimes the design can be both time since enrollment and something else? Looking forward to seeing others examples.

 

Murray, L. (1992). The impact of post-natal depression on infant development. The Journal of Child Psychology and Psychiatry. 33(3)

http://onlinelibrary.wiley.com/doi/10.1111/j.1469-7610.1992.tb00890.x/abstract

 

The research question: The principal aim of the investigation was to compare the cognitive, social and emotional development of infants of mothers with unipolar, non-psychotic postnatal depression with that of infants of non-depressed mothers.

 

The study sample: 702 women presenting on the postnatal wards of the Cambridge maternity hospital during the period February 1986-February 1988 who met the inclusion criteria relating to health history and birth outcome.

 

The longitudinal design: The exposure was maternal depression and the outcome was cognitive and language development of the infant. While the time component was age of the infant, the exposure was measured in post-partum months and not age of the mothers. Infants were assessed at 9 and 18 months. Mothers were assessed at 6, 12, and 18 months. A subsample of mother-infant diads were assessed every 2-3 months.

 

The analysis approach: Mothers whose depression developed later in the infants first year were excluded. Comparisons between infants were made based on exposure to maternal postpartum depression, style of interpersonal contact associated with depression, history of depression or postpartum depression. Covariates included maternal education, employment, social class, paternal psychiatric history, marital friction, infant gender. Regression analysis was used to examine the effects of the duration of depression. All two-way interactions were tested.

 

Becoming married and mental health: a longitudinal study of a cohort of young adults

https://www.jstor.org/stable/353978?seq=1#page_scan_tab_contents

The research question: Do becoming and staying married enhance mental health after controls for premarital rates of disorder? Do becoming and staying married benefit the mental health of women as well as women when male as well and female related outcome variables are considered? How are becoming and staying married linked to mental health?

 

The study sample: Subjects were identified through a telephone survey using random digit dialing, between 1979-1981 from counties in New Jersey. Quota sampling guided initial phase of obtaining subjects and targets were 450 subjects each year evenly divided by age (three groups) and gender.

 

The longitudinal design – Time since enrollment. Surveys were administered at the time of enrollment (T1), 3 years later (T2), and three years after that (T3). 91% of the sample completed the final assessment 7 years after T3 (T4).

 

The analysis approach: Scales for depression and alcohol use were administered at every time. Marriage was coded as a binary variable. Analysis included comparison of gender and marital status in depression and alcohol use scales. Regression models to predict marital status and depression at T4, marital status and depression at T3 on depression at T4, and marital status, depression at T3, and gender on depression at T4 were all fitted.

 

Filippi et al. (2007). Health of women after severe obstetric complications in Burkino Faso: a longitudinal study. Lancet. (370). 1329-37.

https://www.ncbi.nlm.nih.gov/pubmed/17933647

The research question: How do severe obstetric complications affect a range of health and other outcomes in the year after the end of pregnancy in hospitals in Burkina Faso?

 

The study sample: a prospective cohort of women with severe obstetrical complications recruited in hospitals when their pregnancy ended with a live birth, perinatal death, and a lost pregnancy. For all cases of obstetric complications, two unmatched controls were sampled from among normal births concurrently as the cases with sever obstetric complications were recruited.

 

The longitudinal design – Time since end of pregnancy. Baseline data was collected at 3 days post-partum, followup interviews at 3, 6, and 12 months after pregnancy ended.

 

The analysis approach: The sample size was determined with the goal of detecting an approximate 10% risk difference between complicated and uncomplicated cases for outcomes with prevalence between 25% and 75%, and the power between 80% and 90%. Determining differences in mortality were not the objective. Women were stratified into groups by birth outcome and unadjusted and adjusted odds ratio were calculated. Fisher's exact test to compare death rates between women with severe complications and those with uncomplicated births. Cox regression was used to calculate hazard ratios.

 

Re: Week 4 discussion

by Francois Rerolle -

Agreed! In my second example, I think time since study enrollment is the time dimension but in order to assess the effect of their intervention, time since intervention was used as well. Yet it seems it is "delayed" by a fixed number of days for every study participants so I am not sure if that's another time dimension...

Re: Week 4 discussion

by Luis Rodriguez -

Hi Emily,

For your example #1 on postnatal depression and infant development, it seems that the time component was time since birth and exposure was depression-months. You made a good observation about introducing another time factor: mother's age, though it's not clear that the author considered this. I'm curious to hear what your thoughts on this are.   

Re: Week 4 discussion

by Maria Glymour -

Emily,

The Murray paper is really a train wreck to read- they have such a complicated study strategy it's effectively 3 studies in 1.  The core analysis though focused on children's outcomes at 18 months, and analyzed only a single outcome wave for each child, predicted by characteristics of the mom.  So in essence they did not use repeated measures even though their design provided repeated measures on a subsample of children.  In theory they might have gotten additional power by incorporating the data from the subsample of children followed every 2-3 months into the analysis for 18 month outcomes - and a mixed model might have allowed them to do that with such unbalanced data.  However, with kids that little it's hard to identify an outcome that is appropriate at all these ages - ie assessments at 9 months are not appropriate for 18 month olds, so putting them all into one model can be tricky.   In general, when you encounter such an overwhelming paper, it's useful to focus on the assessment of the outcome as used in their analyses (one outcome per person?), and then work backwards to how they were assessing the exposure. 

The Horvitz paper also uses one outcome wave (T4) in their analysis, even though they give a lot of not necessarily important background information about the design of the larger study, which includes repeated measures.  They did some odd things in their analysis, eg dropping people who were married before T3 or married and divorced between T3 and T4.  They discuss these analytic decisions as problematic but couldn't see a better solution - this is a place where a mixed model with a time-updated exposure status would have been appropriate and very useful to them, but I think it would have been somewhat unusual for applied researchers to estimate such a model in 1996 (when this paper was published... and figure they did the research in 1994 or 1995). 

The Filippi paper is very interesting (and thank you for selecting something in the last decade).  This is another case where they could have used a mixed model or a GEE to help understand the time course of depression post-complication.  They have repeated measures (3 mos, 6 mos, 12 mos) but analyze them separately rather than in a single model.  That's a shame because for example the coefficient for 3 months and 6 month overall complications predicting depression is almost identical but not quite statistically significant at 6 months... and they conclude there's no significant difference after 3 months.  If they had used a mixed model they could have described an elevation at 3 months and a time trend of (perhaps quite subtle) reductions in depression over time.  Cool paper.