Research question: Evaluate and synthesize randomized controlled trial (RCT) study designs that investigated the effects of physical activity on working memory performance in healthy individuals.
Main inclusion criteria stipulated (1) a healthy sample population, (2) a physical activity intervention, (3) a working memory outcome measured, and (4) a randomized control trial design.
---------------------------------------------------------------------------------------------------------------------------
(I graduated since submitting this journal and my ability to contact my research adviser is intermittent as she is on sabbatical, so I was hoping to get some additional insight from this thread--hope that is permissible)
Questions:
1) One reviewer commented that including acute and chronic exercise interventions must be separately analyzed to which I now realize and fully agree. My question is that I only have 11 studies and 5 are acute exercise interventions. Should I simply exclude them (per reviewer's recommendation), or perhaps attempt to conduct a separate meta-analysis of the 5 acute exercise-based studies? Doing so, however, may be problematic as each of the 5 studies used different working memory measurement tools (my initial meta-analysis has subgroups where identical tests are analyzed together).
2) This question is also directly relates to my #1: by removing the 5 studies from my initial meta-analyses, some subgroups, which initially had 4 studies (3 of which were acute, for instance) now become 1 study in said subgroup. So, is there a way to resolve this new problem? Looking at previous reviews, it seems one review in particular employed a Hedges' g test that seemingly allowed for the mixing of different working memory tests (again my understanding of what Hedges' g actually is is poor to say the least).
3) Does having just 6 studies in my review (if I in fact simply exclude acute exercise intervention) limit its appeal or worthiness to the scientific community (my search strategy was very specific to begin with as I only found 11 articles over a six year span to begin with)? Currently, I do not want to exclude them, rather try to perform separate analyses.
4) Difference between moderator and mediator variables? Online sources are confusing me. I want to measure the effect of age on my variables (which is defined as a mediator) and also duration (which is defined by some as a moderator).
5) Do I utilize a sensitivity analysis for #4 or a correlational analysis or even a regression meta analysis? I used RevMan, and such additional tests would require further reading on my end.
You need to provide more information. First, what is the research question? State in PICO format. Next, provide the inclusion and exclusion criteria for study eligibility.
Regarding the Hedges' g, it is not a test. It is a corrected version of the standardized mean difference. The Hedges' g is calculated when most of the studies have small samples sizes (i.e., 12 or less).
Dr. Warren,
I have edited my initial question and additional information to better reflect my questions and background. Any help is greatly appreciated!
Dr. Warren,
I have a SR that used Hedge's g and none of the 15 or so studies had samples sizes below 12 (range was 14 to 124). Is this permissible? I only ask because this SR in question used Hedge's g instead of the SMD where subgroups are used to separate the dependent variable measurement tests. In other words, it gives the appearance that the Hedges' g allowed for the pooling for different tests together.
There is nothing wrong using Hedges' g even when the studies have a lot of subjects. In that situation, the Hedges' g value will approach the standardized mean difference value. I don't understand your last point.. An Hedges' g is appropriate whenever a standardized mean difference is.
Sorry, I am a relative novice having only taking one course in Biostatistics. I guess my real question is that if I do my meta-analysis again using the Hedges' g is it possible the results become significant as compared to what I did initially that yielded non-sig results?
I also welcome any more advice from other readers, especially regarding my seemingly laundry list of questions!
Azeem,
I think you need a face-to-face consultation with an expert on systematic reviews and meta-analyses. I often get similar questions from my students and the only way I can fully answer them is after a back-and-forth verbal exchange. And I usually have to see the studies that the students are including in their meta-analysis. I think for many of your questions there is no one right answer.
I am sorry that I can't be of more help.
Gordon
Hello:
I will try to assist but I am not an expert.
1) Omitting the other studies depends on the research question (RQ). If the RQ covers both 'types' of studies, then leave them in but just tease them out. Right now your RQ is not a question but a statement. You need an actual RQ that is answerable. Given what you have as a working title, I would say you leave it in & just separate them out into 2 analyses.
2) I cannot comment on this but it looks like Dr Warren did a fine job
3) Only having 6 studies is not great, but it is acceptable. I have seen less (you need a minimum of 3 but obviously want more). If 6 is all you have, then so be it. That is what the literature has produced thus far, and perhaps someone can pick up on your work down the line and add more studies to it if they become available. But yes - you can do a meta-analysis with only 6 studies.
4) I am not clear on this so I cannot comment
5) Again, I am not clear but I think age is a modifier.
Do seek additional help! As Dr. Warren states, you really need a 1-1. Sorry I cannot offer more.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Techniques
- Meta-Analysis