I am in problem in analysis of two studies. a) In an RCT with 50 patients in each group need three followup at day 0, 28 and 90 days. In every follow up there are missing of some patients. Intension to treat basis analysis I need to apply here(Is it oK?) but I want to know the procedure in SPSS-20. b) In another analytic study with 60 patients with convulsion and 60 patients with headache without convulsion, where TSH, fT3 and fT4( to observe sub clinical hypothyroidism) levels are needed to measure at week o, 12 and 24. Here also there are some patients not coming to follow up. Intention to treat analysis is still applicable here with missing values?
Hi Rajat,
I can address the intention-to-treat (ITT) component of your question, but not the SPSS part. I am attaching the CONSORT statement about RCTs . There is a section there specifically discussing ITT (see discussion starting on page 17). It explains what ITT analysis is, and how missing data affect the results.
If you have any questions after reading that section, let me know and I'll be happy to clarify it for you.
In short: ITT analysis refers to handling losses of follow up in prospective trials, not missing values.
ITT is a recommended conservative approach - you should consider lost to follow up as an untoward event. Missing values, on the othe hand, missing data is an statistical issue to aply some tests and should be treated appropriately.
In SPSS there are four standard methods to deal with missing data - you can find on:
www.csun.edu/sites/default/files/statistics20-core-system-guide-32bit.pdf
In Consort-- "The special strength of the RCT is the avoidance of bias when allocating interventions to trial participants. That strength allows strong inferences about cause and effect that are not justified with other study designs. In order to preserve fully the huge benefit of randomisation we should include all randomised participants in the analysis, all retained in the group to which they were allocated. Those two conditions define an “intention-to-treat” analysis, which is widely recommended as the preferred analysis strategy. Intention-to-treat analysis corresponds to analysing the groups exactly as randomised. Strict intention-to-treat analysis is often hard to achieve for two main reasons—missing outcomes for some participants and non-adherence to the trial protocol."
- How to handle with missing outcomes that making problem in analysis?
Missing outcomes due to attrition (loss to attrition) is handled by censoring. I suggest you read up on survival analysis (also known as time-to-event analysis). I am attaching a link to a tutorial paper I wrote on the topic a long time ago.
Article Evaluating Disease Management Program Effectiveness: An Intr...
The intention to treat part of your question has been well answered.
The other part of your question relates to analysing repeated measures data in which some data points are missing.
In this setting, general linear mixed models have considerable advantages over the traditional GLM (repeated measures ANOVA) approach. However, (unfortunately) although linear mixed models can be fitted using SPSS, the models are much more difficult to specify.
I recommend Cnaan, Laird and Slasor: Tutorial in Biostatistics. Statistics in Medicine 16, 2349-2380 (1997) for an introduction to analysing repeated measures data.
- Badges
- Science topic
- Similar topics
- Biological Science
- Physiology
- Physiological Processes
- Stress