turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

Find a Community

- Home
- /
- Analytics
- /
- Stat Procs
- /
- 3x3 Crossover study with repeated measurements

Topic Options

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

04-04-2010 05:23 AM

I am having difficulties to analyze the following experiment.

I have 3 treatments (A, B and C) that I want to compare and decide which has the better results.

I have 3 groups of patients (each group with 6 people), I can also use as a general group (all patients: 18 people).

Each patient passed by all treatments in different sequences. I performed the 3 types of sequence (each type with 2 people of each patient group): ABC, BCA and CAB.

I could not perform more experiments due to the availability of patients.

During each treatment I make different measurements (variables). Some variables are measured at least once and max 4 times.

My first impulse was to calculate the mean and SD of each variable at the treatment. So I had a value per treatment and per patient. Afterwards I summarized them for all patients (groups) and treatments. At this moment no relation with the sequence was made.

So my question is how can I analyze such data considering the sequences in order to be able to compare treatments. So before I had a mean and SD for each treatment. Considering the sequence I will have this mean and SD divided by components, will I? And with these components I can compare the treatments?

I read some books about crossover studies but they did not help a lot to understand how to interpret and analyze the data. They came with too much theory and are not practical.

I have 3 treatments (A, B and C) that I want to compare and decide which has the better results.

I have 3 groups of patients (each group with 6 people), I can also use as a general group (all patients: 18 people).

Each patient passed by all treatments in different sequences. I performed the 3 types of sequence (each type with 2 people of each patient group): ABC, BCA and CAB.

I could not perform more experiments due to the availability of patients.

During each treatment I make different measurements (variables). Some variables are measured at least once and max 4 times.

My first impulse was to calculate the mean and SD of each variable at the treatment. So I had a value per treatment and per patient. Afterwards I summarized them for all patients (groups) and treatments. At this moment no relation with the sequence was made.

So my question is how can I analyze such data considering the sequences in order to be able to compare treatments. So before I had a mean and SD for each treatment. Considering the sequence I will have this mean and SD divided by components, will I? And with these components I can compare the treatments?

I read some books about crossover studies but they did not help a lot to understand how to interpret and analyze the data. They came with too much theory and are not practical.