Should I use repeated measures ANOVA or just one-way ANOVA?

Question

Hello,

I am conducting a study on different image reconstruction algorithms for computed tomography (CT). My aim is to investigate which of the image reconstruction algorithms that have the highest signal-to-noise ratio (SNR). My dataset is 100 patients who underwent a CT brain scan. Each CT scan will be reconstructed with 4 different image reconstruction algorithms. Then I will measure the SNR for each algorithm and patient and compare the different reconstruction algorithms with regard to the SNR.

My question is if I should use a repeated measures ANOVA or just one-way ANOVA? I was thinking repeated measure since it is the same patient CT scan that I will reconstruct with 4 different image reconstruction algorithms. What do you think? Thank you!

/Michael

Answer 1

I don't think you have repeated measures (i.e. you're not taking measurement over time to look for changes). Instead, you are using 4 different algorithms or "treatments" on the same scan (and only 1 scan per subject), to see which which is best via calculating the SNR for each algorithm. It doesn't sound like you even have any replication. Since you do have N=100, I think all you can assume normality (but it would be a good idea to test for it anyway), and if it is normal data, then do is a simple one-way ANOVA.

By the way: a repeated measures ANOVA is the equivalent of the one-way ANOVA, but for related, not independent groups, and is the extension of the dependent t-test. A repeated measures ANOVA is also referred to as a within-subjects ANOVA or ANOVA for correlated samples.

Answer 2

I would agree with your reasoning to use repeated measures ANOVA.