Search results

Had a closer look at this. The problem is that taking the means first and then their percentage change is sometimes different from taking the percentage change per participant first and then taking the mean. This is especially a problem with wkld_AT and time_sec_AT: I thought this was due to...

I used Youden's J statistic the find the optimal threshold, which is just (true positive rate - false positive rate) or written differently sensitivity - (1-specificity). I think visually you can interpret it as the point on the ROC curve that is furthest away from the red dotted diagonal. For...

I think the Nelson 2019 study is interesting. Even though it is quite small, it is one of the few that used an appropriate analysis comparing both the testing difference (CPET2-CPET1) and group difference (MECFS versus HC) at the same time. They also suggest using percentages: They only...

Nice visualization, thanks. One suggestion: it might more intuitive if both graphs have the same scale, so that difference in VO2 and wkld can be compared. Now they look the same size but VO2 has a scale from -20 to 10 and wkld from -50 to 20.

Seems all very speculative (and that is probably an euphemism).

Here are the SNP that were used for CFS:

Sounds interesting. The GWAS for CFS (code: ukb-b-8961) had 2076 cases of self-reported CFS and 460.857 controls. Vigorous physical activity (VPA) and moderate to vigorous physical (MPA) were self-reported but light (LPA) and average physical activity (APA) were based on accelerometer data...

We haven't posted or discussed this yet, but I think most statisticians would use a mixed linear effects model for this. That way they can account for the repeated measures (day1-day2) of participants but still test for differences between group. I've tried this using the following model: model...

I don't know for sure but I suspect that the measuring device automatically averages multiple values over a short period (for example 10 seconds) and that becomes the score.

There seems to be a moderate effect size for VO2 at peak values (not VO2 at the anaerobic threshold) with ME/CFS patients having lower values than controls, 63% of the time. The associated p-value is 0.005 but the authors tested more than 20 outcomes, at both the maximal and the anaerobic...

One other thing that I've been looking it is Winsorizing the data, meaning cutting of the data at a certain percentile and replacing the values outside the limit with the percentile at both sides of the data. Winsorizing - Wikipedia I tried different cutoffs at 1%, 2.5% and 5%. For the VO_max...

It's similar to CLES I believe. While CLES is the number of wins (groupA > Group B) divided by the total number of possible comparisons, cliff d seems like the (wins - loses) divided by the total number of possible comparisons. I get the same values as you using this formula. I think that...

If found one that I find quite intuitive: the Common Language Effect Size (CLES). If you were to randomly take a participant from the ME/CFS group and a random participant from the HC group, how often would the ME/CFS patients have a lower value? If this was random noice and no equal values...

Small differences like: Cohen_d_difference: I got: -0.129, you got: 0.12646 P_Welch_Difference: I got:0.424, you got: 0.432 etc. Did you exclude those 10 from AT? Is that necessary? I'm not sure that not hitting peak affects their AT values. No sorry, typo, the second overview I posted was for...

Apologies for the wrong p-values, not sure what went wrong there. Here's what I got for values at AT and with PI-026 excluded. The first row looks very similar to your results for Work at AT (although for some reason, some figures are a bit different). One thing that strikes me is that...

Yes I think you make a good point. When expressed as a percentage, there are 4 ME/CFS patients (PI-029, PI-087, PI-114, and PI-166) that have extreme values: That make the distribution of percentage changes quite skewed: With these 4 included, I found a cohen_d of 0.008 and p_value of 0.93...

I think we largely agree. The data does not suggest that there is no difference at all. It's not 100% random noise. I would summarise it as: the data suggests that there might be an effect. But the effect is quite small with poor separation between groups and no correlation with the Bell...

True, my graph looked weird because I checked precision below a certain value if the value was negative but above the value if it was positive. If I don't do this then I get the convergence to the ratio of ME/CFS patients in the total sample that you mentioned:

I tried to look at the precision level for different values for the VO2_percentage change. I had it switch around the 0 point (checked for smaller values in case of negative values and for bigger values when positive values were used). Here's the code I used df = df_max values = np.arange(-40...

Thanks @forestglip. Your coding skills are impressive and very useful. I think your analysis confirms that there might be a small effect. On the other hand, your approach is also iteratively looking for the best threshold, trying different things and looking for a value with the clearest...