Replies to post #388351 on Anavex Life Sciences Corp (AVXL)

[Anshu2]

You have extremely high expectations. Not going to be happen! I'm willing to bet $10k with anyone (of course, the actual bet is infeasible unfortunately).

CEO will NOT provide any additional data/analysis.

The best (even that is far fetched, imo) that can happen is that he may give acceptable reasons to all the flaws/discrepancies in the current numbers on the slide (e.g., p-values, baseline scores on slide #21, n values for all the analysis).

The above is what I want to hear from Missling.

[Anshu2]

On the positive side, MMRM should give positive results, or at least could very well. Also, what is guaranteed is that: If NDA is submitted, the submission data will have everything that is required by FDA. Of course. Nothing to worry there.

It's just that we (investors) will not know all that is submitted --- and CEO is NOT obligated to reveal everything either (I know SRPT never revealed the actual WB dystrophin numbers for the patients, which were terribly low and came to light only when FDA made their briefing docs public).

At this point, I'll be happy with (1) Reasons for discrepancies in the already given numbers, so we have 100% confidence in whatever numbers are already released, (2) Delta ADCS-ADL numbers.

If I get the above two, I'll buy a boatload more for anything less than $12 (maybe, even $13-15).

[peeved]

Thanks again for your insights
I and am sure others very much appreciate your insights.

Sounds like you are seeing this as failure of endpoints unless that data is presented. On slide 21 for numbers it gives ITT but the p value is from PP?

It begs the question as in RETT that if they had data they would have presented it so it seems they might not. I sincerely hope they do.

I am more interested in p4 trial so i was hoping they could present data to fda to convince them of this. I would be flabbergasted if missling does not see the fda requirements and PRs meeting endpoints. This really doesn’t make sense to me

[frrol]

I'll incorporate your thoughts into a couple questions to pass to IR. On Monday, with just 2 days of time, I think we'll get more explanation than additional analysis. What I'd like to hear is that this statistical rigor and transparency is coming with a proper TLR, and when.

Stick around. Ignore "FUD" accusations.

[sab63090]

Doc328

I appreciate your requirements for Missling to present ITT before PP and your hopes that he does give the 30mg and 50mg breakout report...it was interesting to me to see that if they started out with a 50mg treatment and it was lowered to 30mg, it would still be reported at 50mg.

Do you really think that Missling would do as you stated in your post?

"Missling knows this. I hope he does not try to be cute and try to hype PP data if the ITT data is not first presented. An ITT miss with PP hit is a phase 3 fail but not a 2b total loss."

[VuBru]

What they reported were very simple statistics, and I am assuming from what the company said that this was due to time constraints. I think you are right on about needing a MMRM (mixed effect model repeated measures) analysis. That could address the drop-out issue in a reasonable way but would not necessarily hurt the results - this analysis could even improve the p values on the primary outcomes slightly.

[bluesky29]

Some drop out patients can be completely taken off analysis depending on how far in trials.That will create differential bias but very small in treatment arm to placebo.If you pay attention to SD of base line and sample size .Actual p value will improve.I do not think final results far off ITT patients.

[12x]

Here is one recent FDA’s example of Amylyx ALS drug submission illustrating many of the MB discussion points. Slide 36 shows FDA recalculated the p-value using ITT with MMAR instead of company provided mITT with LOCF.

Anavex slides labeled ITT analysis so if that’s the case, the reported results should be in line with FDA expectation. Even if mITT (or PP) was used as some suspected, the p-value impact is small given both placebo and treated baseline ADAS-cog values are both 1 point lower than mITT baseline. The MMRM use random treated group 48week samples to impute the dropout patient’s 48w samples resulting no change in 48w value.

https://www.fda.gov/media/157288/download

[BIOChecker4]

Thanks, DOC328. Readers are very fortunate to have your deep insight and analysis.