Amarin Corp Plc (AMRN)

[mc1988]

After attempting to manually construct a dataset where N=28 mean=300 and SD=233 and where no data point is >500, I now believe that it is indeed correct to claim that there is at least one subject with triglycerides level >500 mg/dL.

The best I could come up with is this data set:

20
20
20
20
20
20
20
30
30
30
40
180
470
480
500
500
500
500
500
500
500
500
500
500
500
500
500
500

where N=28 mean=300 and SD=233.4.

Given that the actual experiment has more "realistic" values rather than values clustered at the extreme ends of 20 and 500, I now believe that the judge is correct in stating

Although Dr. Lavin initially told the PTO that not even one patient in Hayashi would have had triglyceride levels >500mg/dL, Dr. Lavin later testified that he would "rewrite" his declaration on this point, explaining that in Hayashi "you know that there must be at least one subject" with triglycerides levels >500 mg/dL.

I find it rather interesting that the standard deviation for the triglycerides in Hayashi is such a high number. It suggests that the dispersion in TG levels of the experimental subject is very wide, yet that does not seem to fit the distribution of TG levels in Figure 2 of Hayashi.

rmitra, please check my numbers and let me know if my reasoning makes sense? It has been a long while since I last did anything related to statistics. Thank you!