Problem with margestats output

Use of Healpix, camb, CLASS, cosmomc, compilers, etc.
Post Reply
alessandro tronconi
Posts: 6
Joined: February 14 2009
Affiliation: Bologna University

Problem with margestats output

Post by alessandro tronconi » August 11 2016

Hello
i actually cannot understand the output of MC. In the .margestats file, for a parameter added to the analysis, i find the following marginalised limits for 0.68; 0.95; 0.99

mean sddev lower1 upper1 limit1 lower2 upper2 limit2 lower3 upper3 limit3
9.8290747E+00 5.7929799E+00 2.1363450E+00 1.6052064E+01 two 2.7186950E+00 2.1000000E+01 < 2.1839810E+00 2.1000000E+01 <

the lower bounds are not decreasing! How is it possible? In the marginalised plots there is a maximum and the likelihood goes to zero when the parameter goes to zero and goes to a constant value (less than the minimum) when it increases.

Antony Lewis
Posts: 1369
Joined: September 23 2004
Affiliation: University of Sussex
Contact:

Re: Problem with margestats output

Post by Antony Lewis » August 11 2016

The first one is two-tail, the second two are one-tail.

alessandro tronconi
Posts: 6
Joined: February 14 2009
Affiliation: Bologna University

Problem with margestats output

Post by alessandro tronconi » August 11 2016

OK i see! Thanks

Post Reply