Timeline for Quantify Difference/Distance between Lognormal distributions
Current License: CC BY-SA 3.0
2 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 21, 2015 at 18:39 | comment | added | pgkrish | I tried the two sample KS test in Matlab. The h and p values are not of use as such. I was hoping the test statistic could be used as a metric. However in cases where the two distributions are apart and there is no overlap, the statistic is one which leaves me with atleast 7 cases collapsing to one point on the graph ( I am plotting a result: cells invaded in a model built using the two grain size distributions in a particular case versus the test statistic of that case). Are are there any other techniques I can use. | |
| Sep 18, 2015 at 0:32 | history | answered | Saket Choudhary | CC BY-SA 3.0 |