Timeline for Peaks of estimated probability distribution are always lower than those of true distribution - why?
Current License: CC BY-SA 4.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 23, 2021 at 14:33 | answer | added | BigBendRegion | timeline score: 1 | |
| Feb 2, 2021 at 15:39 | comment | added | John L | density is smoothing over a window, so it tends to average out the peaks and valleys. It's sort of like using a moving average. | |
| Feb 2, 2021 at 15:35 | comment | added | Henry |
I would guess this is caused by the density() function smearing the estimated pdf sideways and so bringing down the height. This could explain why larger sample sizes reduce the effect
|
|
| Feb 2, 2021 at 14:34 | history | asked | ManUtdBloke | CC BY-SA 4.0 |