How to analyze loot

[Kosh]

Originally Posted by falkao

sry Kosh for the late reply. The data I used is Starfinders global data. The values are integers and are rounded. It seems floor is used, so rounded downwards.
The purist would say you have to use a discrete distribution. What I'm doing is a continuous approximation and thats sufficiently precise for our data.

If X has an exp dist with mean 1/a then Y = floor(X) has the following density

f(y) = a*exp(-a*n)*(1-exp(-a)) for n= 0, 1, ...

f(x) = a* exp(-a*x)

so the difference between those is a*exp(-a*n)*exp(-a) for x = n = 0,1.

for a = .1 and n = 0 the diff is 0.09 PED.
for a = .1 and n = 1000 the diff is 0 PED.

if a gets smaller (higher mean) say a = .01 and n = 0 (the worst case) the diff is .009.

So that is sufficiently precise from my point of view.

Yes, but there are entire ranges that are left out of the distribution. For instance you do not (or extremely rarely) get size VII ore finds unamped in untaxed areas, so that means you do not get any claims in the range: 6-8 ped. It is the same for mining globals, with certain amps you do not get certain types of globals, again skipping large ranges.
I do no have much data on hunting loot distribution, but have noticed jumps there too.
The loot is certainly exponential or if rounded to be discrete, poisson with a small peak at the beginning of the scale. But I feel that by smoothing the function you miss the true distribution here, which is discrete that skips certain ranges altogether.

When looking at all globals from all mobs it is no surprise to see exponential behaviour from 50 ped, what does this teach us about the specific density functions though?

Can I send you some of my mining deposit data for help? My education is statistics but I work in finance and deal with different kinds of models usually so I think you may get more out of it

[Doer]

Originally Posted by falkao

I did a first check and found 2 avas hunting the same mob (aurlis) with sufficient high number of globals (59/69).


Click to enlarge

Comparing loot leads to p = .419 (Mann-Whitney U-test), so not statistically different. This says nothing atm since we don't know if they have similar skills or not. Maybe one of them can tell us more, therfore the names.

If this i not allowed, then I'll remove them.

I think they have hugely different skills.

If you ever do find a significant difference, check not only skills but the weapon (or damage/s) that they use.

Thanks again for the very educational posts.

[falkao]

Originally Posted by Doer

I think they have hugely different skills.

If you ever do find a significant difference, check not only skills but the weapon (or damage/s) that they use.

Thanks again for the very educational posts.

the weapon has for sure an effect as one can see from Jimmy's thread. What we have atm is a negative finding. However it can be false negative and we need some further data to draw final conclusions.
Thx for pointing this out.

[falkao]

Originally Posted by Kosh

Yes, but there are entire ranges that are left out of the distribution. For instance you do not (or extremely rarely) get size VII ore finds unamped in untaxed areas, so that means you do not get any claims in the range: 6-8 ped. It is the same for mining globals, with certain amps you do not get certain types of globals, again skipping large ranges.
I do no have much data on hunting loot distribution, but have noticed jumps there too.
The loot is certainly exponential or if rounded to be discrete, poisson with a small peak at the beginning of the scale. But I feel that by smoothing the function you miss the true distribution here, which is discrete that skips certain ranges altogether.

When looking at all globals from all mobs it is no surprise to see exponential behaviour from 50 ped, what does this teach us about the specific density functions though?

Can I send you some of my mining deposit data for help? My education is statistics but I work in finance and deal with different kinds of models usually so I think you may get more out of it

Now I know what you mean. Check Jimmy's thread for example.
http://www.entropiaforum.com/forums/...3-post305.html
http://www.entropiaforum.com/forums/...6-post321.html

Loot below 50 PED has some different characteristics. There are gaps in loot. I don’t have a final model for the gaps yet, only some assumptions. However, all is based on exp distributions and/or functions from exp dists. There is also something that I call min loot, so it might be rather interesting to compare loot with finds. So you're welcome to send me the data. I'll pm you.

[falkao]

As we already know, when analyzing normal loot we have also to consider the empty rate, as there is some kind of correction.

Atm, I didn't see any need to do that with global data. However, to be sure we need to know, at least for some mobs, the empty rates.

Ambu's for example will always loot, Formidons have an empty rate of about 30%, whereas Drones or Argos Y are at about 50%.

To start it would be sufficient to know what mobs have an empty rate of 0, i.e. do always loot.

[PrinceYumil]

Does the monster's damage, or even damage type, have any impact on loot? It would make sense that mobs which hit harder (relative to their health) would give more loot, since on average people hunting them will use more decay on armor and faps. So if this is the case, it would justify even further the value of long range and high firing speed on weapons, evader/dodger skills, and high avatar health, as these, in various ways, all guard against extra decay caused by the mob's high attacks.

However if this isn't the case, then maybe it's a bad idea to hunt relatively hard hitting mobs, as they will cause slightly higher decay for anyone, compared to mobs with similar health but lower damage.

As far as damage type, this is just a shot in the dark, but maybe mobs that do common types like impact damage, give more loot than mobs that do say electric damage, because most people use iarmor with impact protection, thus creating more decay from impact damage compared to electric.

[falkao]

Originally Posted by PrinceYumil

Does the monster's damage, or even damage type, have any impact on loot? It would make sense that mobs which hit harder (relative to their health) would give more loot, since on average people hunting them will use more decay on armor and faps. So if this is the case, it would justify even further the value of long range and high firing speed on weapons, evader/dodger skills, and high avatar health, as these, in various ways, all guard against extra decay caused by the mob's high attacks.

However if this isn't the case, then maybe it's a bad idea to hunt relatively hard hitting mobs, as they will cause slightly higher decay for anyone, compared to mobs with similar health but lower damage.

As far as damage type, this is just a shot in the dark, but maybe mobs that do common types like impact damage, give more loot than mobs that do say electric damage, because most people use iarmor with impact protection, thus creating more decay from impact damage compared to electric.

that's indeed an element to investigate and should include also the total HP of the mob and different HP regain.
When we analyze data, we know only base HP of the creature but not the total HP dmg done on it. I had the impression on some mobs, that there are 2 distributions. One from avas that are able to kill the mob as fast as possible and one for those that just managed to kill it (using fap etc..).

[falkao]

Originally Posted by PrinceYumil

Does the monster's damage, or even damage type, have any impact on loot?

I did a fast check and there is indeed a dmg effect.


Click to enlarge


Click to enlarge

The dmg is smaller than the health effect, both however are significant.

Neverthelss, since the effective dmg done is unknown, it might be possible that with dmg I do see the extra dmg done to the mob. Since high dmg mobs might regain more then less hitting mobs, due to time lost with fapping, this might be plausible.

However, the effect is not constantly increasing. There is some kind of interaction. Loot goes up with the first dmg categories, but is diminuished with the highest one. This looks rather strange. An explanation could be that mobs that do a lot of dmg can be hunted only in teams and therefore the effective dmg done is lower, and hence also loot.
37% of the mobs with dmg >111 are hunted in teams whereas for lower dmg mobs this percentage is 16%. So my assumption might be right.

Atm I can't go any further but I'll check it again.

[Ironheart]

Falkao: I cant +rep you again until I spread some, so I will post here instead.

Yet another incredibly good thread, you've started here.

As with other threads your rigorous approach not only brings great insights and important answers, but opens up whole new fields for investigation and experimentation.

I cant praise you highly enough.

Thank you.

[falkao]

here some strange finding on mob dmg and mob health.

I used the following 500 HP mobs where I had enough data:

		n	Dmg	Loot	p (vs Aurli)
Argonaut Guard.	287	40	71		
Atrox Old	213	56	74	.001	
Aurli Weak	155	77	67		
Longu Old	66	69	74	.018

loot in the table is median loot. Dmg is the dmg the mob does. p is the p-Value compared to Aurli.

Kaplan Meier

Click to enlarge

Box-Plot

Click to enlarge

Interestingly Atrox with lower dmg loots better than Aurli. The team percentage is the same, 15% with Atrox and 16% with Aurli. So this time the difference can't be explained by a team effect.

I do not hunt Aurli's very often. So do they hit less often than Atrox, or do they always loot?
The difference is 7 PED, which is quite some (10%). I don't think this is a false positive finding, so there must be some kind of explanation.