issue 26 Patch Notes for May 30th, 2019

[Rokkeb]

I don't think the DFB exp nerfs are inline with what was posted as the goal.

 

Previously it took 2 runs at 100% exp boos to hit 14, and that kept you at about 1/4 the way or less left to 15.

 

Now it took me 4 runs to hit 14 and it barely snuck 14 in. From the reading it looked like they wanted 1 to 10 to remain the same. Previously you'd get 10 in 1 run, and then 4 in the 2nd, then about 2.5 to 3 in the 2nd run, then about a lvl from there on out to 30's, then half a level.

 

Currently you get to about 8 in 1 run.

 

If that's the intention that's fine, I just don't think the exp matches up with what was posted as the intention. Only reason I'm making the post.

 

Personally I would like to hit 15 in 4 runs, that way you get all 4 buffs, then get to move on to DIB, where you can collect all 4 buffs, then be 22, and go about your business in radio missions or TFs or w/e.

[Abraxus]

Proof positive that if XP is really all you're after, there are still ways to do it.  I'm sure there are those who will point out that it isn't the same, which is true.  But, in total it will make the difference between taking less than a day to get to from 1 to 50, and possibly adding a few more hours to the total.  Might seem like light years worth of difference, but in the grand scheme of things, it's really not.

 

The only concern though is that then because the ping pong ball has bounced back over into the ae side of the net, that they'll further pop it etc etc etc.  I get server stability concerns that were had due to the AE map server stuffs but the congregating to the trial was the direct result of that change.  Limiting choices in the short term is what leads to folks being funneled into something else.    Speed of leveling should not be a worry for the team, really outside of server related issues. We're not in the epistemic bubble days of the NC folks needing to figure out how to eek out as much time to play in the game to maintain transactions and subs etc.  Its a different perspective now.  Personally, my only concern is that there is a desire to continue to maintain nc's previous thinking (or a reluctance to let that go for what ever reason).  We're seeing a few of these decisions now and while trying to think of them in the context of the now, it still is compelling to have concerns of the direction that it may continue to go towards.  *shrug*.

 

I understand what you're getting at.  But, I guess I'm just not accustomed, or familiar with being that tied to the stats the game, that any change would change how I feel about playing it.  I love the game, I love the lore, and I love all the things one can do in a such a mature game.  Mostly, I like sharing that play time with friends on-line, which also makes it a social thing.  So, there is very little that could be done to make me want to play anything else.  I have played "anything else" for the past 7 years, and all that ended up being was marking time in the faint hope that this one would come back.  Now it has, and I couldn't be happier.  It's a RARE second chance that I won't be wasting on worrying over what I consider minutia.  I know others feel differently, and that's their prerogative.  But, please don't accuse those of us who are perfectly happy playing the game we love, as being deluded, or viewing things with rose colored glasses.  Some of us have been around long enough to realize what really makes us happy, having tried many other things.  This makes me happy.  But, for those of you who still need to make that journey, I understand.  I was young once too.  8) :)

[justicebeliever]

Actually, I ran a statistical inference and regression anova analysis on this from the responses in the thread. Because there were more than 30 distinct sample responses, it is a statistically viable pool. With the alpha at 5%, confidence level of 95%, it is statistically accurate that the community supports this, as demonstrated by the sample numbers.

 

Being very familiar with statistical analysis, a sample size of 30 or more has been shown to be statistically representitive of the population. Data, and proof.

 

I’m not arguing but for a population in 50-90k range, 30 seems like too small a sample size

 

When I first began learning statistics, I felt the same. Mathematical evidence has shown that 30 or more is accurate, at around a 95% confidence with a margin of error of +/- 3%.

 

Ipsos and all other polls use the same mathematical standards proofed over the last 200 years or so.

 

Again, not trying to argue, just learn - most Ipsos polls and certain all of Gallup polls I've seen track around 1,000 responses - which is the confidence level and margin's you've expressed and covers a population larger than the planet earth has.  For a population of 90K, with the same margin and confidence level, I'm calculating 988 responses needed. 

 

Here's the tool I always used for marketing - https://www.surveysystem.com/sscalc.htm and what I used to derive the numbers above...

 

Again, I'm not trying argue, feel free to explain here or send me a PM.  I'd love to learn more

 

 

[justicebeliever]

I don't think the DFB exp nerfs are inline with what was posted as the goal.

 

Previously it took 2 runs at 100% exp boos to hit 14, and that kept you at about 1/4 the way or less left to 15.

 

Now it took me 4 runs to hit 14 and it barely snuck 14 in. From the reading it looked like they wanted 1 to 10 to remain the same. Previously you'd get 10 in 1 run, and then 4 in the 2nd, then about 2.5 to 3 in the 2nd run, then about a lvl from there on out to 30's, then half a level.

 

Currently you get to about 8 in 1 run.

 

If that's the intention that's fine, I just don't think the exp matches up with what was posted as the intention. Only reason I'm making the post.

 

Personally I would like to hit 15 in 4 runs, that way you get all 4 buffs, then get to move on to DIB, where you can collect all 4 buffs, then be 22, and go about your business in radio missions or TFs or w/e.

 

There is a known issue with the Exp levels lower than lvl 10 not working as intended.  - https://forums.homecomingservers.com/index.php/topic,3220.msg23670.html?PHPSESSID=j80oq10v80omch26v3ocmrrhh5#msg23670

 

[Abraxus]

I don't think the DFB exp nerfs are inline with what was posted as the goal.

 

Previously it took 2 runs at 100% exp boos to hit 14, and that kept you at about 1/4 the way or less left to 15.

 

Now it took me 4 runs to hit 14 and it barely snuck 14 in. From the reading it looked like they wanted 1 to 10 to remain the same. Previously you'd get 10 in 1 run, and then 4 in the 2nd, then about 2.5 to 3 in the 2nd run, then about a lvl from there on out to 30's, then half a level.

 

Currently you get to about 8 in 1 run.

 

If that's the intention that's fine, I just don't think the exp matches up with what was posted as the intention. Only reason I'm making the post.

 

Personally I would like to hit 15 in 4 runs, that way you get all 4 buffs, then get to move on to DIB, where you can collect all 4 buffs, then be 22, and go about your business in radio missions or TFs or w/e.

 

I think I heard that there was a bug in the 1-10 XP, and that it was being looked at for a fix.  So, it doesn't match the intent at the moment, but I feel like a fix is coming soon.  They are probably just gathering other things to make the patching/downtime effort worthwhile. 

[artphobia]

Most of the graphical changes listed above are from Flashtoo, who kindly offered their work after posting on the....

 

:)

Here is a graphic error(?) with the villain accomplishment badges I noticed since CoV was live.

 

You can see how the dots/stars increase in rank & set as you progress in availability... for villains there is a set of TWO badges for each artwork, EXCEPT for "one star, one dot" there are FOUR... and subsequently NONE of the badges are utilizing the "one star, two dots" artwork ... iirc the correct art asset is in the game files and as such should have been applied two of them. These badges being Bad Luck, Exterminator, Skip Tracer, Portal Hopper. Which two of the four could probably be determined by lvl range.

 

BUT if Flashtoo is adventurous enough they could make the whole villain-set more inline with the hero-set... where EACH badge uses its own art asset by adding more ribbon colors. Attached are examples of what both sides show currently. Or if needed/wanted I could personally work up the extra colors on these (and do other badge fixes/variations), as I've worked on UI and 2D/3D graphics/modeling in the past... just been a few years/career ago. :)

 

https://ibb.co/vQbYTjM

https://ibb.co/jW3Bgsr

 

(tried to attach images ... probably need a higher post count)

[Kelanor]

Amazing job on the patch Devs!

Such awesome changes. I even noticed DFB starting to thin out a bit, a welcome change.

 

If you guys are going to be actively developing this game going forward i would love to see scale-able limbs! :-D

(Like being able to shrink those massive wings or enlarge those tiny tails.)

[Skyhawke]

I didn’t see it listed, but I’ve noticed enhancements drop more frequently now. Before, I could play for hours and maybe see one drop. I’m getting several per mission now. Definitely a nice change.

[SwitchFade]

Actually, I ran a statistical inference and regression anova analysis on this from the responses in the thread. Because there were more than 30 distinct sample responses, it is a statistically viable pool. With the alpha at 5%, confidence level of 95%, it is statistically accurate that the community supports this, as demonstrated by the sample numbers.

 

Being very familiar with statistical analysis, a sample size of 30 or more has been shown to be statistically representitive of the population. Data, and proof.

 

I’m not arguing but for a population in 50-90k range, 30 seems like too small a sample size

 

When I first began learning statistics, I felt the same. Mathematical evidence has shown that 30 or more is accurate, at around a 95% confidence with a margin of error of +/- 3%.

 

Ipsos and all other polls use the same mathematical standards proofed over the last 200 years or so.

 

Again, not trying to argue, just learn - most Ipsos polls and certain all of Gallup polls I've seen track around 1,000 responses - which is the confidence level and margin's you've expressed and covers a population larger than the planet earth has.  For a population of 90K, with the same margin and confidence level, I'm calculating 988 responses needed. 

 

Here's the tool I always used for marketing - https://www.surveysystem.com/sscalc.htm and what I used to derive the numbers above...

 

Again, I'm not trying argue, feel free to explain here or send me a PM.  I'd love to learn more

 

Thread hijacking may be occuring when trying to delve into statistical mathematics. Simply, a sample size of 30 or greater is sufficient. Whether the sample is 30, 300 or 1000, the difference will continue to refine, but the results will largely be the same. Only when a a population is unknown is it necessary to calculate sample size. If it is unknown, the we use the afore mentioned formula.

[Sanguinesun]

 

 

I understand what you're getting at.  But, I guess I'm just not accustomed, or familiar with being that tied to the stats the game, that any change would change how I feel about playing it.  I love the game, I love the lore, and I love all the things one can do in a such a mature game.  Mostly, I like sharing that play time with friends on-line, which also makes it a social thing.  So, there is very little that could be done to make me want to play anything else.  I have played "anything else" for the past 7 years, and all that ended up being was marking time in the faint hope that this one would come back.  Now it has, and I couldn't be happier.  It's a RARE second chance that I won't be wasting on worrying over what I consider minutia.  I know others feel differently, and that's their prerogative.  But, please don't accuse those of us who are perfectly happy playing the game we love, as being deluded, or viewing things with rose colored glasses.  Some of us have been around long enough to realize what really makes us happy, having tried many other things.  This makes me happy.  But, for those of you who still need to make that journey, I understand.  I was young once too.  8) :)

 

 

I'm sorry but can you please cite where I made an accusation of others being deluded?  I stated a concern that decision making regarding speed of or choices of leveling were mired in wishing to maintain the same intentions of the original development team, which had goals based on making the game take time to encourage spending money(ie micro transactions to enable convenience, subs to facilitate the same and more.); but not necessarily keeping in mind that those speed bumps were in place for that specific purpose.  Thus no delusion or "rose tinted" glasses view point was being expressed.

 

As for the other seemingly veiled, churlish statements made, a sears console for some of us was our first gaming console :P.

 

Its great to be excited about the game "being back". (Technically for some it never went a way, mind you I too was not of that fortunate crowd.) But that also doesn't invalidate anyone who express concerns regarding the decisions made in goals towards its remaining available and active either.

 

 

[whiteknight012]

Went to donate and saw that it was already closed! But I cannot say thank you enough for bringing this game and community back into my life. Perhaps I'll catch the donations on the next round!

[Sanguinesun]

 

 

Speaking of AE, the rewards for running content through there seem to have dropped off substantially as well. I was running some maps prior to the patch, and it would get roughly 220-240 tickets per run. Post-patch, those same maps are giving 150-170 per run. Larger/longer maps are giving the same reduced rewards, or about a 30-40% reduction in what you used to get. I don't know if this was an intentional nerf, or something that just slipped in, but it wasn't documented in the patch notes, so if it's another "undocumented nerf", that's a bit annoying. I'd hope it's simply a bug, or if it's intended, that they'd announce it.

 

Primarily my post was in relation to the exp AE missions, but yes the AE ticket rewards seem to be experiencing some sort of strangeness.  The rewards are all over the place.  Yesterday I was testing 3 different missions' ticket rewards(since I was noticing the strangeness) and saw rewards that were in the 500 range only being 1 in 5 chances of having that 500(give or take in change) tickets.  The other 4 were between 240 and 400 and never consistent in the amounts.  Some something has changed for sure.

 

As far as the exp though, its still constant/consistent.  I noticed no changes from the previous reduction changes weeks ago. Thus they're still viable as a good source of leveling with little to no down time.

[HoundsTooth]

The population can be considered known. The sample size is the participants in the thread.

 

The mistake you're making is that taking more samples fixes always fixes your inference. It does not. If you take a lot of sample but they don't represent the population, you get a wrong answer that is calculated very precisely.

 

You are making an assumption, whether you realize it or not. You have to assume your sample is representative of the population. You assumed the responses in this thread represent the responses of everyone playing the game. I have no idea if this is true or not, but I suspect it is not.

 

 

The population can be considered known. The sample size is the participants in the thread.

 

The argument that forum participants are not representative of the whole population can be accurate is the sample size is under 30. As sample size grows over 30, this is a non issue.

 

 

The sample size of 30 is a totally unrelated concept. It has nothing to do with how representative a sample is. People say it's safe to trust [linear] regression hypothesis tests (confidence intervals and p-values) with a sample > 30.

 

 

This goes beyond a simple poll of data, in a vacuum. Why? A set data poll within itself is a population, not a sample. A sample is used to model a population and must be run through statistical formulae.

 

I'm sorry, but I have no idea what this means. A poll is a sample of a population. It has uncertainty in it which you must account for.

 

 

In essence, the thread has enough data to accurately model the population with a confidence level of 95% and a margin of error of +/- 3%, supporting that the population in majority (51% or greater) is in favor of the change.

 

This is just not true. Your sample is not random. It is not represented of the population. You may be able to get the desired margin of error, but the sample is incorrect. You need a truly random sample or you need to apply weights when you perform an analysis.

 

I am a statistician. I am happy to help you make your poll better or to improve your understanding. Respectfully, the analysis is not as insightful as you believe.

 

[HoundsTooth]

Actually, I ran a statistical inference and regression anova analysis on this from the responses in the thread. Because there were more than 30 distinct sample responses, it is a statistically viable pool. With the alpha at 5%, confidence level of 95%, it is statistically accurate that the community supports this, as demonstrated by the sample numbers.

 

Being very familiar with statistical analysis, a sample size of 30 or more has been shown to be statistically representitive of the population. Data, and proof.

 

I’m not arguing but for a population in 50-90k range, 30 seems like too small a sample size

 

When I first began learning statistics, I felt the same. Mathematical evidence has shown that 30 or more is accurate, at around a 95% confidence with a margin of error of +/- 3%.

 

Ipsos and all other polls use the same mathematical standards proofed over the last 200 years or so.

 

Again, not trying to argue, just learn - most Ipsos polls and certain all of Gallup polls I've seen track around 1,000 responses - which is the confidence level and margin's you've expressed and covers a population larger than the planet earth has.  For a population of 90K, with the same margin and confidence level, I'm calculating 988 responses needed. 

 

Here's the tool I always used for marketing - https://www.surveysystem.com/sscalc.htm and what I used to derive the numbers above...

 

Again, I'm not trying argue, feel free to explain here or send me a PM.  I'd love to learn more

 

Thread hijacking may be occuring when trying to delve into statistical mathematics. Simply, a sample size of 30 or greater is sufficient. Whether the sample is 30, 300 or 1000, the difference will continue to refine, but the results will largely be the same. Only when a a population is unknown is it necessary to calculate sample size. If it is unknown, the we use the afore mentioned formula.

 

I'm sorry, but this is really, really wrong.

 

A sample size of >30 is a totally unrelated concept. The rule of thumb is that when the sample is >30, you can use normal based confidence intervals because your sample size is large enough for the Central Limit Theorem to apply. You need large sample sizes so you can correctly sample everyone of interest in your population, and so you can add weights to your survey to account for low responses in certain groups.

[Rikis]

Hopefully this is a bug, but being in a team while completing a morality mission gave everyone reward merits. Now, only the mission owner gets the merits, effectively making the alignment/morality progression a solo endeavor. I mentioned that I hoped this was a bug because right after the patch things were working like they were before, but I noticed the change yesterday.

[SwitchFade]

The population can be considered known. The sample size is the participants in the thread.

 

The mistake you're making is that taking more samples fixes always fixes your inference. It does not. If you take a lot of sample but they don't represent the population, you get a wrong answer that is calculated very precisely.

 

You are making an assumption, whether you realize it or not. You have to assume your sample is representative of the population. You assumed the responses in this thread represent the responses of everyone playing the game. I have no idea if this is true or not, but I suspect it is not.

 

 

The population can be considered known. The sample size is the participants in the thread.

 

The argument that forum participants are not representative of the whole population can be accurate is the sample size is under 30. As sample size grows over 30, this is a non issue.

 

 

The sample size of 30 is a totally unrelated concept. It has nothing to do with how representative a sample is. People say it's safe to trust [linear] regression hypothesis tests (confidence intervals and p-values) with a sample > 30.

 

 

This goes beyond a simple poll of data, in a vacuum. Why? A set data poll within itself is a population, not a sample. A sample is used to model a population and must be run through statistical formulae.

 

I'm sorry, but I have no idea what this means. A poll is a sample of a population. It has uncertainty in it which you must account for.

 

 

In essence, the thread has enough data to accurately model the population with a confidence level of 95% and a margin of error of +/- 3%, supporting that the population in majority (51% or greater) is in favor of the change.

 

This is just not true. Your sample is not random. It is not represented of the population. You may be able to get the desired margin of error, but the sample is incorrect. You need a truly random sample or you need to apply weights when you perform an analysis.

 

I am a statistician. I am happy to help you make your poll better or to improve your understanding. Respectfully, the analysis is not as insightful as you believe.

 

Much of your response was written in a fashion that is suspect, vis a vi, I am unable to place great confidence in several of your proclamations. While you do have a grasp of some statistical concepts, you are misunderstanding many of them. A sample size of larger than 30 is valid. Population is known. If you have no idea what I mean when I say a sample in a vacuum is a population, I apologize but I am unable to make the sentence any more plain; I suspect it may just require rereading the sentence several more times to grasp the meaning. While the sample may not be random, as most are not, without other means of conducting a "truly random sample," we must begin by analyzing the data presented. The thread represents such data. You suspect the thread does not represent the population, which is a valid observation, that would warrant further research, yet it is an assumption and is biased. The data in the thread is not and I merely analyzed the data.

 

It's all fine and we'll to assume that any of this data is wrong, and then pretend we should not bother analyzing it, but that would be another form of bias.

 

Should we have more accurate data? Sure. Is this data biased? Sure. Did I account for it? Yes.

[SwitchFade]

Actually, I ran a statistical inference and regression anova analysis on this from the responses in the thread. Because there were more than 30 distinct sample responses, it is a statistically viable pool. With the alpha at 5%, confidence level of 95%, it is statistically accurate that the community supports this, as demonstrated by the sample numbers.

 

Being very familiar with statistical analysis, a sample size of 30 or more has been shown to be statistically representitive of the population. Data, and proof.

 

I’m not arguing but for a population in 50-90k range, 30 seems like too small a sample size

 

When I first began learning statistics, I felt the same. Mathematical evidence has shown that 30 or more is accurate, at around a 95% confidence with a margin of error of +/- 3%.

 

Ipsos and all other polls use the same mathematical standards proofed over the last 200 years or so.

 

Again, not trying to argue, just learn - most Ipsos polls and certain all of Gallup polls I've seen track around 1,000 responses - which is the confidence level and margin's you've expressed and covers a population larger than the planet earth has.  For a population of 90K, with the same margin and confidence level, I'm calculating 988 responses needed. 

 

Here's the tool I always used for marketing - https://www.surveysystem.com/sscalc.htm and what I used to derive the numbers above...

 

Again, I'm not trying argue, feel free to explain here or send me a PM.  I'd love to learn more

 

Thread hijacking may be occuring when trying to delve into statistical mathematics. Simply, a sample size of 30 or greater is sufficient. Whether the sample is 30, 300 or 1000, the difference will continue to refine, but the results will largely be the same. Only when a a population is unknown is it necessary to calculate sample size. If it is unknown, the we use the afore mentioned formula.

 

I'm sorry, but this is really, really wrong.

 

A sample size of >30 is a totally unrelated concept. The rule of thumb is that when the sample is >30, you can use normal based confidence intervals because your sample size is large enough for the Central Limit Theorem to apply. You need large sample sizes so you can correctly sample everyone of interest in your population, and so you can add weights to your survey to account for low responses in certain groups.

 

Again, you are misunderstanding the text presented, which means it is not "really, really wrong."

 

To reiterate, a sample size of greater than 30 is VALID when a population is known. A sample of larger numbers of a population renders finer results, but the outcome is largely the same. Your proclamation that you need a large sample size to account for everyone of interest in a population is somewhat misleading, we are interested in the whole population, and must attempt to fairly represent them through sampling MEANS.

 

I do appreciate your insight. There are no incorrect statements, analogies, inferences, descriptors or concepts in my responses as you have mentioned.

[justicebeliever]

I'm sorry, but this is really, really wrong.

 

A sample size of >30 is a totally unrelated concept. The rule of thumb is that when the sample is >30, you can use normal based confidence intervals because your sample size is large enough for the Central Limit Theorem to apply. You need large sample sizes so you can correctly sample everyone of interest in your population, and so you can add weights to your survey to account for low responses in certain groups.

 

Again, you are misunderstanding the text presented, which means it is not "really, really wrong."

 

To reiterate, a sample size of greater than 30 is VALID when a population is known. A sample of larger numbers of a population renders finer results, but the outcome is largely the same. Your proclamation that you need a large sample size to account for everyone of interest in a population is somewhat misleading, we are interested in the whole population, and must attempt to fairly represent them through sampling MEANS.

 

I do appreciate your insight. There are no incorrect statements, analogies, inferences, descriptors or concepts in my responses as you have mentioned.

 

My understanding for n=30 is that it's tied to the CLT, which can only be applied for data sets with successive, random sampling.  Neither of which is present in a forum thread.  Again, I am not a statistics PhD, but part of my background is in marketing, and I never heard the CLT applied there (just discovered it due to this thread).  I've also seen quite a bit of debate about the utility of n=30 (in fact that it is an accepted standard due to it being what fits best in textbooks - though that seems spurious reasoning).  As I said, feel free to PM me more information (on the web, or start a dialogue) if you are concerned about threadjacking  - I'd really like to learn more.  And for what it's worth, if you want people to buy into what you are saying you have to do more than say - I am an expert, trust me...you need some reasoning.  I don't doubt you have it, please share!

[HoundsTooth]

I'm sorry, but this is really, really wrong.

 

A sample size of >30 is a totally unrelated concept. The rule of thumb is that when the sample is >30, you can use normal based confidence intervals because your sample size is large enough for the Central Limit Theorem to apply. You need large sample sizes so you can correctly sample everyone of interest in your population, and so you can add weights to your survey to account for low responses in certain groups.

 

Again, you are misunderstanding the text presented, which means it is not "really, really wrong."

 

To reiterate, a sample size of greater than 30 is VALID when a population is known. A sample of larger numbers of a population renders finer results, but the outcome is largely the same. Your proclamation that you need a large sample size to account for everyone of interest in a population is somewhat misleading, we are interested in the whole population, and must attempt to fairly represent them through sampling MEANS.

 

I do appreciate your insight. There are no incorrect statements, analogies, inferences, descriptors or concepts in my responses as you have mentioned.

 

My understanding for n=30 is that it's tied to the CLT, which can only be applied for data sets with successive, random sampling.  Neither of which is present in a forum thread.  Again, I am not a statistics PhD, but part of my background is in marketing, and I never heard the CLT applied there (just discovered it due to this thread).  I've also seen quite a bit of debate about the utility of n=30 (in fact that it is an accepted standard due to it being what fits best in textbooks - though that seems spurious reasoning).  As I said, feel free to PM me more information (on the web, or start a dialogue) if you are concerned about threadjacking  - I'd really like to learn more.  And for what it's worth, if you want people to buy into what you are saying you have to do more than say - I am an expert, trust me...you need some reasoning.  I don't doubt you have it, please share!

 

I am a statistics PhD. Your understanding is correct. The rule of thumb is that when you have >30 sample, you can apply the CLT. This has nothing to do with a sample representing the population. It is used to calculate uncertainty, e.g. margin of error

[justicebeliever]

I am a statistics PhD. Your understanding is correct. The rule of thumb is that when you have >30 sample, you can apply the CLT. This has nothing to do with a sample representing the population. It is used to calculate uncertainty, e.g. margin of error

 

Fascinating.  So for a population of 100K and provided you are doing random sampling, how do you determine a valid sample size? I know there are several variables to consider.

[_NOPE_]

I am a statistics PhD. Your understanding is correct. The rule of thumb is that when you have >30 sample, you can apply the CLT. This has nothing to do with a sample representing the population. It is used to calculate uncertainty, e.g. margin of error

 

Fascinating.  So for a population of 100K and provided you are doing random sampling, how do you determine a valid sample size? I know there are several variables to consider.

 

I have a PhD in Terryology. So, I can tell you definitively that the best way to determine the best sample size is to prove that 1x1=2. But that'd be obvious if you were a genius like me.

[HoundsTooth]

I am a statistics PhD. Your understanding is correct. The rule of thumb is that when you have >30 sample, you can apply the CLT. This has nothing to do with a sample representing the population. It is used to calculate uncertainty, e.g. margin of error

 

Fascinating.  So for a population of 100K and provided you are doing random sampling, how do you determine a valid sample size? I know there are several variables to consider.

 

I suspect you chose 100K so you can get a nice, clean number but it's not so simple. Nothing in life is simple  :)

 

You need to decide on a few things:

[*] You choose a model you want to fit. Linear regression is the most common model.

[*] You say the smallest relationship you are interested in seeing. Ex: If my new medicine works, I want to be able to see an increase of at least 3 weeks remission time. 

[*] You define the statistical power you want. Power is the probably of seeing a relationship if there is one. Ex: If there my new medicine treats cancer better than a placebo, I want an 80% chance to see this improvement 

[*] Confidence level. Ex: 95% confidence

 

Then there are formulas to get you the required sample size. You can look those up if you're interested. Here's a link to a sample size calculator for linear regression https://www.danielsoper.com/statcalc/calculator.aspx?id=1.

 

Sample size calculations are surprisingly hard to do. People routinely publish papers about sample size calculations in new settings.

 

EDIT: If this is something you're interested in or something you need to learn I can DM you some resources.

[HoundsTooth]

I am a statistics PhD. Your understanding is correct. The rule of thumb is that when you have >30 sample, you can apply the CLT. This has nothing to do with a sample representing the population. It is used to calculate uncertainty, e.g. margin of error

 

Fascinating.  So for a population of 100K and provided you are doing random sampling, how do you determine a valid sample size? I know there are several variables to consider.

 

I have a PhD in Terryology. So, I can tell you definitively that the best way to determine the best sample size is to prove that 1x1=2. But that'd be obvious if you were a genius like me.

 

Impressive. I failed my Terrology 101 class.

[Rockfall]

I saw the "powerleveling for inf" spam on lfg tonight (correctly predicted by a number of folks). I was mostly ignoring lfg, so I can't say how prevalent it was.

[Zolgar]

I saw the "powerleveling for inf" spam on lfg tonight (correctly predicted by a number of folks). I was mostly ignoring lfg, so I can't say how prevalent it was.

 

I've seen it a couple times.

 

It's not super prevalent, at least on Everlasting, yet. It's going to be an omnipresent problem with a population this big though.