Magic Johnson vs Kevin Garnett

[limbo]

1. Who had the better one year peak?

2. Whose extended prime was better ?

3. Who ranks higher all time?

1.KG
2.KG
3.KG

KG was a superior player and played for longer. You have to be really low on KG's offense to make this debatable.

[Timmyyy]

RAPM does not use box score data, you may be thinking of RPM.

Both are actually regressive analysis based on box-score data. Which is why the stat doesn't really work in the playoffs because there isn't enough data.

BPM is the most simplistic one that is basically just straight off box score data (and usage)

That is flat out not true.

Both RAPM and RPM are the result of regressing lineup data (+/-). RPM uses boxscore data as a prior. RAPM uses either no prior or RAPM data from the years before. RAPM is completely free of boxscore influence.

[kendogg]

RAPM does not use box score data, you may be thinking of RPM.

Both are actually regressive analysis based on box-score data. Which is why the stat doesn't really work in the playoffs because there isn't enough data.

BPM is the most simplistic one that is basically just straight off box score data (and usage)

That is flat out not true.

Both RAPM and RPM are the result of regressing lineup data (+/-). RPM uses boxscore data as a prior. RAPM uses either no prior or RAPM data from the years before. RAPM is completely free of boxscore influence.

It is calculated using possession by possession data which is the same data as box scores, just on a possession by possession basis rather than game by game basis. It's the same thing though, ultimately.

[Timmyyy]

Both are actually regressive analysis based on box-score data. Which is why the stat doesn't really work in the playoffs because there isn't enough data.

BPM is the most simplistic one that is basically just straight off box score data (and usage)

That is flat out not true.

Both RAPM and RPM are the result of regressing lineup data (+/-). RPM uses boxscore data as a prior. RAPM uses either no prior or RAPM data from the years before. RAPM is completely free of boxscore influence.

It is calculated using possession by possession data which is the same data as box scores, just on a possession by possession basis rather than game by game basis. It's the same thing though, ultimately.

No man, it doesn't become true when you repeat it.

The input for RAPM is how lineup X (consisting of 5 different guys) fared against lineup Y (again 5 guys) on a +/- bases (looking how the point differential was when these two lineups faced each other). It doesnt care if one of those player had 5 rebounds and another one 10 steals or whatever. Pure +/-, no boxscore.

[kendogg]

You are not listening or understanding, one of the two. The raw data used in RAPM (and RPM) is possession data generally from basketball-reference.com. It is not using box scores yes, but it is still using historical data from past games. It isn't just making up all of its numbers out of thin air.

[Timmyyy]

You are not listening or understanding, one of the two. The raw data used in RAPM (and RPM) is possession data generally from basketball-reference.com. It is not using box scores yes, but it is still using historical data from past games. It isn't just making up all of its numbers out of thin air.

What you are saying right now is something completely different than at the beginning. Who argued that the numbers come out of thin air? And where is the relevance for the debate?

You even started saying KG's case would be based on boxscore, guys said no it is +/-, then you argued RAPM is boxscore derived, now you say no it's just not a number that appears out of thin air. I can't follow the logic anymore.

[kendogg]

What you are saying right now is something completely different than at the beginning.

It is calculated using possession by possession data which is the same data as box scores, just on a possession by possession basis rather than game by game basis. It's the same thing though, ultimately.

That is what I just said and you argued it. Ok enough thread derailment. My point is that yes, KG is a productive player but that doesn't mean he's better than Magic or that he's a GOAT tier player. Stats can lie. Especially in regards to the playoffs, where we simply do not have enough data to really make a good regressive analysis.

[Timmyyy]

What you are saying right now is something completely different than at the beginning.

It is calculated using possession by possession data which is the same data as box scores, just on a possession by possession basis rather than game by game basis. It's the same thing though, ultimately.

That is what I just said and you argued it. Ok enough thread derailment. My point is that yes, KG is a productive player but that doesn't mean he's better than Magic or that he's a GOAT tier player. Stats can lie. Especially in regards to the playoffs, where we simply do not have enough data to really make a good regressive analysis.

I argued it because the way it is worded it's wrong. It sounds as if instead of PPG RPG APG and so on RAPM uses PPP RPP and APP. That is not the case. If you meant something different, ok no problem, but the way it's worded it appears confusing.

Stats don't lie, you only have to be aware of how to use them (misuse of stats is the fault of the guy that uses them not the stat itself). The playoff thing is a good example of that. The +/- data for the PO's in single years is way to small to draw a lot of conclusions, although it is easy to say that KG at least wasn't bad in the PO most of the time as suggested numerous times on this board. But because of the small sample of the +/- and the drop off in some box areas it is ok to be skeptical with how good he really was in the PO's. I don't disagree with that.

[FrogBros4Life]

Stats don't lie

Stats can "lie", and that is one of the first things they teach you in any statistics course. Stats can't lie to the degree that lying requires activity as opposed to passivity. Stats can't lie to the degree that lying implies deceitfulness and numbers themselves do not engage in deception. But stats can absolutely be "untruthful", which I believe is the spirit in which kendogg's statement was made. This exists regardless of the interpretation. It's why things like sample size guidelines and confidence intervals exist in the first place...because unreliability of data and statistical computation as always being truthful is an acknowledged thing, and these are some of the measures implemented to ensure that we can estimate truthfulness as best as possible. But it's not a black/white, stats are always right/never wrong (re: it's always the fault of the person interpreting the stats) dichotomy.

Even when we do generally account for things that let us assume a certain level of truthfulness, there are still plenty of other examples on record of statistics not always offering an explanation of data that can be categorized as honest or accurate.

[Timmyyy]

Stats don't lie

Stats can "lie", and that is one of the first things they teach you in any statistics course. Stats can't lie to the degree that lying requires activity as opposed to passivity. Stats can't lie to the degree that lying implies deceitfulness and numbers themselves do not engage in deception. But stats can absolutely be "untruthful", which I believe is the spirit in which kendogg's statement was made. This exists regardless of the interpretation. It's why things like sample size guidelines and confidence intervals exist in the first place...because unreliability of data and statistical computation as always being truthful is an acknowledged thing, and these are some of the measures implemented to ensure that we can estimate truthfulness as best as possible. But it's not a black/white, stats are always right/never wrong (re: it's always the fault of the person interpreting the stats) dichotomy.

Even when we do generally account for things that let us assume a certain level of truthfulness, there are still plenty of other examples on record of statistics not always offering an explanation of data that can be categorized as honest or accurate.

I won't engage in another semantics debate with you as I fear this will end up in one, but here is a sum up. My main point is that there is always a reason data is how it is. Even if the reason is simply randomness. Empirical data is collected to draw conclusions about connections between things. It is not collected to show you the connections in itself in a randomless result without a need to interpret it. So when someone who interprets the data isn't aware about the possibility of randomness in the model, yes, he is the one to blame. The same is true about premises made in the models. So where is the lie? A model has a KNOWN room for error and KNOWN premises. Also I don't know what is happening in your statistic courses, but I had 3 statistic lectures during my time at university and I never was told that stats can lie, but that just on a side note.
If you wanna say stats can be random, that is true, but it is on the guy who interprets it to know that.

To bring it on topic again. I want to show why I wanted to make that clear with regards to KG. The RAPM results are getting more precise the higher the sample is, meaning the room for error shrinks. KG has 19 years of career, where we have RAPM data for and nearly all of that data is painting the same picture. Meaning that the possibility that KG in some sort had way less impact than these numbers suggest are really small (near 0). Now making conclusions about single PO runs isn't as clear at all. It is included in the RAPM numbers with way smaller samples than RS and can't be extracted. We can look at raw +/- numbers but there is a lot of room for error. Knowing all of that, we can't be certain about his high impact in the playoffs at all and can only use it as weak indicators.
So did the PO +/- lie to me? No I just have to use my knowledge about it to interpret it.

[FrogBros4Life]

Stats don't lie

Stats can "lie", and that is one of the first things they teach you in any statistics course. Stats can't lie to the degree that lying requires activity as opposed to passivity. Stats can't lie to the degree that lying implies deceitfulness and numbers themselves do not engage in deception. But stats can absolutely be "untruthful", which I believe is the spirit in which kendogg's statement was made. This exists regardless of the interpretation. It's why things like sample size guidelines and confidence intervals exist in the first place...because unreliability of data and statistical computation as always being truthful is an acknowledged thing, and these are some of the measures implemented to ensure that we can estimate truthfulness as best as possible. But it's not a black/white, stats are always right/never wrong (re: it's always the fault of the person interpreting the stats) dichotomy.

Even when we do generally account for things that let us assume a certain level of truthfulness, there are still plenty of other examples on record of statistics not always offering an explanation of data that can be categorized as honest or accurate.

I won't engage in another semantics debate with you as I fear this will end up in one, but here is a sum up. My main point is that there is always a reason data is how it is. Even if the reason is simply randomness. Empirical data is collected to draw conclusions about connections between things. It is not collected to show you the connections in itself in a randomless result without a need to interpret it. So when someone who interprets the data isn't aware about the possibility of randomness in the model, yes, he is the one to blame. The same is true about premises made in the models. So where is the lie? A model has a KNOWN room for error and KNOWN premises. Also I don't know what is happening in your statistic courses, but I had 3 statistic lectures during my time at university and I never was told that stats can lie, but that just on a side note.
If you wanna say stats can be random, that is true, but it is on the guy who interprets it to know that.

To bring it on topic again. I want to show why I wanted to make that clear with regards to KG. The RAPM results are getting more precise the higher the sample is, meaning the room for error shrinks. KG has 19 years of career, where we have RAPM data for and nearly all of that data is painting the same picture. Meaning that the possibility that KG in some sort had way less impact than these numbers suggest are really small (near 0). Now making conclusions about single PO runs isn't as clear at all. It is included in the RAPM numbers with way smaller samples than RS and can't be extracted. We can look at raw +/- numbers but there is a lot of room for error. Knowing all of that, we can't be certain about his high impact in the playoffs at all and can only use it as weak indicators.
So did the PO +/- lie to me? No I just have to use my knowledge about it to interpret it.

I'm really less concerned with whatever particular argument you are trying to make for KG here as I am with you (or anyone) throwing out the very specific blanket statement "Stats don't lie", or rather "stats can never be untruthful".

[Timmyyy]

I'm really less concerned with whatever particular argument you are trying to make for KG here as I am with you (or anyone) throwing out the very specific blanket statement "Stats don't lie", or rather "stats can never be untruthful".

Look at the first post you quoted, I explained what I meant with that statement, but you decided to quote the 'blanket statement' without context. With my answer to you I even made it more precise what I meant. You still answer that you don't like the 'blanket statement', without engaging in the particular premise that I explained, why I think that way.

2nd statement wasn't made by me and without reading all the thread I didn't see anyone saying that.

All in all it is exactly what I thought it would end up, a semantics debate for the sake of having a debate.

[WarriorGM]

If you understand what happens in the regression and the adjustments and priors being used, yes, you have a solid understanding what is happening there. The stock market is also a completely different situation as right now, we are not talking about about predicting the future as in the stock market (even if RAPM is actually a tool for predicting), we try to say how precise the correlation between players being on the court and their teams point differentials measured in the RAPM numbers is to the real world impact these guys have and when you have the needed knowledge to see where the strength and weaknesses of the stat are you have a way more precise picture than looking at team wins.

I beg to differ. For example let us take RPM which uses something like height as a prior. I may "understand" why that might increase the accuracy of the body of predictions as a whole but I also understand it is an artificial distortion that may unjustly penalize shorter players with outlier skills and I do not understand it enough to correct for it easily. Better not to use it at all in my view. There is understanding and then there is understanding. Understanding the limits of the statistical model and what it is is very important. For example you look at both RAPM and wins as indicators and say RAPM gives you a more precise picture than looking at team wins. In my view you are already making a fundamental mistake. While you may be very correct in one sense you completely miss the point in another. Wins are not just another indicator. It is the ultimate indicator. To value RAPM over wins the way you have done is like saying a drug is successful because it lowered cholesterol levels even though it didn't reduce mortality outcomes.

I'm not entirely sure what you're asking here. Garnett was playing in the NBA, and the impact metrics come entirely from that sample.
Are you asking "is it possible that there is some unknown circumstance that's causing Garnett's teams to improve more when he plays and fall more when he sits, a circumstance which is not directly related to his actual goodness?". If that's your question, I would say yes, it's definitely possible, but I personally find it unlikely.

No, my question is directed to whether we know if playing on a weak team inflates RAPM relative to playing on a strong team. The reason always given for Garnett not accomplishing as much as his supporters believe he could is that he played with bad teammates. He may have played in the NBA but if we accept this argument one could translate it to mean that he played with an NBA B-Team. Extend the idea further and you have something like the example I gave. This comes back to understanding of RAPM and derivative numbers like it. Does anyone really understand it?

It may be the above factor is taken into account by RAPM. But I wouldn't be the least bit surprised if there are probably other variables that can distort or confound RAPM results and if one isn't aware of them make inaccurate conclusions based on RAPM.

The regression itself adjusts for players playing on bad teams having huge on/off numbers AND guys playing on good teams having huge on court net ratings (yes, it could go both ways, not just one). In smaller samples these effects aren't perfectly accounted for but the larger the sample size is the less the error gets by the nature of the regression. SInce KG ranks great in single years, in multiyears in 5 year spans in 10 year spans and for his whole career (no matter if Boston years or MIN) the probability of him being overrated by the data is close to 0, because of the fact that different sample sizes, different data sets and so on all paint the same picture.

I'm unconvinced you've addressed my point. I'm unsure if it's the proper term/idea but I think you are assuming homoskedasticity in the data but what if it's heteroskedastic or it doesn't follow a bell curve probability distribution? Sample size reliability also seems largely limited to the year of measurement. Yes using multiple years gives affirmation that the general conclusion is correct (KG is a very good player) but it loses precision I therefore disagree the probability of KG being overrated by the data is close to 0.

Perhaps it would be useful to have a common set of data we can refer to so I can point out specific concerns with RAPM I have. If you are willing to look though I notice from one source that LeBron's RAPM dips in the years he is on the Heat while it rises when he is with the Cavaliers? Can you explain this? LeBron's and KG's situations also would appear similar in their early years as is their style of play. Maybe being a big fish point forward in a small pond is just naturally conducive to high RAPM numbers?

It definitely isn't a tool to base conclusions on without further context. Nobody that uses these numbers is doing it that way (somehow everybody that doesn't like what he sees in RAPM is using this argument when nobody is approaching the data that way).
Yet you draw conclusions from team wins and use it more heavily in your analysis than any 'RAPM user' uses RAPM. Additionally you are pointing to raw numbers, which are the input for RAPM, being more reliable, when it is just the unadjusted version of RAPM (so by virtue of making adjustments RAPM IS more precise).
It just isn't clear why we should use the least adjusted data there is (team wins) and the raw input for something, above the thing itself when the thing is adjusting for correlation issues between the team and the player in question. We want the impact of the player not the team.

I've stated above why I give special import to wins. Your claim that I use it more heavily than RAPM users use RAPM strikes me as false. I use a lot of supporting evidence that verifies the wins. Using wins as the starting point has that advantage though: there will be supporting evidence. Like the accidental discovery of penicillin you have a useful cure already so determining how it works is easier than first coming up with a hypothesis then trying to find a cure the way they have tried to find one for Alzheimers and gotten nowhere.

Raw data contains the information derivative data does; it actually contains more data. It's like mining for gold. You might come up with a lot of worthless rocks but there may be platinum and even more valuable minerals in there than the gold you initially sought to find. A moving average might at one glance provide an easier to understand picture of what is happening in a data series and you might even find great value in the slope of the moving average another derivative. But there is information in the raw values themselves that using other forms of analysis might yet unlock. In regards to how I use raw +/- specifically I think you also vastly overestimate my use of it. I've only referred to it in exceptional cases. But its transparency and ease of understanding I think make it just as if not more reliable in those particular instances than RAPM. I'm perfectly willing to refer to RAPM too.

[FrogBros4Life]

I'm really less concerned with whatever particular argument you are trying to make for KG here as I am with you (or anyone) throwing out the very specific blanket statement "Stats don't lie", or rather "stats can never be untruthful".

Look at the first post you quoted, I explained what I meant with that statement, but you decided to quote the 'blanket statement' without context. With my answer to you I even made it more precise what I meant. You still answer that you don't like the 'blanket statement', without engaging in the particular premise that I explained, why I think that way.

2nd statement wasn't made by me and without reading all the thread I didn't see anyone saying that.

All in all it is exactly what I thought it would end up, a semantics debate for the sake of having a debate.

This isn't about semantics at all. You explaining what you meant about KG in regard to that particular point is neither here nor there. Again, this is not about your current discussion involving KG. Kendogg made a very direct statement: "stats can lie". I'm pretty sure I can assume he didn't mean that as "stats can lie only with regard to Kevin Garnett", rather, he was saying in a general sense that stats can sometimes be untruthful. You directly disagreed with that statement, saying "Stats don't lie", or that stats can never be untruthful. I find it highly skeptical that your reply could be interpreted as "Stats don't lie about this single individual point I am making about KG", but like kendogg, you were instead speaking broadly. "Stats don't lie" is the only part of your post that I quoted, because it's the only part of your post that was relevant to the counterpoint. Namely, forming an ideology based around the premise that "stats can never be untruthful" seems like a dangerous approach to take from a critical thinking standpoint. If you believe otherwise, well......ok.

[Timmyyy]

I beg to differ. For example let us take RPM which uses something like height as a prior. I may "understand" why that might increase the accuracy of the body of predictions as a whole but I also understand it is an artificial distortion that may unjustly penalize shorter players with outlier skills and I do not understand it enough to correct for it easily. Better not to use it at all in my view. There is understanding and then there is understanding. Understanding the limits of the statistical model and what it is is very important. For example you look at both RAPM and wins as indicators and say RAPM gives you a more precise picture than looking at team wins. In my view you are already making a fundamental mistake. While you may be very correct in one sense you completely miss the point in another. Wins are not just another indicator. It is the ultimate indicator. To value RAPM over wins the way you have done is like saying a drug is successful because it lowered cholesterol levels even though it didn't reduce mortality outcomes.

Height is a prior as you said. It's influence gets lower the bigger the sample size of the data set is. In a whole season of PI RAPM the prior doesn't influence the scores heavily. At best you see slight over-/underrating which you again can account for when you see a score that strikes you as not reliable (note that height is only used for the split between O and D and not for the score on defense itself, means RAPM isn't overrating him. DRAPM may overrate him while ORAPM would underrate him to the same degree).

I'm unconvinced you've addressed my point. I'm unsure if it's the proper term/idea but I think you are assuming homoskedasticity in the data but what if it's heteroskedastic or it doesn't follow a bell curve probability distribution? Sample size reliability also seems largely limited to the year of measurement. Yes using multiple years gives affirmation that the general conclusion is correct (KG is a very good player) but it loses precision I therefore disagree the probability of KG being overrated by the data is close to 0.

Perhaps it would be useful to have a common set of data we can refer to so I can point out specific concerns with RAPM I have. If you are willing to look though I notice from one source that LeBron's RAPM dips in the years he is on the Heat while it rises when he is with the Cavaliers? Can you explain this? LeBron's and KG's situations also would appear similar in their early years as is their style of play. Maybe being a big fish point forward in a small pond is just naturally conducive to high RAPM numbers?

What I read out of your post prior to this and in this one is that you are concerned RAPM overrates players on bad teams. I addressed that. It could also be that RAPM overrates players on good teams because of their high point differentials. I addressed that to. RAPM adjusts for these things. What it is meant to say is roughly 'how much more than the average NBA player in that year did the player in question impact the point differential playing on a random team, against a random team' (somebody can correct me if there is missing something or misrepresented). So my answer is it may be easier to have higher raw on/off numbers on weak teams but not higher RAPM.
The Lebron thing I can't quite confirm. I always look at multiple data sets. Most of them are from JE. Looking at the scores of RS + PO data 12 and 09 look close enough to call it roughly a draw, because of the difficulties already explained about comparing between years (not being exact). One has 12 in front some others 09 slightly. Looking at how they did compared to competition both are far and away the best in RAPM in the respective years. RS only data has 12 a little behind what I don't think is all that contrarian to the eye test. One NPI set has Lebron at 6th or something, but again NPI RS only is a small sample with bigger room for error. 13 is falling a bit behind these too. 16 on the other hand again is very comparable.
So I don't think what you are saying is confirmed looking at JE's data sets.

For the probability KG is overrated. I worded it strong, but KG is great in single years (saying he was impactful in the years themselves) multiyears who are more precise because of the bigger sample but lose year by year info but confirm that he was that great. increasing the sample even more loses more detailed year by year information but confirms what we already saw in the year by year data itself. The probability that all these different data sets and sample sizes had big errors is just really really unlikely (note that RAPM has KG on Lebron level yet nobody is arguing him at Lebron level, knowing about the possibility it overrates him at least a little, but in a big way that you could say he isn't comparable to Shaq or Duncan? In my eyes nearly no way.).

I've stated above why I give special import to wins. Your claim that I use it more heavily than RAPM users use RAPM strikes me as false. I use a lot of supporting evidence that verifies the wins. Using wins as the starting point has that advantage though: there will be supporting evidence. Like the accidental discovery of penicillin you have a useful cure already so determining how it works is easier than first coming up with a hypothesis then trying to find a cure the way they have tried to find one for Alzheimers and gotten nowhere.

It also has an disadvantage. You dismiss great players simply for having bad luck over an extended period of time. Players that were unfortunate are thought of badly right from the start because your starting point is wins. If you concede there is the possibility that players are simply unfortunate, you should account for that and not dismiss players at your starting point (especially when every data for individual players that is made to show the impact on team wins are pointing to a player impacting it big). But I have to say I don't want to discuss the 'win approach' anymore. We discussed it enough. We have different views on sports and that is ok. Agree to disagree.

Raw data contains the information derivative data does; it actually contains more data. It's like mining for gold. You might come up with a lot of worthless rocks but there may be platinum and even more valuable minerals in there than the gold you initially sought to find. A moving average might at one glance provide an easier to understand picture of what is happening in a data series and you might even find great value in the slope of the moving average another derivative. But there is information in the raw values themselves that using other forms of analysis might yet unlock. In regards to how I use raw +/- specifically I think you also vastly overestimate my use of it. I've only referred to it in exceptional cases. But its transparency and ease of understanding I think make it just as if not more reliable in those particular instances than RAPM. I'm perfectly willing to refer to RAPM too.

The raw data is lineup data. KG's +/- is actually KG + teammates +/- data. So not it is not just showing you RAPM results in raw form. Your and my brain aren't able to make the adjustments RAPM makes in regard to teammates, opponents and so on. We can't look at the data and extract the impact of a single player (which should be the goal since you want to evaluate individuals and not lineups) in our head. Don't get me wrong, I use raw data too for small samples like PO to at least see trends and indicators. But when we have a big sample no human being can extract the impact of a single player out of lineup data as good as the ridge regression used for RAPM.

Some of your points are actually valid questions when you are new to RAPM, but in the end it might be better to just inform in the internet since I am not an expert and most of the discussion really is about the nature of the model itself. So it can be answered by simply looking at sources in the internet. I know what it does, I know how to use it. But to get the best information possible, you should just inform yourself at the main sources for that.

[Timmyyy]

I'm really less concerned with whatever particular argument you are trying to make for KG here as I am with you (or anyone) throwing out the very specific blanket statement "Stats don't lie", or rather "stats can never be untruthful".

Look at the first post you quoted, I explained what I meant with that statement, but you decided to quote the 'blanket statement' without context. With my answer to you I even made it more precise what I meant. You still answer that you don't like the 'blanket statement', without engaging in the particular premise that I explained, why I think that way.

2nd statement wasn't made by me and without reading all the thread I didn't see anyone saying that.

All in all it is exactly what I thought it would end up, a semantics debate for the sake of having a debate.

This isn't about semantics at all. You explaining what you meant about KG in regard to that particular point is neither here nor there. Again, this is not about your current discussion involving KG. Kendogg made a very direct statement: "stats can lie". I'm pretty sure I can assume he didn't mean that as "stats can lie only with regard to Kevin Garnett", rather, he was saying in a general sense that stats can sometimes be untruthful. You directly disagreed with that statement, saying "Stats don't lie", or that stats can never be untruthful. I find it highly skeptical that your reply could be interpreted as "Stats don't lie about this single individual point I am making about KG", but like kendogg, you were instead speaking broadly. "Stats don't lie" is the only part of your post that I quoted, because it's the only part of your post that was relevant to the counterpoint. Namely, forming an ideology based around the premise that "stats can never be untruthful" seems like a dangerous approach to take from a critical thinking standpoint. If you believe otherwise, well......ok.

Man, read my damn post. I explained it well enough why I think stats can't lie at all. Without mentioning KG a single time.

Stats don't lie, you only have to be aware of how to use them (misuse of stats is the fault of the guy that uses them not the stat itself).

I won't engage in another semantics debate with you as I fear this will end up in one, but here is a sum up. My main point is that there is always a reason data is how it is. Even if the reason is simply randomness. Empirical data is collected to draw conclusions about connections between things. It is not collected to show you the connections in itself in a randomless result without a need to interpret it. So when someone who interprets the data isn't aware about the possibility of randomness in the model, yes, he is the one to blame. The same is true about premises made in the models. So where is the lie? A model has a KNOWN room for error and KNOWN premises. Also I don't know what is happening in your statistic courses, but I had 3 statistic lectures during my time at university and I never was told that stats can lie, but that just on a side note.
If you wanna say stats can be random, that is true, but it is on the guy who interprets it to know that.

Not a single inclusion of KG.

How is it the stats fault when the guy that uses it doesn't educate himself how it is properly used or how much error it can have?

Stats and the models creating them have room for error, that is known. They also have certain premises, that is also known.
A lie is a false claim to deceive someone. How does the stat or model deceive you when the information about it are well known.

Don't bother to reply to me again. First the objectivity thing and now that one. If you would have read a dictionary on the words you used, we wouldn't even need to have these discussions.

[FrogBros4Life]

Look at the first post you quoted, I explained what I meant with that statement, but you decided to quote the 'blanket statement' without context. With my answer to you I even made it more precise what I meant. You still answer that you don't like the 'blanket statement', without engaging in the particular premise that I explained, why I think that way.

2nd statement wasn't made by me and without reading all the thread I didn't see anyone saying that.

All in all it is exactly what I thought it would end up, a semantics debate for the sake of having a debate.

This isn't about semantics at all. You explaining what you meant about KG in regard to that particular point is neither here nor there. Again, this is not about your current discussion involving KG. Kendogg made a very direct statement: "stats can lie". I'm pretty sure I can assume he didn't mean that as "stats can lie only with regard to Kevin Garnett", rather, he was saying in a general sense that stats can sometimes be untruthful. You directly disagreed with that statement, saying "Stats don't lie", or that stats can never be untruthful. I find it highly skeptical that your reply could be interpreted as "Stats don't lie about this single individual point I am making about KG", but like kendogg, you were instead speaking broadly. "Stats don't lie" is the only part of your post that I quoted, because it's the only part of your post that was relevant to the counterpoint. Namely, forming an ideology based around the premise that "stats can never be untruthful" seems like a dangerous approach to take from a critical thinking standpoint. If you believe otherwise, well......ok.

Man, read my damn post. I explained it well enough why I think stats can't lie at all. Without mentioning KG a single time.

Stats don't lie, you only have to be aware of how to use them (misuse of stats is the fault of the guy that uses them not the stat itself).

I won't engage in another semantics debate with you as I fear this will end up in one, but here is a sum up. My main point is that there is always a reason data is how it is. Even if the reason is simply randomness. Empirical data is collected to draw conclusions about connections between things. It is not collected to show you the connections in itself in a randomless result without a need to interpret it. So when someone who interprets the data isn't aware about the possibility of randomness in the model, yes, he is the one to blame. The same is true about premises made in the models. So where is the lie? A model has a KNOWN room for error and KNOWN premises. Also I don't know what is happening in your statistic courses, but I had 3 statistic lectures during my time at university and I never was told that stats can lie, but that just on a side note.
If you wanna say stats can be random, that is true, but it is on the guy who interprets it to know that.

Not a single inclusion of KG.

How is it the stats fault when the guy that uses it doesn't educate himself how it is properly used or how much error it can have?

Stats and the models creating them have room for error, that is known. They also have certain premises, that is also known.
A lie is a false claim to deceive someone. How does the stat or model deceive you when the information about it are well known.

Don't bother to reply to me again. First the objectivity thing and now that one. If you would have read a dictionary on the words you used, we wouldn't even need to have these discussions.

You are so indignant that it's borderline insufferable. MY first post already addressed all of your supposed "non KG" points you keep repeating. Perhaps if you would have read it you'd understand why what you're saying isn't a valid counterclaim to what I'm stating. You're not above reproach, and quite frankly, it's humorous for an ESL person to continuously challenge other posters to read the dictionary, especially when they have much more experience with the language than you do. I'm not going to hold your hand and walk you through easily understandable concepts, especially when you have such an obstreperous attitude, but like I said in my first post, there are examples, both theoretical and real life in nature that can be used to reject the statement "stats can never be untruthful".

You can't make sweepingly bold statements like "stats don't lie and any non-truthfulness derived from a statistical analysis is at the fault of the interpreting party" and really not expect someone to call shenanigans, can you? If you don't want people throwing red flags on blanket statements that are tossed around carelessly...then....be more careful about making blanket statements in your arguments maybe? And since you like to keep bringing up dictionaries, perhaps you should go look up the definition of civility.

[Timmyyy]

This isn't about semantics at all. You explaining what you meant about KG in regard to that particular point is neither here nor there. Again, this is not about your current discussion involving KG. Kendogg made a very direct statement: "stats can lie". I'm pretty sure I can assume he didn't mean that as "stats can lie only with regard to Kevin Garnett", rather, he was saying in a general sense that stats can sometimes be untruthful. You directly disagreed with that statement, saying "Stats don't lie", or that stats can never be untruthful. I find it highly skeptical that your reply could be interpreted as "Stats don't lie about this single individual point I am making about KG", but like kendogg, you were instead speaking broadly. "Stats don't lie" is the only part of your post that I quoted, because it's the only part of your post that was relevant to the counterpoint. Namely, forming an ideology based around the premise that "stats can never be untruthful" seems like a dangerous approach to take from a critical thinking standpoint. If you believe otherwise, well......ok.

Man, read my damn post. I explained it well enough why I think stats can't lie at all. Without mentioning KG a single time.

Stats don't lie, you only have to be aware of how to use them (misuse of stats is the fault of the guy that uses them not the stat itself).

I won't engage in another semantics debate with you as I fear this will end up in one, but here is a sum up. My main point is that there is always a reason data is how it is. Even if the reason is simply randomness. Empirical data is collected to draw conclusions about connections between things. It is not collected to show you the connections in itself in a randomless result without a need to interpret it. So when someone who interprets the data isn't aware about the possibility of randomness in the model, yes, he is the one to blame. The same is true about premises made in the models. So where is the lie? A model has a KNOWN room for error and KNOWN premises. Also I don't know what is happening in your statistic courses, but I had 3 statistic lectures during my time at university and I never was told that stats can lie, but that just on a side note.
If you wanna say stats can be random, that is true, but it is on the guy who interprets it to know that.

Not a single inclusion of KG.

How is it the stats fault when the guy that uses it doesn't educate himself how it is properly used or how much error it can have?

Stats and the models creating them have room for error, that is known. They also have certain premises, that is also known.
A lie is a false claim to deceive someone. How does the stat or model deceive you when the information about it are well known.

Don't bother to reply to me again. First the objectivity thing and now that one. If you would have read a dictionary on the words you used, we wouldn't even need to have these discussions.

You are so indignant that it's borderline insufferable. MY first post already addressed all of your supposed "non KG" points you keep repeating. Perhaps if you would have read it you'd understand why what you're saying isn't a valid counterclaim to what I'm stating. You're not above reproach, and quite frankly, it's humorous for an ESL person to continuously challenge other posters to read the dictionary, especially when they have much more experience with the language than you do. I'm not going to hold your hand and walk you through easily understandable concepts, especially when you have such an obstreperous attitude, but like I said in my first post, there are examples, both theoretical and real life in nature that can be used to reject the statement "stats can never be untruthful".

You can't make sweepingly bold statements like "stats don't lie and any non-truthfulness derived from a statistical analysis is at the fault of the interpreting party" and really not expect someone to call shenanigans, can you? If you don't want people throwing red flags on blanket statements that are tossed around carelessly...then....be more careful about making blanket statements in your arguments maybe? And since you like to keep bringing up dictionaries, perhaps you should go look up the definition of civility.

I read your first post but I don't see how argued any of my points. Some statements go in the direction but aren't disagreeing with what I said except for the sematics part.

As far as I see it you see random results in data as a lie because they misrepresent the 'real world', right? I said that randomness is a known thing, guys that use data should be aware of. So for me this is a semantics debate nothing more, nothing less. And that was clear since your very first post where you said lying acquires activity instead of passivity. With this you were already opening a door of a semantics debate and you were setting premises (that activity in this case will be disregarded) to show what YOU mean or understand when you hear that statement. I gave you how I see it (and passivity is actually the first thing for me why stats can't lie).

But you want to stubbornly continue to make this senseless semantics debate as if one is right or wrong in this case.
The word lie by its very meaning can't possibly qualify for stats. I made that clear. You just discuss it with your own premises (excluding requirements for lying) and now want to call me out for what exactly? That I used words for their very meaning?

By the way I give my best with my english. I understand the word 'lie' pretty good and that is exactly what I was calling you out for.

Saying the things I say are wrong when I mentioned that I take the word 'lie' by its exact meaning when you didn't and to see that I am not wrong you just have to open a dictionary. If you want to see the word 'lie' in a way that it excludes the activity part, go ahead but don't say I am wrong because I don't. Then using my english skills to get into a position of authority is just weak when the word in question is as simple as the word 'lie'.

These discussions are so pointless and I knew it in the beginning saying that I am not interested in these types of debates and you still made it one and I was dumb enough to engage. It was the exact same thing the last time which is why I am so annoyed of you going the exact route again this time.
I had you on ignore after last time unfortunately you still get an alert when someone is answering you. I will keep your posts disclaimed in the future.

[penbeast0]

Closing this thread because it has turned into a pointless and annoying discussion that does nothing to address the original question assuming that question was meant to actually talk about these great players' careers rather than make a point about using advanced statistics.