With or Without You: Mario Lemieux

[seventieslord]

Just to ask. Do you mean that one is not "a serious stats guy" if one uses methods other than "on/off" to adjust the raw +/-?
Or are you referring to "adjusted +/-" as opposed to raw +/-?

I spent an hour, in the middle of the night, trying to explain to you how I meant, so I would find it a bit disrespectful if you just discarded my attempt to answer you.

No, I am just saying that raw +/- is next to useless and it is ridiculous to conclude that player A is in any way better than player B just because his +/- is better. adjusted +/- removes a ton of the bias and provides a good starting point for discussion.

 

[Czech Your Math]

Just to ask. Do you mean that one is not "a serious stats guy" if one uses methods other than "on/off" to adjust the raw +/-?
Or are you referring to "adjusted +/-" as opposed to raw +/-?

I'm pretty sure he means the bolded.

I tried to address much of what you've been saying in the sticky thread, but personally, I don't want to clutter that with this type of discussion. Maybe in the future, if there's not much content there, it would be worthwhile to use that thread for purposes other than posting links to studies. I've also encouraged you to link to some/all of your studies, if/when you want to do that. You should realize that there are only so many people who A) may have seen a particular study you did, B) be able to understand the process and implications of the study, C) felt they had something worthwhile to say about it.

From my limited knowledge of only some of your studies, or aspects of them as presented them in various threads, I know you are very capable and very rigorous in your methodology. I think you're expressing the natural frustration that goes along with many hours developing and researching larger studies of that sort. As you know, it's difficult to perform a study which:

- is understood by most and/or more easily understood by those properly qualified to evaluate it
- is interesting to a broad spectrum
- is more comprehensive in nature
- covers a long span of time
- is broad in its impact, IOW has a meaningful change in how teams/players are evaluated and valued
- is easily applicaple to exisiting data, esp. on a broad scale

I don't know why you don't receive more feedback, but some of the factors are listed above. Starting or "bumping" a thread for your study is the best way to receive meaningful readership and constructive criticism. The newly created sticky thread is meant to assist in reaching a wider audience for such specific threads.

My intuition is that you may overwhelm many with the amount of data which you often present, your rigorous methodology is not easily understood by the casual reader, and it may be difficult to apply some results directly and meaningfully in a short amount of time. I don't think is uncommon, nor particular to your studies, as I also run into this. I'd rather constructive, meaningful feedback from the select few who understand what is being presented, than a bunch of pats on the back from people who may not understand the study, don't care about the process, don't realize its implications and/or applications, etc. The goal as I see it is to improve one's own study, make it of use to a more (but likely still very limited) audience, and let it be read and used by others who may use it to build and/or improve their own studies. It's not a quick and easy process to advance the knowledge in any area.

That's why I would suggest starting/bumping a thread for the study that meets the most or most important criteria (from your perspective) and see what happens. If you receive some meaningful feedback about at least one study, it may give you insights into how your other studies could be modified or presented differently. If you do that at least a couple times with what you feel is your best work, and no one seems to care or respond, then perhaps you are right and either not enough value your studies or not enough really understand what is being presented to them. If you are performing such studies mainly in hopes of glory or mainly for reasons other than your own innate curiosity and enjoyment, then you may be disappointed, but I wouldn't suggest giving up until you are more certain that is what is best.

 

[Czech Your Math]

This would be mostly because of the players they play with and the players they play against, correct? Brian MacDonald has calculated fully adjusted plus-minus numbers that account for these factors, but they only cover the last few seasons because they necessary data only exists for those seasons.

Just looking at the data it appears that having 2 or 3 star players together on a line is a big factor in plus-minus, including basic adjusted versions. See Trottier/Bossy, Simmer/Dionne/Taylor, Gretzky/Kurri, Savard/Larmer, Leclair/Lindros, Kariya/Selanne, Heatley/Spezza/Alfredsson, etc. Compare to players like younger Steve Yzerman or Dale Hawerchuk who didn't have star linemates and didn't stand out in plus-minus. Marcel Dionne was only OK in plus-minus in his first few seasons, but when Dave Taylor and later Charlie Simmer joined him they were dominant in plus-minus.

If you want to move beyond a "basic" adjusted plus-minus and start adjusting for teammates, by all means go for it. I haven't done so because the data isn't easily available and I don't want to put the time into merging databases (one of those time-consuming tasks that is often required). But it might be possible to adjust historical (pre-lockout) data for the effect of linemates to some degree by using the number of even strength points players participated in together as a proxy for time spent together.

As you point out, except for very recently, there just doesn't seem to be enough data for which teammates were on the ice together at ES, nor for which opponents they faced at ES.

I think plusandminus mentions one factor that might possibly be used to refine adjusted plus-minus further, which is to divide the ESGF portion more in proportion to ES points/ESGF for each player. The ESGA portion has less optimal options. Does one somehow reduce the ESGA attribution for forwards (which are generally focused more on ESGF) and increase it for d-men? I think to do so fairly would be difficult without the appropriate data.

I really like the elegant simplicity of adjusted plus-minus, as I've said in previous posts. Adding more components could yield an even better metric, but one would have to be confident that the new attributions were fair and consistent for both forwards and d-men, which seems difficult to achieve while retaining similar understanding and acceptance of the current metric, esp. given the limits of the data as you go farther back pre-lockout.

 

[Czech Your Math]

Well, I tried to give my point of view, and to explain how I looked at it. You seem dead sure that it's only about what you write above. I am familiar with other methods. I'm a bit surprised others aren't. Maybe some kind of misunderstanding somewhere.

I'm not sure what you mean here. I have read many studies on HF and on other sites, but not most. I read those that interest me and/or may be applicable to studies I may have done or will do. I assume that others do the same if anything.

I think I understand the logic and methodology of adjusted plus-minus. If one had the proper data, one could refine the metric further. One such way is to factor in the teammates and opponents on the ice for each GF or GA. I believe someone is already doing this? This seems like a good refinement. Studies that uses much less direct data like shots and/or more subjective data like shot quality is not something in which I'm very interested, because it is so subjective IMO.

I disagree with you. And I have tried to explain why, and how I think. I think both methods have advantages and disadvantages. I do think I know enough hockey, and statistics, to have a decent understanding of what I'm talking about. And I do think you too knows math and stats well, and knows a lot about hockey.

For example, the best players on a team aren't necessarily the ones with best +/- on the team (or best ES +/- per time unit).

I said yesterday, I have spent very many hours during the last year on NHL stats. While it has broaden my knowledge, and made me learn interesting things, I came to a point where I thought it might be enough for me. I have examined lots of things. There are many more things to examine, but from my point of view it would require a lot of work, and I think I at this point rather stop where I am.

I had hoped I would have been able to better communicate here about some things, but it seems I can't. I've been into stats and hockey since the late 1970s, and been writing here for about 16 months, and would have hoped to sort of have "made a name" here by now (among the regulars). But instead, when I write it's a bit as if the respondents think I have just turned my attention to hockey and its statistics. Instead of getting a feeling they sort of know in general about my previous posts and studies, and all the work I have done in organizing data in order to do studies few (or sometimes none) here are able to currently do, I never get referred to or even mentioned.

While I learn all the time from others, it seems as I basically can't ever make others curious or "learn" about things I write. Seldom anyone writes something like "Good point!" or similar, like is often the case when others write. If (hypothetically) there are 12 things that matter, and I take the time to go through 10 of them, I get replies about the the I didn't mention rather than the 10 I mentioned. (I know I myself often tend to focus on missing things, but tries to balance it.) This isn't news to some here, as this is how I've been experiencing things for a while.

I am still sure that I have things of value to contribute with, things that will help bring hockey knowlegde forward. I think I would be a loss for the forum if I stopped writing. But as I said, after about 16 months here it's obvious (in the eyes of the regulars here) I am just where I started, and definitely wouldn't be missed. So it would be unwise for me to participate here due to "the warm climate", "supporting atmosphere" or because "this is a place where I feel appreciated", because to me it's rather the opposite. If I have a strong and true curiosity about learning more about NHL and its stats, then that in itself could be a strong reason for me to spend time here in order to get feedback and inspiration. And so it was. But now my curiosity have started to fade, and I think that if I try to discuss "advanced" things in a half-hearted way, it may not turn out very good.

I also feel I'm at a level now where any discussions like the ones here in this thread, will be "advanced" and take up a lot of time. I'm "done" with most of the more easy studies (like "on/off +/-" or "adjusted points") and would want to "move on" to more advanced studies that builds on the common ones. And that takes time, lots of time, and discussions also take lots of times. And there will be very few, if anyone, to discuss them with. And based from previous experience here, few if any would be interested anyway. Plus that I have a feeling that even very time consuming studies won't help us get rid of different biases anyway.

Maybe I ought to summarize. Thanks for your questions and suggestions. It's hard for me to reply because it seems to require me to explain about my "whole focus", so I tend to write fragments that I feel are being prone to misunderstandings.

I can understand why you feel as you do. I think most are either not interested, can't completely understand and evaluate, or are busy with their own studies. You're probably right that most will keep their biases in the face of any and all new evidence, that's just human nature mostly.

I'd always be open to help with or co-author a study as time permits. However, you seem to want to move on from the very topics I'd be most interested in looking at further, such as how to more effectively compare across eras. A couple of months ago, we started to discuss, in the the thread for my study, how to possibly improve which players are included and which seasons, etc. If I had a complete database in useable format, I would be more inclined to do it myself. You did some related to work, so perhaps the two can be combined in some way? (your database, code writing, and related studies... with my study). My aim was for an index number by season that could be used to compare across seasons. You could also combine that with adjustment by schedule, so that there's an index factor by team and season, such as "1986 Edmonton" or "1989 Pittsburgh."

Honestly, I may not be doing much more work in this field either, for many of the very reasons you give. I think the interest and understanding is very narrow, so that only a few really appreciate what is being done and the efforts involved. Rather than be frustrated by this, it is best, as you say, to face this. I do studies out of interest and enjoyment, as you suggest, and to keep my analytical skills sharp. Also, even when I try to help others see things or help with their studies, they often would rather cling to their biases, as you suggest. Basically, I'm approaching the combined limits of data, my interest in the data, and the ways in which I know how to effectively use the data to produce results that may be valid and of interest/use to others. If that's the case, then I can "retire" satisfied. If something piques my interest, then I can always come out of retirement.