Comments on Basement Dwellers: A dirty way of predicting reliever leverage when p...

Wow, awesome post.

I run a Rays' blog over ...

2008-01-15T18:08:00.000-05:00

Wow, awesome post.

I run a Rays' blog over at RaysBaseball.Blogspot.Com

Would you like to trade links? If so, just post a comment on my blog and we've ourselves a deal.

Tango,

Wow, thanks for that, and especiall...

2008-01-15T14:28:00.000-05:00

Tango,

Wow, thanks for that, and especially for your step-by-step explanation in post #5 in the linked thread. I may give that a go and see how well I can automate it.

I sure wish that Sagarin's files included lahman or retro ID's, though I can usually construct a lookup string.
-j

Justin, post #1 here shows how to do historical LI.

Hi Dan,

I just went to the 2007 leader boar...

2008-01-14T19:07:00.000-05:00

Hi Dan,

I just went to the 2007 leader boards at fangraphs (linked above) and did the 'ole copy and paste. The only irritating thing about it is that they only show 50 or so players at a time IIRC. That's part of the reason that I limited my sample to 25 IP or more in a season. :)

If you're interested in my spreadsheet, I'm happy to send it your way. Just fire me an e-mail: jinaz.reds@gmail.com
-j

Justin, I'm very glad you wrote this piece, as I w...

2008-01-14T19:01:00.000-05:00

Justin, I'm very glad you wrote this piece, as I was thinking about a portion of this just a few days ago. I didn't feel like e-mailing David Appelman (he never responds, it's very annoying), so I'll ask you... How did you get the pLI numbers from Fangraphs in bulk? I can't imagine you went player by player writing it down, that would have taken days. If you can just write a little step by step of how to extract data from fangraphs that would be much appreciated.

Dan

@Rick, I agree that it's something that might be w...

2008-01-14T18:07:00.000-05:00

@Rick, I agree that it's something that might be worth thinking about moving forward. ... But I'm ok with leaving it as it is for now. :)

@Alex, you got me. :)

The link is pretty funny though. Word 'round the campfire is that the Israeli Baseball League is unlikely to continue much longer, which is unfortunate.
-j

I think I found you, Berliad... :)

Just tho...

2008-01-14T16:53:00.000-05:00

I think I found you, Berliad... :)

Just thought you might enjoy this:

http://www.israelbaseballleague.com/baseballinisrael/biblical/

Fair enough, I didn't realize fangraphs had it for...

2008-01-14T16:21:00.000-05:00

Fair enough, I didn't realize fangraphs had it for hitters and the figures back up your point. Good stuff. Still, while the effect might not be as large on a per PA basis, because the volume of performance is so much larger, the effect on overall value may still be important for hitters. A 10% boost or decrease is nothing to sneeze at.

Interestingly, the two highest pLI for positional players are both Giants -- two guys who tended to bat very near the highest OBP guy in baseball.

What?! You want me to support my claims with data...

2008-01-14T16:03:00.000-05:00

What?! You want me to support my claims with data?! :)

I don't know of a comprehensive study on this, but the effect is pretty dramatic. I'd just recommend going to fangraphs and looking at the 2007 leaderboards for hitters, starters, and relievers.

Qualified hitters had pLI's ranging from 0.92 to 1.17.

Qualified starters had pLI's ranging from 0.87 to 1.09.

There's no "qualified" button for relievers, of course, but among those with >50 IP, pLI's ranged from 0.48 (Chris Bootcheck) to 2.35 (Trevor Hoffman).

I'll grant that some of that may be sample size, but Hoffman (to take one example has had pLI's of 2.02, 2.12, 2.08, and 2.35 from '04-'07. That means that we effectively have to DOUBLE his RAR to get a reasonable picture of his impact on wins.

You'll see minor deviations from 1.0 for hitters and starters, but rarely are they more than 10% or so (compared to 100% for closers). Looking through the numbers, it certainly does seem to be the case that middle-of-the-order hitters tend to have slightly higher pLI than other hitters, but we're talking about pLI's of 1.00-1.10 instead of 0.95-1.05. Nothing like the doubling of pLI that we see in closers.

If I can summarize, the purpose of using a leverag...

2008-01-14T15:44:00.000-05:00

If I can summarize, the purpose of using a leverage adjustment is to account for the fact that opportunities are not distributed equally in regards to their potential effect on game outcome. Thus, to estimate the effect of a given player's performance on game outcome, we must adjust for this usage difference.

Is this fair/accurate?

Without challenging the accuracy of your claims, do you have any data back your claim in your first paragraph?

It would seem to me that the manager does have great affect over the leverage of batters. How many men were on base for Brandon Phillips versus Adam Dunn by virtue of the place in the lineup? Ryan Howard had lots of opportunities to drive in runs, certainly a statistically significant difference of greater opportunities than were they randomly distributed. All else equal, were he asked to bat 8th, rather than cleanup, surely his performance would have had a significantly different effect on wins.

That managers choose to bat hitters such to maximize the effect of their performance seems akin to reliever use. Now, unlike pitchers, managers cannot control the specfic scenario usage with hitters. They can however, try to maximize the interaction effect of having ones best hitters grouped together. That Ryan Howard batted 4th and not 8th did have some multiplicative effect on the win-value of his performance. Perhaps, as you suggest, it's merely an order of scale, but it seems to deserve more than a paragraph's worth of treatment. Maybe you can direct me to a thread elsewhere where this was discussed?

For starting pitchers and hitters, seasonal deviat...

2008-01-14T12:28:00.000-05:00

For starting pitchers and hitters, seasonal deviations from average leverage are more or less random events, and few hitters or pitchers with a full season of data come in with a pLI that's particularly different from 1.0. Therefore, a hitter's runs above replacement, for example, translates closely to his wins above replacement. And wins really is what I'm after, ultimately, because that's the currency of success in baseball.

The same is not true for relievers. Managers have considerable power in determining what sorts of situations relievers are used. Therefore, because closers, in particular, tend to be used more in high-leverage situations, their runs allowed influence wins more than other players. This is predictable and repeatable, which is why I think it's important to consider it in these estimates.

Including leverage w/ releivers is not the same as including OPS with RISP in one's RC estimate. That's an adjustment that looks at how a hitter did in a fraction of his plate appearances, and then adjusts the overall production by his performance in that fraction of appearances. Those clutch performances, as I'm sure you're aware, have very little repeatability, which is why I tend to not be interested in bothering to adjust for them.

But with relievers, we're adjusting their entire performance based on the leverage of situations in which they pitched. So if a closer pitches in situations that are, on average, twice as important as normal situations (pLI=2), this approach essentially sets any RAR he provides to have double the value...no matter how well he does overall.
-j

Justin, can you make the generic case in why we sh...

2008-01-14T11:55:00.000-05:00

Justin, can you make the generic case in why we should look at leverage in assigning value? It seems to me that for offense, we try to neutralize away opportunity. Isn't leverage akin to OPS w/ RISP or some other such measure. There seems to be an inconsistency in this approach. If we're going to include the "when" issue for relievers, shouldn't we be doing it for everybody?