Archive for the ‘Roto Relevant Research’ Category

The dreaded ‘hometown scoring bias’ can go in either direction depending on the situation. Your pitcher is in the midst of a no-hitter? That’s an error. Your hitter is in the midst of a hit streak? That’s a hit. These sorts of situations make it tough to see a pattern through all the noise.

That didn’t stop Doug at HighHeatStats. By taking away errors from home errors for both the home team and away team at each park, he tried to find systematic pro- or anti-error bias in each stadium’s scoring team. It’s a little hard to read the graph, but here’s what he found:

Read the rest of this entry »

We’ve spent a lot of time and energy trying to improve our ERA estimators. In order to really show what the pitcher can control, we’ve taken things out, added things, and moved away from our simplest estimators in a search for the tiniest slivers of r-squared value. In trying to better predict next year’s ERA, we’ve run through FIP, xFIP, tERA, SIERA and more. Plenty of cooks, plenty of spices, plenty of tweaks in this alphabet soup.

Turns out, we coulda stopped before we started.

At least when it comes to in-season ERA estimation, the simplest estimator looks like it beats all the fancy ones. Glenn DuPaul did the legwork on The Hardball Times today, and he found that (K-BB)/IP beat SIERA out for in-season ERA prediction.

Read the rest of this entry »

I can’t get into specifics (so please don’t ask) but I will say this: there are things that are generally publicly held as sabermetric doctrine—in some cases, crucial underlying assumptions—that are demonstrably false. — Russell A. Carlton (nee Pizza Cutter) for Baseball Prospectus

The first frontier for baseball research was correctly rewarding hitters for their work at the plate. Branch Rickey started work on that subject in the 1950s with an equation that attempted to put a number on offense and defense. The second frontier might have been correctly rewarding pitchers for their work on the mound. Voros McCracken famously created the DIPS theory of pitching by showing that pitchers had very little control over a ball once it was in play.

The current frontier is not so well defined. There’s great work being done on pitching injuries, the effect of the shift, and process-based metrics that attempt to quantify ‘stuff.’ We’re constantly trying to stay on top here at Roto-Relevant Research.

Read the rest of this entry »

Search the internet for information about ‘popups baseball,’ and the first few pages of results are largely videos and tutorials aimed at young hitters — chop the ball as if you’re using an axe, keep your back elbow up, stiffen that front leg. Around the third page, you start getting some fielding tips — stay under the ball, block the sun, call off your teammates. Somewhere after the 12th page, you start getting nonsensical or irrelevant results — Tecmo Bowl and RBI baseball ROM emulator downloads, urban dictionary entries, and popup ad blockers.

Not once on the first 20 pages of results is there a ‘how to’ link for pitchers. Surely, if hitters have to avoid hitting the things, there must be a way for pitchers to induce them?

Not if inducing popups is not a repeatable skill.

Read the rest of this entry »

You’ll see it from time to time — ‘this guy is hot, you have to pick him up,’ or ‘this guy is hot, this team needs to move him up in the batting order.’ Brandon Belt was terrible last week, now he should be the number two hitter. Jon Jay is hitting .444 over the past two weeks, maybe you even heard someone tout him specifically.

Except that, if you read The Book: Playing the Percentages in Baseball, you know that a player’s work over the past week or two has little predictive bearing when it comes to his next plate appearance. There’s a recap of the study here if you need a refresher. It makes intuitive sense — if you’ve gathered information on a player for four minor league seasons, and then two-plus major league seasons, why would Jay’s last two weeks stack up to that? We’ve learned all about sample size, and this is in the SSS wheelhouse.

Read the rest of this entry »

The statistician George Box once wrote that “Essentially, all models are wrong, but some are useful.” … Perfect models only occur when severe constraints can be imposed.

Since you can’t have a perfect model, the designer and user must decide what level of accuracy is acceptable for the purposes for which the model will be used. — Patriot, “All Models are Wrong,” at Walk Like a Sabermetrician

If you’ve ever worked in a science or even a social science, some of the practices of the sabermetric community might be surprising. There’s a lower threshold for significant findings, for one. And ‘experiments’ are almost never performed in the same way that you’ll find in a psychology lab. You can’t impose constraints, and there’s no way to test an assertion in a sterile environment. You can’t have an alternate MLB universe where you change one aspect of the game and play it out.

And so, as Patriot affirms, all sabermetric models are wrong. They’ll be wrong somewhere. He goes on to to set up a delicate balance between accuracy at the extremes and simplicity.

Read the rest of this entry »