Predicting Speed Rating from Past Ratings

[Grits]

Originally post by Trifecta Mike
Let me ask a question, which appears to have an obvious answer.

I am fairly new to horse racing and have heard about the importance of speed ratings to predicting winners.

So, I think I've come up with a good idea.

Originally Posted by TrifectaMike

Building a model is not the point here.

Let's move on.

After speaking with some experienced horse players and showing them the results I was given, they all agreed something was wrong.

Another trip to the university. Directed to a more advanced stat guy. He agrees that something doesn't make sense.

He tells me. I'll take your data and stratify it by track. And since I have the results of the races, I'll use a Binary regression (Logistic). All Greek to me. Okay by me.

A week later he informs me that he sees a similar pattern that was observed in the Linear Regression. But not to worry, because he'll redo the analysis controlling for class, distance, etc.

Okay. Whatever you say. Call me when you're done.

Mike

An honest question because I get the feeling your story is contrived. Have you forgotten what you've stated to others, here, in the past... that you are (or were) the educator of grad students at a major NY university? While now, you present yourself as new to handicapping? This is one past thread, summer of 2011. I admit, I'm woefully lost.

http://www.paceadvantage.com/forum/s...2&page=1&pp=15

[Grits]

Originally Posted by Cratos

However what can be done is to create a timefigure (not speedfigure) based on “conditional time impacts” that will be a “what if” timefigure if the arbitrary adjustments are met and that is where the “weights” come in probabilistically.

Cratos, you're a really smart guy. I know this, along with all the alphabet behind your name. However, here's a tidbit you need to seriously consider.

People who are comfortable in their own skin, people who, like yourself, have had a long, successful career. People who are now retired and living well? They don't have to prove anything. They don't write 17 letter, lengthy crap words like probabilistically when something as fine as most likely will do. If you dare roll this one off your tongue in conversation, every friend and associate you've known in your lifetime is gonna be shaking their head.

"Now he's just sitting on the internet playing WORDS WITH FRIENDS. Poor guy."

Please, relax, Cratos. Just be normal.

[GameTheory]

Originally Posted by Grits

Cratos, you're a really smart guy. I know this, along with all the alphabet behind your name. However, here's a tidbit you need to seriously consider.

People who are comfortable in their own skin, people who, like yourself, have had a long, successful career. People who are now retired and living well? They don't have to prove anything. They don't write 17 letter, lengthy crap words like probabilistically when something as fine as most likely will do.

Does that mean you understood the rest of that sentence? I can't make heads or tails of it. Nevertheless, "probabilistically" does not mean "most likely". I don't think there is "normal" substitute for it -- if you're going to talk about probability, you're going to have to use technical words here and there. But some further explanation and clarification is in order if you do want "normal" people to get the gist of what you are saying. But he may not care about that anyway.

Well before I get to the word "probabilistically", I am wondering what the difference is between a timefigure and speed figure, what these "conditional time impacts" are, what a "what if timefigure" is, and what are the arbitrary adjustments to be met. "Probabilistically" is about the only thing I got in there...

[Tom]

A very sagacious post, GRITS.
Your perspicaciousness is manifest!

[GameTheory]

Disesteem for sesquipedalian phraseology!

[thaskalos]

It all sounds Greek to me.

[Cratos]

Originally Posted by Grits

Cratos, you're a really smart guy. I know this, along with all the alphabet behind your name. However, here's a tidbit you need to seriously consider.

People who are comfortable in their own skin, people who, like yourself, have had a long, successful career. People who are now retired and living well? They don't have to prove anything. They don't write 17 letter, lengthy crap words like probabilistically when something as fine as most likely will do. If you dare roll this one off your tongue in conversation, every friend and associate you've known in your lifetime is gonna be shaking their head.

"Now he's just sitting on the internet playing WORDS WITH FRIENDS. Poor guy."

Please, relax, Cratos. Just be normal.

In all due respect, what the question is about in this thread is the application of "weights" which would be metrics "Probabilistically" applied.

Incidentally, when I read a post I only concern myself with its "content" and its relevancy to my thought process.

If there is a word that I don't understand I research its meaning and add it to my vocabulary.

I don't sit around thinking of words to impress.

[Greyfox]

Originally Posted by Robert Fischer

TrifectaMike at the very least, presented an example.

An example? An example of What and Where?

How about an example applied to tomorrow's card at any track he chooses, and how it helps handicappers.

That ain't gonna happen.

[thaskalos]

Originally Posted by Cratos

In all due respect, what the question is about in this thread is the application of "weights" which would be metrics "Probabilistically" applied.

Incidentally, when I read a post I only concern myself with its "content" and its relevancy to my thought process.

If there is a word that I don't understand I research its meaning and add it to my vocabulary.

I don't sit around thinking of words to impress.

I had already guessed that...when I read that your "hero" is Warren Edward Buffett. Not too impressive...as far as "heroes" go.

[Cratos]

Originally Posted by thaskalos

I had already guessed that...when I read that your "hero" is Warren Edward Buffett. Not too impressive...as far as "heroes" go.

Sorry, we all have our " heroes" and WEB is mine.

[whodoyoulike]

Originally Posted by Greyfox

An example? An example of What and Where?

How about an example applied to tomorrow's card at any track he chooses, and how it helps handicappers.

That ain't gonna happen.

I'm kicking myself for reading most of the posts in this thread. I actually thought he would provide an example of how and when to use it. I will be very surprised if there is one but, I think "that ain't gonna happen" either.

I like your quote Greyfox, hope you don't mind. I would like to start using it when discussions about CDI and their plans on lowering take out comes up.

[HUSKER55]

Originally Posted by GameTheory

Disesteem for sesquipedalian phraseology!

that is easy for you to say.....

[whodoyoulike]

Originally Posted by Grits

An honest question because I get the feeling your story is contrived. Have you forgotten what you've stated to others, here, in the past... that you are (or were) the educator of grad students at a major NY university? While now, you present yourself as new to handicapping? This is one past thread, summer of 2011. I admit, I'm woefully lost.

http://www.paceadvantage.com/forum/s...2&page=1&pp=15

Thanks for the link, I missed it first time around. I guess he still hasn't really comprehended what others have posted in that thread.

[whodoyoulike]

Originally Posted by TrifectaMike

Ok. I (the new guy in post 1) take your advice (linear regression) make a visit to a local university and ask for help. A grad student, for pay, is willing to help. He directs me to get a years data for all tracks and performs a linear regression.

A short time later he delivers his results. The grad student knows nothing about horse racing. His results show that one weight is insignificant and it is not w4, which if I believe that more recent performances are more important...seems odd to me. But he can't help any further.

Mike

Were you the grad student? So, how do you predict speed ratings from past ratings?

[TrifectaMike]

Originally Posted by whodoyoulike

Were you the grad student? So, how do you predict speed ratings from past ratings?

With a Hierarchical Bayes Model

Mike