Search results

The only place I know of so far is CRSP, they supposedly have the weights for each stock every day. Unfortunately it is super-expensive and I don't know anyone with a subscription that includes the index module. If you find another source please post.

I tried to do this using the current S&P 500 and the historical add/drops from the S&P website. Don't do it that way! It sucked and I gave up, I will probably just buy it at some point.

Here's a paper that has my favorite way to measure earnings surprise. They call it ABR - it is the 4 day abnormal return around the earnings date. It seems to work better than the accounting based measures (recently too) and is much easier to calculate. And if you combine it with an...

Size - I am pretty sure I have seen a published study where the earnings reports in the holding period actually add to the returns of the system, implying future earnings surprises tend to be in the same direction as the last one. It was old so it may be worth checking if still true though...

Hey Talon, More good stuff. I never traded this but have backtested it. Here's what I did. This is from memory, if the discussion continues I'll look for the actual code and results. This is based on the academic literature, not my own ideas. 1) Start with a database of all earnings...

I don't know but my linear regression model told me I would see a thread like this one day.

I think about it more like don't let your ideas add up into an unintended sector bet.

There are sector portfolio definitions and historical returns at different levels of granularity at: http://mba.tuck.dartmouth.edu/pages/faculty/ken.french/data_library.html You can use the historical returns to get some idea of how different "max % of portfolio" rules would have done in...

Hi Talon, Good thread, please ignore the aholes and keep with it. Also for the skeptics I can somewhat vouch for the idea - I have seen the research and know somebody who trades (or used to) trade it. But I am particularly interested in knowing how you get confidence that it still works...

Seriously, I don't see what the 'controversy' here is. Of course its not conclusive but I think it is cool that somebody runs these tests and shares the results. Not interesting enough to actually read though.

Page 5 you bitch! Sorry I couldn't resist.

I actually think differently. IMO it is easier to get something that works on a basket. Say there is a predictable component of a stock's return and an unpredictable surprise component. In an individual stock your return can be dominated by the surprise component even if your algorithm...

No, I don't mean a scanner. There are different ways to do it but what I am thinking of is called a Fama-Macbeth regression, and it definitely meets your need for putting it together an making a projection. It is especially good in sorting out redundant information from multiple indicators...

The short answer is I don't know. Without knowing much about this market I would guess the third one. But I can imagine scenarios where the other two would be better. BTW this description sounds funny - I didn't think it is called PFOF when the MM gets paid a rebate. Is that correct? I...

Thanks for the reply. I understand, I just don't agree. You might be right about what rules the exchange should choose but I don't think things like that should be mandated without a strong reason. IMHO protecting small liquidity providers is not a strong reason. As I said before I think...

This is similar to what a lot of quant equity strategies do, and the basic framework is in the public domain. I can post more on it later maybe with some references but the basic idea is you have a regression model with return on the left hand side and a bunch of stock characteristics on the...

Nitro - I am curious why you think payment for order flow is bad. Do you think this is true in general? I would think if a market can increase volume by getting more market orders they should pay for order flow. If they need more limit orders they should give a rebate for providing...

You can tell from CBOE data when MM's are long or short. It varies. FWIW I was told by someone who worked on a swaptions desk that they usually want to be a little long vol overall - little theta losses are part of life but big losses get people fired. But they can be very short in a...

When I am kind of rich I am going to hire a bunch of people to impersonate BLS workers and do my own survey so I will know ahead of time. Then I will get really rich. So hopefully I will be able to tell you the day before in a few years if you ask nicely, but no clue for tomorrow.