Search results

http://lmgtfy.com/?q=2012+analysts+forecast+%22s%26p+500%22

Not sure how accurately JO correlates with futures but...

The top "psychologists" work for Morgan Stanley, Goldman Sachs, Barclays, JP Morgan Chase, etc. They don't have to trade money because you willingly give them your money. Instead they trade other things.

Thanks for the details. I would expect stocks to be highly correlated with the index they're in, for example Apple and Google should be highly correlated with both the Nasdaq 100 and the S&P 500. However Apple and Google should be less correlated with the Russell 2000.

Your strategy might only work during bull markets. In either bear market or choppy directionless market it might tend to fail. This site follows breakout and unusual volume and growth stocks: http://volumewatchers.com/

Can you run these cloud (SaaS) companies.... Ariba, Inc. (ARBA) Citrix Systems, Inc. (CTXS) Cornerstone OnDemand, Inc. (CSOD) DemandTec, Inc. (DMAN) Kenexa Corporation (KNXA) NetSuite, Inc. (N) Salesforce.com (CRM) SPS Commerce, Inc. (SPSC) Taleo Corp. (TLEO) Ultimate Software...

+1 "In capitalist America, the game games you." * * http://images.icanhascheezburger.com/completestore/2009/2/17/128793922234337800.jpg

If this chart is to be believed, U6 unemployment during the Great Depression peaked at around 37-38%. So we have a ways to go to get there. And even then Europe will probably revolt before the U.S. does. The Europeans know how to properly protest en masse in the streets.

KER?

R-squared and Adjusted R-squared Correlation between y and y-hat F-test and significance level of F You are right that R-squared is goodness of fit. I mean to say, in layman's terms there is more than one way to tell the regression is trying to fit chop. If the residuals and measures of...

Regarding (a), on the contrary, just try doing linear regression in Excel. Various goodness of fit statistics are generated. It is easy to tell a good fit from an attempt to fit chop.

You're missing the point of my response. The context is "so many times during the day". While algos may incorporate short term memory, most algo research is on long term memory. When talking about multiple intraday moves, it is unlikely that long term memory is being considered.

Does the mkt have a memory? NO. Because 70% of trading is algos. Does the mkt have a memory? YES. Because memory is usually defined to be longer term than algo time periods.

Agree 100%. Forward walk is very important, it is all too easy to fool oneself with something that backtests great. I haven't read the entire thread but if data is 3 years 2007 - 2010, try testing the same strategy for 3 years 2003 - 2006 or any other untested 3 year period, while not a forward...

Short is approx 21% of float, although less than a month ago. Other companies with high P/E and large percent of shares short: http://finviz.com/screener.ashx?v=121&f=fa_fpe_o25,fa_pe_o25,sh_curvol_o1000,sh_short_o20&ft=2 ATHN athenahealth, Inc. P/E:100.43 Fwd P/E:40.92 PEG:2.71 DANG...

Is this information useful? Or useless? http://www.bloomberg.com/news/2011-06-24/u-s-stock-options-with-biggest-changes-in-implied-volatility.html?cmpid=yhoo

Yes it will be a really bad estimate. Basically use the inverse of the liquidity ratio "how much dollar volume is required to move a stock's price up or down by one percentage point". Plug in the percent move and there you have the (very approximate) volume.

I'm not sure if this is what you mean, but it is common enough to create a random* time series and test against that. Basically this can, among other things, determine how much random element is part of the time series. Also look into cross validation. Cross validation helps avoid over-fitting...

My anecdotal experience agrees. Although I think some US freelancers have learned to do the same thing. Claim it will be done in 2 weeks, ahead of time, under budget. Then 2 weeks later the project is 2% complete because "Oh it was more complicated than we expected" and any assumed features that...

Keep in mind there is at least one known regime shift, I forget the year, but within the last 20 years for sure and possibly within the last 10. So testing for 20 years may be too long. (Depending on the strategy. It is possible to have a strategy is regime independent and in that case 20 years...