Reputation
3,506
Top tag
Next privilege 4,000 Rep.
Access 'trusted user' tools
Badges
8 16
Newest
 Yearling
Impact
~88k people reached

Oct
6
revised Why does it take so many lines of code to price even the simplest of options with QuantLib
Fixing some spelling issues.
Oct
5
answered Autocorrelation in the GARCH model residuals
Sep
29
comment How to perform risk budgeting for non-linear portfolios?
See papers.ssrn.com/sol3/papers.cfm?abstract_id=2276632 and papers.ssrn.com/sol3/papers.cfm?abstract_id=1358533
Sep
28
answered Tests for Mean Reversion in a Portfolio Rebalancing
Sep
25
comment Tests for Mean Reversion in a Portfolio Rebalancing
You should read up on cointegration. Learn about the Engle-Granger test. If your portfolio weights are proportion to regression coefficients, then it should be similar to what you're talking about wrt testing for mean-reversion in a portfolio of assets.
Sep
25
answered Adjust regression for thin trading
Sep
8
comment Is there any index calculation methodology that is suitable when constituents change frequently?
I would probably consider the concept of an index to be broader than the concept of a benchmark. There are a number of goals for a benchmark that you don't necessarily need to have with an index. You want to easily replicate someone's benchmark. You have a bit more freedom with an index. That means that what's "suitable" depends. For instance, you could specify some objective and then tell the optimizer to constrain turnover in order to handle frequent adds or drops. Lots of options.
Aug
11
comment Calculate turnover for portfolio
@user1723765 I'm getting null when I try to extract them from results. That why I thought it was the issue.
Aug
11
comment Calculate turnover for portfolio
I think the problem is with the line results <- Return.portfolio(data,rebalance_on="months",geometric=F,verbose=T) It is returning a xts/zoo type, rather than a list of the multiple outputs that you're trying to get from it.
Aug
11
revised Calculate turnover for portfolio
Fixing some issues
Jun
11
answered Reproducing levels when PCA has been done on changes
Jun
11
comment Reproducing levels when PCA has been done on changes
You might want to add some more details about what kind of analysis you want to do about the levels. For instance, do you want to forecast the future levels of the time series.
Jun
4
comment Beta Constrained Markowitz Minimum Variance Portfolio - Closed Form Solution
The constraints can be grouped together to something like $Aw=b$, so that the lambdas are a vector. This set-up is actually pretty common. I typically refer to the derivation in edoc.hu-berlin.de/master/jiao-wei-2003-12-16/PDF/jiao.pdf
Jun
3
comment Regression model when samples are small and not correlated
@cogolesgas It wouldn't surprise me that it's very low. However, it might or might not be a statistically significant relationship. Moreover, they could also test applying the equation to hundreds of stocks and see if it makes sense to try to trade on it.
Jun
2
comment Regression model when samples are small and not correlated
I think you should give a few more details as to the motivation of using the Kalman filter and why it would be useful in this case.
Jun
2
comment Regression model when samples are small and not correlated
I'm finding your notation a little confusing. D represents date, T represents intraday time. The (dt, dt+1) and (dt-1, dt) are a little confusing. It might be better to put all of that explanation in Latex like the formula. Anyway, I'm not sure about any "machine learning" technique, but I would recommend a mixed effects model (see lme4 for R) to allow you to group the dates.
May
27
comment Compare performance buy-and-hold strategies after stock-split
That formula looks like a good start.
May
27
comment Compare performance buy-and-hold strategies after stock-split
My recommendation would be to focus on the cumulative difference in returns around the splits and to ignore the longer-term.
May
26
comment R package for portfolio
Auxiliary variables can be tricky though when you extend them to other circumstances, like turnover constraints or transaction costs. You sometimes have to impose additional constraints to ensure that $w_{i}y_{i}=0$, which makes the problem no longer fit for quadratic optimizers.
May
26
comment Compare performance buy-and-hold strategies after stock-split
I'm not sure I understand what you're talking about here, but the fact that two share classes don't have a statistically significant difference in returns is not surprising.