Re: [R-SIG-Finance] CUSIP Numbers
I've always gotten CUSIPs from the finra website. I haven't tried to scrape them, but it shouldn't be terribly difficult with Hadley's rvest package. > On Jan 21, 2015, at 10:45 AM, Anshul Pandey wrote: > > Hi All, > > I am moving some of my backtesting logics to CUSIP from tickers. > How do I download the CUSIP number of US stocks? > > I know S&P has a paid subscription, but I read that CUSIP is publicly > available at a few resources. > > Any suggestions are highly welcome. > > Thanks > Anshul > >[[alternative HTML version deleted]] > > ___ > R-SIG-Finance@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-sig-finance > -- Subscriber-posting only. If you want to post, subscribe first. > -- Also note that this is not the r-help list where general R questions > should go. ___ R-SIG-Finance@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-finance -- Subscriber-posting only. If you want to post, subscribe first. -- Also note that this is not the r-help list where general R questions should go.
Re: [R-SIG-Finance] CUSIP Numbers
Thank you all for the reply.
This is very helpful.
I am going through the Bloomberg Open Symbology. Looks like CUSIP and SEDOL
are becoming popular (the last 3 hedge funds I talked to mentioned one of
these two), so it would be nice to see what Bloomberg has to offer.
James, you raised a very valid concern. I will keep that in mind while
setting up my production system.
Best Regards
Anshul
On Thu, Jan 22, 2015 at 3:55 AM, G See wrote:
> Since this is an R mailing list, I'll try to bring this thread back on
> topic. Unless you are willing to pay, the only free source that I am
> aware of to get CUSIPs via R is TradeKing.
> https://developers.tradeking.com/documentation/market-ext-quotes-get-post
>
> You must have an account, but you can create an account for free and
> you don't have to fund it in order to do this.
>
>
> library(ROAuth) #importFrom(ROAuth, OAuthFactory)
> library(RJSONIO) #importFrom(RJSONIO, fromJSON)
>
> #' ## This part could go in your .Rprofile
> #' # Set your application keys #
> https://developers.tradeking.com/applications
> #' cKey <- ''
> #' cSecret <- '#'
> #' oKey <- ''
> #' oSecret <- ''
>
> # Set the API endpoint
> tkURL <- "https://api.tradeking.com/v1/market/ext/quotes.json";
>
> # Create the OAuth connection - this is straight from the ROAuth
> documentation on CRAN
> credentials <- OAuthFactory$new(consumerKey=cKey,
> consumerSecret=cSecret,
> oauthKey = oKey,
> oauthSecret = oSecret,
> needsVerifier=FALSE,
> signMethod='HMAC')
> # Update the connection so the handshake is TRUE
> credentials$handshakeComplete <- TRUE
>
> Symbols <- tolower(c("AAPL", "MSFT")) ## Whatever symbols you want
> symbols <- paste(Symbols, collapse=",")
>
> #what <- "datetime,bidsz,bid,ask,asksz,last,chg,pchg,opn,hi,lo,vl"
> what <- "cusip"
> what <- gsub(" ", "", tolower(paste(unlist(strsplit(what, ",")),
> collapse=",")))
> tkURL <- "https://api.tradeking.com/v1/market/ext/quotes.json";
> query <- list(symbols=symbols, fids=what)
> response <- credentials$OAuthRequest(tkURL, query)
> res <- fromJSON(response)
> qt <- res$response$quotes$quote
> qt
>
> #[[1]]
> # cusip exch symbol
> #"59491810" "NASD" "MSFT"
> #
> #[[2]]
> # cusip exch symbol
> #"03783310" "NASD" "AAPL"
>
> HTH,
> Garrett
>
--
Anshul Vikram Pandey
+1-929-231-6784
home: www.anshulvp.com
thoughts: www.anshulvp.com/blog
contact: anshul.b...@gmail.com, he...@anshulvp.com
[[alternative HTML version deleted]]
___
R-SIG-Finance@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should
go.
Re: [R-SIG-Finance] IBrokers Package: wrong Clientid returns ?
I use stable version. I tried latest beta too, didn't help.
Indeed downgrade fixed clientid problem but my main problem
(https://groups.yahoo.com/neo/groups/TWSAPI/conversations/messages/33071 ) ,
event handler returns garbled data persists, instead of correct 2100 error I
still get :
paraml[[1]]= -1
paraml[[2]]= NA
paraml[[3]]= PF1
paraml[[4]]= API client has been unsubscribed from account data..NA
I guess I need to contact IBrokers maintainer , I can't think of what else to
do .
best
ce
-Original Message-
From: "cen six" [cens...@gmail.com]
Date: 01/21/2015 11:24 AM
To: "ce"
CC: "r-sig-finance@r-project.org"
Subject: Re: [R-SIG-Finance] IBrokers Package: wrong Clientid returns ?
Well, for sure a downgrade of the TWS would fix it, but its obviously not a
long term solution. Are you using a beta TWS version or a stable release ?
On Wed, Jan 21, 2015 at 4:07 AM, ce wrote:
I downgraded IBrokers version to 0.9-10, while keeping TWS Build 948.3c, Jan 5,
2015 5:12:23 PM ,
still I got the wrong clientid from TWS.
Then I downgraded TWS to Build 945.2b, Jun 3, 2014 11:11:57 AM and it worked
correctly with IBrokers 0.9-10
I see my clientid 96 is returned from TWS :
TWS OpenOrder: orderId=2 clientId=96 conId=14321015 symbol=GBP status=Filled
-Original Message-
From: "ce" [zadi...@excite.com]
Date: 01/20/2015 07:52 PM
To: cens...@gmail.com
CC: r-sig-finance@r-project.org
Subject: Re: [R-SIG-Finance] IBrokers Package: wrong Clientid returns ?
Hi Cen six,
I am using IBrokers 0.9.12 from cran r web site.
In fact I was testing the demo program from you emailed me. It was working fine
but one or two weeks ago event handler started to fail ( maybe after IBrokers
update ) as I explained in :
https://groups.yahoo.com/neo/groups/TWSAPI/conversations/messages/33071
then I upgraded TWS but now clientid returned by event handler is wrong.
Maybe I should downgrade IBrokers or TWS ?
ce
-Original Message-
From: "cen six" [cens...@gmail.com]
Date: 01/20/2015 03:04 PM
To: "ce"
CC: "r-sig-finance@r-project.org"
Subject: Re: [R-SIG-Finance] IBrokers Package: wrong Clientid returns ?
Are you using the IBrokers package version 0.9-10 or higher ? (from
code.google.com)
cheers
On Tue, Jan 20, 2015 at 2:38 AM, ce wrote:
Dear all,
I just upgraded TWS to Build 948.3c, Jan 5, 2015 5:12:23 PM
My program that worked fine before started to return wrong clientid . I set
client ID to 96. but after sending the order, In order status , or order
execution events I get clientid 6 !! Even I tried to set Master API Client ID
to 96 in TWS -> Configuration -> API. didnt work.
If I set Clientid to 6, TWS returns 0 as Clientid.
Here is some piece of code :
> ibClientId <- 96
>
>
> #global: create the connection to IB (this can probably not be stored
> anywhere, so
> #we have to recreate it within "IBexecuteStrategy.r"
> ibConnection<-NULL
> if (!is.twsConnection(ibConnection)) {
+ ibConnection<- twsConnect(clientId=ibClientId, host="localhost",
+ port=7496, verbose=TRUE,
+ timeout=15, filename=NULL)
+ }
> print(ibConnection)
TWS OpenOrder: orderId=3 clientId=6 conId=12087807 symbol=EUR status=Submitted
___
R-SIG-Finance@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should
go.
___
R-SIG-Finance@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should g
___
R-SIG-Finance@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should
go.
Re: [R-SIG-Finance] CUSIP Numbers
Since this is an R mailing list, I'll try to bring this thread back on
topic. Unless you are willing to pay, the only free source that I am
aware of to get CUSIPs via R is TradeKing.
https://developers.tradeking.com/documentation/market-ext-quotes-get-post
You must have an account, but you can create an account for free and
you don't have to fund it in order to do this.
library(ROAuth) #importFrom(ROAuth, OAuthFactory)
library(RJSONIO) #importFrom(RJSONIO, fromJSON)
#' ## This part could go in your .Rprofile
#' # Set your application keys # https://developers.tradeking.com/applications
#' cKey <- ''
#' cSecret <- '#'
#' oKey <- ''
#' oSecret <- ''
# Set the API endpoint
tkURL <- "https://api.tradeking.com/v1/market/ext/quotes.json";
# Create the OAuth connection - this is straight from the ROAuth
documentation on CRAN
credentials <- OAuthFactory$new(consumerKey=cKey,
consumerSecret=cSecret,
oauthKey = oKey,
oauthSecret = oSecret,
needsVerifier=FALSE,
signMethod='HMAC')
# Update the connection so the handshake is TRUE
credentials$handshakeComplete <- TRUE
Symbols <- tolower(c("AAPL", "MSFT")) ## Whatever symbols you want
symbols <- paste(Symbols, collapse=",")
#what <- "datetime,bidsz,bid,ask,asksz,last,chg,pchg,opn,hi,lo,vl"
what <- "cusip"
what <- gsub(" ", "", tolower(paste(unlist(strsplit(what, ",")),
collapse=",")))
tkURL <- "https://api.tradeking.com/v1/market/ext/quotes.json";
query <- list(symbols=symbols, fids=what)
response <- credentials$OAuthRequest(tkURL, query)
res <- fromJSON(response)
qt <- res$response$quotes$quote
qt
#[[1]]
# cusip exch symbol
#"59491810" "NASD" "MSFT"
#
#[[2]]
# cusip exch symbol
#"03783310" "NASD" "AAPL"
HTH,
Garrett
___
R-SIG-Finance@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should
go.
Re: [R-SIG-Finance] CUSIP Numbers
2015-01-21 16:45 GMT+01:00 Anshul Pandey : > Hi All, > > I am moving some of my backtesting logics to CUSIP from tickers. > How do I download the CUSIP number of US stocks? > > I know S&P has a paid subscription, but I read that CUSIP is publicly > available at a few resources. > > Any suggestions are highly welcome. You may be interested in Bloomberg Open Symbology, as an alternative to CUSIP. http://bsym.bloomberg.com/sym/ Best regards, Daniel > > Thanks > Anshul > ___ R-SIG-Finance@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-finance -- Subscriber-posting only. If you want to post, subscribe first. -- Also note that this is not the r-help list where general R questions should go.
Re: [R-SIG-Finance] CUSIP Numbers
Fidelity customers can find CUSIPs (one at a time): http://activequote.fidelity.com/mmnet/SymLookup.phtml On 01/21/2015 1:03 PM, James Ho wrote: Hi Anshul, CUSIP's are owned by S&P so they aren't really public. Anyhow, you wont want to use those to backtest as they are driven by the underlying company's name (imagine what happens to a CUSIP when there is any M&A activity). MSCI Barra & S&P's Compustat's Point-In-Time ID's are built for this type of backtesting. If you have access to BBID's that would be a decent alternative but looking for an open source identifier system is going to be tough. Good luck sir. ~James On Wed, Jan 21, 2015 at 7:45 AM, Anshul Pandey wrote: Hi All, I am moving some of my backtesting logics to CUSIP from tickers. How do I download the CUSIP number of US stocks? I know S&P has a paid subscription, but I read that CUSIP is publicly available at a few resources. Any suggestions are highly welcome. Thanks Anshul [[alternative HTML version deleted]] ___ R-SIG-Finance@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-finance -- Subscriber-posting only. If you want to post, subscribe first. -- Also note that this is not the r-help list where general R questions should go. [[alternative HTML version deleted]] ___ R-SIG-Finance@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-finance -- Subscriber-posting only. If you want to post, subscribe first. -- Also note that this is not the r-help list where general R questions should go. ___ R-SIG-Finance@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-finance -- Subscriber-posting only. If you want to post, subscribe first. -- Also note that this is not the r-help list where general R questions should go.
Re: [R-SIG-Finance] CUSIP Numbers
Hi Anshul, CUSIP's are owned by S&P so they aren't really public. Anyhow, you wont want to use those to backtest as they are driven by the underlying company's name (imagine what happens to a CUSIP when there is any M&A activity). MSCI Barra & S&P's Compustat's Point-In-Time ID's are built for this type of backtesting. If you have access to BBID's that would be a decent alternative but looking for an open source identifier system is going to be tough. Good luck sir. ~James On Wed, Jan 21, 2015 at 7:45 AM, Anshul Pandey wrote: > Hi All, > > I am moving some of my backtesting logics to CUSIP from tickers. > How do I download the CUSIP number of US stocks? > > I know S&P has a paid subscription, but I read that CUSIP is publicly > available at a few resources. > > Any suggestions are highly welcome. > > Thanks > Anshul > > [[alternative HTML version deleted]] > > ___ > R-SIG-Finance@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-sig-finance > -- Subscriber-posting only. If you want to post, subscribe first. > -- Also note that this is not the r-help list where general R questions > should go. > [[alternative HTML version deleted]] ___ R-SIG-Finance@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-finance -- Subscriber-posting only. If you want to post, subscribe first. -- Also note that this is not the r-help list where general R questions should go.
Re: [R-SIG-Finance] IBrokers Package: wrong Clientid returns ?
Well, for sure a downgrade of the TWS would fix it, but it's obviously not
a long term solution. Are you using a beta TWS version or a stable release ?
On Wed, Jan 21, 2015 at 4:07 AM, ce wrote:
>
> I downgraded IBrokers version to 0.9-10, while keeping TWS Build 948.3c,
> Jan 5, 2015 5:12:23 PM ,
> still I got the wrong clientid from TWS.
>
> Then I downgraded TWS to Build 945.2b, Jun 3, 2014 11:11:57 AM and it
> worked correctly with IBrokers 0.9-10
>
> I see my clientid 96 is returned from TWS :
>
> TWS OpenOrder: orderId=2 clientId=96 conId=14321015 symbol=GBP
> status=Filled
>
>
> -Original Message-
> From: "ce" [zadi...@excite.com]
> Date: 01/20/2015 07:52 PM
> To: cens...@gmail.com
> CC: r-sig-finance@r-project.org
> Subject: Re: [R-SIG-Finance] IBrokers Package: wrong Clientid returns ?
>
>
> Hi Cen six,
>
> I am using IBrokers 0.9.12 from cran r web site.
> In fact I was testing the demo program from you emailed me. It was working
> fine but one or two weeks ago event handler started to fail ( maybe after
> IBrokers update ) as I explained in :
> https://groups.yahoo.com/neo/groups/TWSAPI/conversations/messages/33071
>
> then I upgraded TWS but now clientid returned by event handler is wrong.
> Maybe I should downgrade IBrokers or TWS ?
>
> ce
>
>
> -Original Message-
> From: "cen six" [cens...@gmail.com]
> Date: 01/20/2015 03:04 PM
> To: "ce"
> CC: "r-sig-finance@r-project.org"
> Subject: Re: [R-SIG-Finance] IBrokers Package: wrong Clientid returns ?
>
> Are you using the IBrokers package version 0.9-10 or higher ? (from
> code.google.com)
>
>
> cheers
>
>
> On Tue, Jan 20, 2015 at 2:38 AM, ce wrote:
>
> Dear all,
>
> I just upgraded TWS to Build 948.3c, Jan 5, 2015 5:12:23 PM
> My program that worked fine before started to return wrong clientid . I
> set client ID to 96. but after sending the order, In order status , or
> order execution events I get clientid 6 !! Even I tried to set Master API
> Client ID to 96 in TWS -> Configuration -> API. didnt work.
> If I set Clientid to 6, TWS returns 0 as Clientid.
>
> Here is some piece of code :
>
> > ibClientId <- 96
> >
> >
> > #global: create the connection to IB (this can probably not be stored
> anywhere, so
> > #we have to recreate it within "IBexecuteStrategy.r"
> > ibConnection<-NULL
> > if (!is.twsConnection(ibConnection)) {
> +ibConnection<- twsConnect(clientId=ibClientId, host="localhost",
> + port=7496, verbose=TRUE,
> + timeout=15, filename=NULL)
> + }
> > print(ibConnection)
>
>
> TWS OpenOrder: orderId=3 clientId=6 conId=12087807 symbol=EUR
> status=Submitted
>
> ___
> R-SIG-Finance@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> -- Subscriber-posting only. If you want to post, subscribe first.
> -- Also note that this is not the r-help list where general R questions
> should go.
>
> ___
> R-SIG-Finance@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> -- Subscriber-posting only. If you want to post, subscribe first.
> -- Also note that this is not the r-help list where general R questions
> should g
>
[[alternative HTML version deleted]]
___
R-SIG-Finance@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should
go.
Re: [R-SIG-Finance] Portfolio Optimisation as a function of targeted Risk rather than return.
Thank you Ilya, much appreciated From: Ilya Kipnis [mailto:ilya.kip...@gmail.com] Sent: 21 January 2015 15:50 To: Pierre Org Cc: r-sig-finance@r-project.org Subject: Re: [R-SIG-Finance] Portfolio Optimisation as a function of targeted Risk rather than return. Check out the PortfolioAnalytics package. On Wed, Jan 21, 2015 at 6:13 AM, Pierre Org wrote: I am currently working on a portfolio optimisation strategy that would involves optimising a portfolio so that it maximises the returns for a user defined level of risk. E.g. keeping the volatility of the portfolio at 10% annualised whilst maximising the return for this level. For that purpose I was hoping to use the function maxreturnPortfolio in fPortfolio that should return the portfolio with the maximal return for a fixed target risk. Clearly though showing in this great package the function has been/is in development by the authors of the package and currently does not work as intended. This is confirmed by various posts and answer to those by the authors. I wonder if anyone knows of another more up to date package or way of doing this in R ? Any help would be really appreciated. [[alternative HTML version deleted]] ___ R-SIG-Finance@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-finance -- Subscriber-posting only. If you want to post, subscribe first. -- Also note that this is not the r-help list where general R questions should go. [[alternative HTML version deleted]] ___ R-SIG-Finance@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-finance -- Subscriber-posting only. If you want to post, subscribe first. -- Also note that this is not the r-help list where general R questions should go.
Re: [R-SIG-Finance] Portfolio Optimisation as a function of targeted Risk rather than return.
Check out the PortfolioAnalytics package. On Wed, Jan 21, 2015 at 6:13 AM, Pierre Org wrote: > I am currently working on a portfolio optimisation strategy that would > involves optimising a portfolio so that it maximises the returns for a > user > defined level of risk. E.g. keeping the volatility of the portfolio at > 10% > annualised whilst maximising the return for this level. For that purpose I > was hoping to use the function maxreturnPortfolio in fPortfolio that > should > return the portfolio with the maximal return for a fixed target risk. > Clearly though showing in this great package the function has been/is in > development by the authors of the package and currently does not work as > intended. This is confirmed by various posts and answer to those by the > authors. I wonder if anyone knows of another more up to date package or > way of doing this in R ? > > > > Any help would be really appreciated. > > > > > > > > > [[alternative HTML version deleted]] > > ___ > R-SIG-Finance@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-sig-finance > -- Subscriber-posting only. If you want to post, subscribe first. > -- Also note that this is not the r-help list where general R questions > should go. > [[alternative HTML version deleted]] ___ R-SIG-Finance@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-finance -- Subscriber-posting only. If you want to post, subscribe first. -- Also note that this is not the r-help list where general R questions should go.
[R-SIG-Finance] CUSIP Numbers
Hi All, I am moving some of my backtesting logics to CUSIP from tickers. How do I download the CUSIP number of US stocks? I know S&P has a paid subscription, but I read that CUSIP is publicly available at a few resources. Any suggestions are highly welcome. Thanks Anshul [[alternative HTML version deleted]] ___ R-SIG-Finance@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-finance -- Subscriber-posting only. If you want to post, subscribe first. -- Also note that this is not the r-help list where general R questions should go.
Re: [R-SIG-Finance] Passing optim.control arima arguments to ugarchfit in rugarch
Ah, a misunderstanding on my part. Of course it makes perfect sense that
they are jointly estimated.
Thanks for the suggestions and the swift response.
Best regards,
Andreas
--
Andreas Keller
M.Sc. student in Economics and Management
On Wed, Jan 21, 2015 at 12:19 PM, alexios wrote:
> Hi,
>
> arima is only used to obtain mean equation starting values for the joint
> recursion which is then ML based. Your best bet is to try using
> solver="gosolnp" which searches the parameter space for good starting
> values.
> Also, try setting variance.targeting=TRUE (in variance.model), and
> fit.control=list(scale=1).
>
> Ofcourse, this is all dependent on using a reasonable amount of data for
> the estimation (already discussed numerous times over the years).
>
> Regards,
>
> Alexios
>
>
> On 21/01/2015 10:38, Andreas Keller Leth Laursen wrote:
>
>> Dear all
>>
>> I am currently estimating a number of GARCH models using the excellent
>> rugarch package.
>>
>> I am however having a small problem, as the mean equation has convergence
>> problems. It is a simple ARMA(6,5) model, that is being used as mean
>> equation.
>>
>> When estimating the mean equation, I understand that ugarchfit() use the
>> standard arima() function. Is there a way to pass optim.control arguments
>> to the arima solver? A simple increase in the default maxit should solve
>> the problem, but I cannot figure out if there is a way to pass this
>> argument.
>>
>> As a small hack I have tried to simply give the arma(6,5) estimates as
>> stating values to ugarchspec() using arima() with a higher maxit.
>> However, ugarchfit() still reports convergence problems in the mean
>> equation, when I attempt this.
>>
>> Any help will be much appreciated.
>>
>> Current code:
>>
>> arima_start_val <- arima(input_series, order = c(6, 0, 5), optim.control =
>> list(maxit = 2000)) %>%
>> coef %>%
>> as.list
>>
>> names(arima_start_val) <- c("ar1", "ar2", "ar3", "ar4", "ar5", "ar6",
>> "ma1", "ma2", "ma3", "ma4", "ma5", "mu")
>>
>> model <- ugarchspec(
>> variance.model = list(model = "sGARCH", garchOrder = c(1, 1)),
>> mean.model = list(armaOrder = c(6, 5)),
>> start.pars = arima_start_val,
>> distribution = "norm")
>>
>> ugarchfit(spec = model, data = input_series)
>>
>> Best regards,
>> Andreas Keller
>>
>> --
>> Andreas Keller
>>
>> [[alternative HTML version deleted]]
>>
>> ___
>> R-SIG-Finance@r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
>> -- Subscriber-posting only. If you want to post, subscribe first.
>> -- Also note that this is not the r-help list where general R questions
>> should go.
>>
>>
>>
>
[[alternative HTML version deleted]]
___
R-SIG-Finance@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should
go.
Re: [R-SIG-Finance] Passing optim.control arima arguments to ugarchfit in rugarch
Hi,
arima is only used to obtain mean equation starting values for the joint
recursion which is then ML based. Your best bet is to try using
solver="gosolnp" which searches the parameter space for good starting
values.
Also, try setting variance.targeting=TRUE (in variance.model), and
fit.control=list(scale=1).
Ofcourse, this is all dependent on using a reasonable amount of data for
the estimation (already discussed numerous times over the years).
Regards,
Alexios
On 21/01/2015 10:38, Andreas Keller Leth Laursen wrote:
Dear all
I am currently estimating a number of GARCH models using the excellent
rugarch package.
I am however having a small problem, as the mean equation has convergence
problems. It is a simple ARMA(6,5) model, that is being used as mean
equation.
When estimating the mean equation, I understand that ugarchfit() use the
standard arima() function. Is there a way to pass optim.control arguments
to the arima solver? A simple increase in the default maxit should solve
the problem, but I cannot figure out if there is a way to pass this
argument.
As a small hack I have tried to simply give the arma(6,5) estimates as
stating values to ugarchspec() using arima() with a higher maxit.
However, ugarchfit() still reports convergence problems in the mean
equation, when I attempt this.
Any help will be much appreciated.
Current code:
arima_start_val <- arima(input_series, order = c(6, 0, 5), optim.control =
list(maxit = 2000)) %>%
coef %>%
as.list
names(arima_start_val) <- c("ar1", "ar2", "ar3", "ar4", "ar5", "ar6",
"ma1", "ma2", "ma3", "ma4", "ma5", "mu")
model <- ugarchspec(
variance.model = list(model = "sGARCH", garchOrder = c(1, 1)),
mean.model = list(armaOrder = c(6, 5)),
start.pars = arima_start_val,
distribution = "norm")
ugarchfit(spec = model, data = input_series)
Best regards,
Andreas Keller
--
Andreas Keller
[[alternative HTML version deleted]]
___
R-SIG-Finance@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should
go.
___
R-SIG-Finance@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should
go.
[R-SIG-Finance] Portfolio Optimisation as a function of targeted Risk rather than return.
I am currently working on a portfolio optimisation strategy that would involves optimising a portfolio so that it maximises the returns for a user defined level of risk. E.g. keeping the volatility of the portfolio at 10% annualised whilst maximising the return for this level. For that purpose I was hoping to use the function maxreturnPortfolio in fPortfolio that should return the portfolio with the maximal return for a fixed target risk. Clearly though showing in this great package the function has been/is in development by the authors of the package and currently does not work as intended. This is confirmed by various posts and answer to those by the authors. I wonder if anyone knows of another more up to date package or way of doing this in R ? Any help would be really appreciated. [[alternative HTML version deleted]] ___ R-SIG-Finance@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-finance -- Subscriber-posting only. If you want to post, subscribe first. -- Also note that this is not the r-help list where general R questions should go.
[R-SIG-Finance] Passing optim.control arima arguments to ugarchfit in rugarch
Dear all
I am currently estimating a number of GARCH models using the excellent
rugarch package.
I am however having a small problem, as the mean equation has convergence
problems. It is a simple ARMA(6,5) model, that is being used as mean
equation.
When estimating the mean equation, I understand that ugarchfit() use the
standard arima() function. Is there a way to pass optim.control arguments
to the arima solver? A simple increase in the default maxit should solve
the problem, but I cannot figure out if there is a way to pass this
argument.
As a small hack I have tried to simply give the arma(6,5) estimates as
stating values to ugarchspec() using arima() with a higher maxit.
However, ugarchfit() still reports convergence problems in the mean
equation, when I attempt this.
Any help will be much appreciated.
Current code:
arima_start_val <- arima(input_series, order = c(6, 0, 5), optim.control =
list(maxit = 2000)) %>%
coef %>%
as.list
names(arima_start_val) <- c("ar1", "ar2", "ar3", "ar4", "ar5", "ar6",
"ma1", "ma2", "ma3", "ma4", "ma5", "mu")
model <- ugarchspec(
variance.model = list(model = "sGARCH", garchOrder = c(1, 1)),
mean.model = list(armaOrder = c(6, 5)),
start.pars = arima_start_val,
distribution = "norm")
ugarchfit(spec = model, data = input_series)
Best regards,
Andreas Keller
--
Andreas Keller
[[alternative HTML version deleted]]
___
R-SIG-Finance@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should
go.
[R-SIG-Finance] Help with quantstrat
Hi all,
I am beginner with quantstrat. I would like to try a simple strategy but
I have some
difficulties to program it. The strategy is based on two signals : the
CCI and the RSI.
First, I compute RSI and CCI for period n=21. Let's denote them rsi21
and cci21.
Secondly, I compute two moving average for rsi21 and cci21 with two
periodes : 8 and 14. I obtain four signals. Let's denote i3 and i4 for
rsi21, and i5 and i6 for cci21.
Finally, I enter for a long position if (i3>i4)&(i5>i6)
I enter for a short position if (i3i4)&(i5>i6)
dn=(i3add.indicator(strategy =mystrategy, name = "SMA",arguments = list(x =
quote(RSI(Cl(mktdata),n=8)), n=20), label="i3")
add.indicator(strategy =mystrategy, name = "SMA",arguments = list(x =
quote(RSI(Cl(mktdata),n=14)), n=20), label="i4")
add.indicator(strategy =mystrategy, name = "SMA",arguments = list(x =
quote(CCI(Cl(mktdata),n=8)), n=20), label="i5")
add.indicator(strategy =mystrategy, name = "SMA",arguments = list(x =
quote(CCI(Cl(mktdata),n=14)), n=20), label="i6")
#signals
add.signal(mystrategy,name="sigCrossover",arguments =
list(columns=c("i3","i4"),relationship="gt"), label="i3.gt.i4")
add.signal(mystrategy,name="sigCrossover", arguments =
list(columns=c("i5","i6"),relationship="gt"), label="i5.gt.i6")
add.signal(mystrategy,name="sigCrossover", arguments =
list(columns=c("i3","i4"),relationship="lt"), label="i3.lt.i4")
add.signal(mystrategy,name="sigCrossover", arguments =
list(columns=c("i5","i6"),relationship="lt"), label="i5.lt.i6")
#rules
???
Could someone help me ?
Best regards,
Olivier.
___
R-SIG-Finance@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should
go.
