Need help please

classic Classic list List threaded Threaded
5 messages Options
Reply | Threaded
Open this post in threaded view
|

Need help please

Bogaso
Dear folks,

I got a very notorious weekly price series where price seldom changes like :

6-Jan-92 4.38
13-Jan-92 4.38
20-Jan-92 4.38
27-Jan-92 4.38
3-Feb-92 4.38
10-Feb-92 4.38
17-Feb-92 4.38
24-Feb-92 4.38
2-Mar-92 4.38
9-Mar-92 4.38
16-Mar-92 4.38
23-Mar-92 4.38
30-Mar-92 4.38
6-Apr-92 4.38
13-Apr-92 4.38
20-Apr-92 6.56
27-Apr-92 6.56
4-May-92 6.56
11-May-92 6.56
18-May-92 6.56
25-May-92 6.56
1-Jun-92 6.56
8-Jun-92 6.63
15-Jun-92 6.63
22-Jun-92 6.63
29-Jun-92 6.63
6-Jul-92 6.63
13-Jul-92 6.63
20-Jul-92 6.99
27-Jul-92 6.99
3-Aug-92 6.99
10-Aug-92 6.99
17-Aug-92 6.99
24-Aug-92 6.99
31-Aug-92 6.99
7-Sep-92 6.99
14-Sep-92 6.99
21-Sep-92 6.99
28-Sep-92 6.99
5-Oct-92 6.99
12-Oct-92 6.99
19-Oct-92 6.99
26-Oct-92 6.99
2-Nov-92 6.99
9-Nov-92 6.99
16-Nov-92 6.99
23-Nov-92 6.99
30-Nov-92 6.99
7-Dec-92 6.99
14-Dec-92 6.99
21-Dec-92 6.99
28-Dec-92 6.99
4-Jan-93 6.99
11-Jan-93 6.99
18-Jan-93 6.99
25-Jan-93 6.99
1-Feb-93 6.99
8-Feb-93 6.99
15-Feb-93 6.99
22-Feb-93 6.99
1-Mar-93 6.99
8-Mar-93 6.99
15-Mar-93 6.99
22-Mar-93 6.56
29-Mar-93 6.56
5-Apr-93 6.56
12-Apr-93 6.56
19-Apr-93 6.56
26-Apr-93 6.56
3-May-93 6.56
10-May-93 6.63
17-May-93 6.63
24-May-93 6.63
31-May-93 6.63
7-Jun-93 6.63
14-Jun-93 6.63
21-Jun-93 6.99
28-Jun-93 6.99
5-Jul-93 6.99
12-Jul-93 6.99
19-Jul-93 6.99
26-Jul-93 6.99
2-Aug-93 6.99
9-Aug-93 6.99
16-Aug-93 6.99
23-Aug-93 6.99

I have a mandate to calculate VaR on that price data, probably in Parametric way. My question is can I apply standard way which we generally use like log-normally distributed price, to calculate VaR here? Or some other modeling approach needs to be taken care? Can anyone please provide me any references over net, how to handle this type of scenario?

Your help will be highly appreciated.

Thanks,
Reply | Threaded
Open this post in threaded view
|

Re: [R-SIG-Finance] Need help please

Zhang, Ivan
Hi Bogaso,

This may not necessarily help you get an answer, but perhaps would steer
you in another direction:

If the series doesn't look continuous you may potentially be able to
pick a quantile that would make this measure not "coherent" which
basically invalidates the use of VaR as a measure of risk in this case.

For more information on Coherent risk measures, see below link or Google
"coherent risk measure"

http://www.math.ethz.ch/~delbaen/ftp/preprints/CoherentMF.pdf


Hope this helps,


-Ivan Zhang

-----Original Message-----
From: [hidden email]
[mailto:[hidden email]] On Behalf Of Bogaso
Sent: Tuesday, January 26, 2010 3:25 AM
To: [hidden email]
Subject: [R-SIG-Finance] Need help please


Dear folks,

I got a very notorious weekly price series where price seldom changes
like :

6-Jan-92 4.38
13-Jan-92 4.38
20-Jan-92 4.38
27-Jan-92 4.38
3-Feb-92 4.38
10-Feb-92 4.38
17-Feb-92 4.38
24-Feb-92 4.38
2-Mar-92 4.38
9-Mar-92 4.38
16-Mar-92 4.38
23-Mar-92 4.38
30-Mar-92 4.38
6-Apr-92 4.38
13-Apr-92 4.38
20-Apr-92 6.56
27-Apr-92 6.56
4-May-92 6.56
11-May-92 6.56
18-May-92 6.56
25-May-92 6.56
1-Jun-92 6.56
8-Jun-92 6.63
15-Jun-92 6.63
22-Jun-92 6.63
29-Jun-92 6.63
6-Jul-92 6.63
13-Jul-92 6.63
20-Jul-92 6.99
27-Jul-92 6.99
3-Aug-92 6.99
10-Aug-92 6.99
17-Aug-92 6.99
24-Aug-92 6.99
31-Aug-92 6.99
7-Sep-92 6.99
14-Sep-92 6.99
21-Sep-92 6.99
28-Sep-92 6.99
5-Oct-92 6.99
12-Oct-92 6.99
19-Oct-92 6.99
26-Oct-92 6.99
2-Nov-92 6.99
9-Nov-92 6.99
16-Nov-92 6.99
23-Nov-92 6.99
30-Nov-92 6.99
7-Dec-92 6.99
14-Dec-92 6.99
21-Dec-92 6.99
28-Dec-92 6.99
4-Jan-93 6.99
11-Jan-93 6.99
18-Jan-93 6.99
25-Jan-93 6.99
1-Feb-93 6.99
8-Feb-93 6.99
15-Feb-93 6.99
22-Feb-93 6.99
1-Mar-93 6.99
8-Mar-93 6.99
15-Mar-93 6.99
22-Mar-93 6.56
29-Mar-93 6.56
5-Apr-93 6.56
12-Apr-93 6.56
19-Apr-93 6.56
26-Apr-93 6.56
3-May-93 6.56
10-May-93 6.63
17-May-93 6.63
24-May-93 6.63
31-May-93 6.63
7-Jun-93 6.63
14-Jun-93 6.63
21-Jun-93 6.99
28-Jun-93 6.99
5-Jul-93 6.99
12-Jul-93 6.99
19-Jul-93 6.99
26-Jul-93 6.99
2-Aug-93 6.99
9-Aug-93 6.99
16-Aug-93 6.99
23-Aug-93 6.99

I have a mandate to calculate VaR on that price data, probably in
Parametric
way. My question is can I apply standard way which we generally use like
log-normally distributed price, to calculate VaR here? Or some other
modeling approach needs to be taken care? Can anyone please provide me
any
references over net, how to handle this type of scenario?

Your help will be highly appreciated.

Thanks,
--
View this message in context:
http://n4.nabble.com/Need-help-please-tp1290132p1290132.html
Sent from the Rmetrics mailing list archive at Nabble.com.

_______________________________________________
[hidden email] 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.

_______________________________________________
[hidden email] 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.
Reply | Threaded
Open this post in threaded view
|

Re: [R-SIG-Finance] Need help please

julien cuisinier
Hi Bogaso,


I am not a VaR expert at all, but I would say this:
1. Not enough data to compute anything with any sensible level of  
statistical significance (probably already very weak for volatility,  
but most probably very very very weak for VaR estimation)
2. I do not know this "very notorious" time series personally  
(probably my own limitation), but it looks pretty odd to me, basically  
you have 7 different prices repeated many times giving you 6 returns -  
one of which is almost 50% - and many nil returns...
3. VaR using the simple log-normal model of asset prices (I guess you  
mean VaR(99%)=average - 2.33*stdev) is vastly documented to be  
insufficient for financial assets like equity, so most probably not  
for whatever this thing is.

So I would personally simply say that it is not possible with the data  
at hand. Better to accept you cannot than use inappropriate "models"  
just to get some number out. But that's a personal opinion. Or there  
is another complex way (probably with a set of strong assumptions on  
the variable) which is beyond my knowledge

& as Ivan pointed out, this does not even enter the debate whether VaR  
is a sensible risk measure (coherence, best outcome in a bad day,  
etc...). I may be wrong of course, but I would be interested to have  
other list member opinion on this.


Sorry, this is most probably not the hoped/expected feedback.


Rgds,
Julen






On Jan 27, 2010, at 5:44 PM, Zhang, Ivan wrote:

> Hi Bogaso,
>
> This may not necessarily help you get an answer, but perhaps would  
> steer
> you in another direction:
>
> If the series doesn't look continuous you may potentially be able to
> pick a quantile that would make this measure not "coherent" which
> basically invalidates the use of VaR as a measure of risk in this  
> case.
>
> For more information on Coherent risk measures, see below link or  
> Google
> "coherent risk measure"
>
> http://www.math.ethz.ch/~delbaen/ftp/preprints/CoherentMF.pdf
>
>
> Hope this helps,
>
>
> -Ivan Zhang
>
> -----Original Message-----
> From: [hidden email]
> [mailto:[hidden email]] On Behalf Of Bogaso
> Sent: Tuesday, January 26, 2010 3:25 AM
> To: [hidden email]
> Subject: [R-SIG-Finance] Need help please
>
>
> Dear folks,
>
> I got a very notorious weekly price series where price seldom changes
> like :
>
> 6-Jan-92 4.38
> 13-Jan-92 4.38
> 20-Jan-92 4.38
> 27-Jan-92 4.38
> 3-Feb-92 4.38
> 10-Feb-92 4.38
> 17-Feb-92 4.38
> 24-Feb-92 4.38
> 2-Mar-92 4.38
> 9-Mar-92 4.38
> 16-Mar-92 4.38
> 23-Mar-92 4.38
> 30-Mar-92 4.38
> 6-Apr-92 4.38
> 13-Apr-92 4.38
> 20-Apr-92 6.56
> 27-Apr-92 6.56
> 4-May-92 6.56
> 11-May-92 6.56
> 18-May-92 6.56
> 25-May-92 6.56
> 1-Jun-92 6.56
> 8-Jun-92 6.63
> 15-Jun-92 6.63
> 22-Jun-92 6.63
> 29-Jun-92 6.63
> 6-Jul-92 6.63
> 13-Jul-92 6.63
> 20-Jul-92 6.99
> 27-Jul-92 6.99
> 3-Aug-92 6.99
> 10-Aug-92 6.99
> 17-Aug-92 6.99
> 24-Aug-92 6.99
> 31-Aug-92 6.99
> 7-Sep-92 6.99
> 14-Sep-92 6.99
> 21-Sep-92 6.99
> 28-Sep-92 6.99
> 5-Oct-92 6.99
> 12-Oct-92 6.99
> 19-Oct-92 6.99
> 26-Oct-92 6.99
> 2-Nov-92 6.99
> 9-Nov-92 6.99
> 16-Nov-92 6.99
> 23-Nov-92 6.99
> 30-Nov-92 6.99
> 7-Dec-92 6.99
> 14-Dec-92 6.99
> 21-Dec-92 6.99
> 28-Dec-92 6.99
> 4-Jan-93 6.99
> 11-Jan-93 6.99
> 18-Jan-93 6.99
> 25-Jan-93 6.99
> 1-Feb-93 6.99
> 8-Feb-93 6.99
> 15-Feb-93 6.99
> 22-Feb-93 6.99
> 1-Mar-93 6.99
> 8-Mar-93 6.99
> 15-Mar-93 6.99
> 22-Mar-93 6.56
> 29-Mar-93 6.56
> 5-Apr-93 6.56
> 12-Apr-93 6.56
> 19-Apr-93 6.56
> 26-Apr-93 6.56
> 3-May-93 6.56
> 10-May-93 6.63
> 17-May-93 6.63
> 24-May-93 6.63
> 31-May-93 6.63
> 7-Jun-93 6.63
> 14-Jun-93 6.63
> 21-Jun-93 6.99
> 28-Jun-93 6.99
> 5-Jul-93 6.99
> 12-Jul-93 6.99
> 19-Jul-93 6.99
> 26-Jul-93 6.99
> 2-Aug-93 6.99
> 9-Aug-93 6.99
> 16-Aug-93 6.99
> 23-Aug-93 6.99
>
> I have a mandate to calculate VaR on that price data, probably in
> Parametric
> way. My question is can I apply standard way which we generally use  
> like
> log-normally distributed price, to calculate VaR here? Or some other
> modeling approach needs to be taken care? Can anyone please provide me
> any
> references over net, how to handle this type of scenario?
>
> Your help will be highly appreciated.
>
> Thanks,
> --
> View this message in context:
> http://n4.nabble.com/Need-help-please-tp1290132p1290132.html
> Sent from the Rmetrics mailing list archive at Nabble.com.
>
> _______________________________________________
> [hidden email] 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.
>
> _______________________________________________
> [hidden email] 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.
>

_______________________________________________
[hidden email] 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.
Reply | Threaded
Open this post in threaded view
|

Re: [R-SIG-Finance] Need help please

Tony Plate
In reply to this post by Bogaso
Are these are actual market prices each week?  Or are they for an instrument
that only trades every few months, and someone has just filled in the data
with the most recent trade price?  If it is that, then there are only a few
actual data points.  If these are real prices from each week, then it might
be worth trying to understand the price formation process -- these numbers
don't look like most price series from auction markets.  The actual prices
are a little strange too, all of them look like they could be prices in 1/16
ticks, rounded to two digits, except for the 6.99.

-- Tony Plate

On Tue, Jan 26, 2010 at 1:25 AM, Bogaso <[hidden email]> wrote:

>
> Dear folks,
>
> I got a very notorious weekly price series where price seldom changes like
> :
>
> 6-Jan-92        4.38
> 13-Jan-92       4.38
> 20-Jan-92       4.38
> 27-Jan-92       4.38
> 3-Feb-92        4.38
> 10-Feb-92       4.38
> 17-Feb-92       4.38
> 24-Feb-92       4.38
> 2-Mar-92        4.38
> 9-Mar-92        4.38
> 16-Mar-92       4.38
> 23-Mar-92       4.38
> 30-Mar-92       4.38
> 6-Apr-92        4.38
> 13-Apr-92       4.38
> 20-Apr-92       6.56
> 27-Apr-92       6.56
> 4-May-92        6.56
> 11-May-92       6.56
> 18-May-92       6.56
> 25-May-92       6.56
> 1-Jun-92        6.56
> 8-Jun-92        6.63
> 15-Jun-92       6.63
> 22-Jun-92       6.63
> 29-Jun-92       6.63
> 6-Jul-92        6.63
> 13-Jul-92       6.63
> 20-Jul-92       6.99
> 27-Jul-92       6.99
> 3-Aug-92        6.99
> 10-Aug-92       6.99
> 17-Aug-92       6.99
> 24-Aug-92       6.99
> 31-Aug-92       6.99
> 7-Sep-92        6.99
> 14-Sep-92       6.99
> 21-Sep-92       6.99
> 28-Sep-92       6.99
> 5-Oct-92        6.99
> 12-Oct-92       6.99
> 19-Oct-92       6.99
> 26-Oct-92       6.99
> 2-Nov-92        6.99
> 9-Nov-92        6.99
> 16-Nov-92       6.99
> 23-Nov-92       6.99
> 30-Nov-92       6.99
> 7-Dec-92        6.99
> 14-Dec-92       6.99
> 21-Dec-92       6.99
> 28-Dec-92       6.99
> 4-Jan-93        6.99
> 11-Jan-93       6.99
> 18-Jan-93       6.99
> 25-Jan-93       6.99
> 1-Feb-93        6.99
> 8-Feb-93        6.99
> 15-Feb-93       6.99
> 22-Feb-93       6.99
> 1-Mar-93        6.99
> 8-Mar-93        6.99
> 15-Mar-93       6.99
> 22-Mar-93       6.56
> 29-Mar-93       6.56
> 5-Apr-93        6.56
> 12-Apr-93       6.56
> 19-Apr-93       6.56
> 26-Apr-93       6.56
> 3-May-93        6.56
> 10-May-93       6.63
> 17-May-93       6.63
> 24-May-93       6.63
> 31-May-93       6.63
> 7-Jun-93        6.63
> 14-Jun-93       6.63
> 21-Jun-93       6.99
> 28-Jun-93       6.99
> 5-Jul-93        6.99
> 12-Jul-93       6.99
> 19-Jul-93       6.99
> 26-Jul-93       6.99
> 2-Aug-93        6.99
> 9-Aug-93        6.99
> 16-Aug-93       6.99
> 23-Aug-93       6.99
>
> I have a mandate to calculate VaR on that price data, probably in
> Parametric
> way. My question is can I apply standard way which we generally use like
> log-normally distributed price, to calculate VaR here? Or some other
> modeling approach needs to be taken care? Can anyone please provide me any
> references over net, how to handle this type of scenario?
>
> Your help will be highly appreciated.
>
> Thanks,
> --
> View this message in context:
> http://n4.nabble.com/Need-help-please-tp1290132p1290132.html
> Sent from the Rmetrics mailing list archive at Nabble.com.
>
> _______________________________________________
> [hidden email] 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]]

_______________________________________________
[hidden email] 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.
Reply | Threaded
Open this post in threaded view
|

Re: Need help please

Arun.stat
In reply to this post by Bogaso
hmmm..........interesting no doubt............what about this sort of modeling?

1. 1st define a r.v. to represent the number of days/weeks price is being kept fixed, you could try some exponential dist.
2. 2nd define another r.v. to represent the magnitude of change in prices.

Then you need to combine those two r.v., perhaps you could use "convolution" concept (i am not sure exactly) and then simulate different price scenario and choose the worst 5th. By this way can calculate VaR under MCS framework, not really parametric as you wished.

However I would really be happy if someone throws points on following "

1. How to incorporate correlation (if any, if not you need to quantify still to justify that) between above those 2 r.v.s
2. How to calculate VaR from a portfolio perspective.

I would really be happy if someone would point out the feasibility of above approach.

Thanks,