[R] Cross-Correlation function (CCF) issues

David Winsemius dwinsemius at comcast.net
Wed Apr 22 00:18:28 CEST 2009


When I get such unexpected behavior, I generally reinstall software. I  
am currently using the Urbanek prepared MacOSX  2.8.1 binary under  
Leopard with the 64 bit GUI. The stats package is part of the core  
distribution, so reinstalling the stats package would mean  
reinstalling R. Other options would include using trace or other  
debugging facilities.

-- 
David.

On Apr 21, 2009, at 5:45 PM, manta wrote:

>
> The problem is that I was doing that for the tiny sample objects.
> So I really have no clue about
>
> David Winsemius wrote:
>>
>>
>> If you were doing that with the full sized do1 and dr1, then my guess
>> would be different data as the root cause. If you were doing this on
>> the tiny sample objects that I created from your dput output, then I
>> don't have an answer, since there were no missing values in those
>> objects.
>>
>> -- 
>> David Winsemius
>>
>>
>> On Apr 21, 2009, at 5:21 PM, manta wrote:
>>
>>>
>>> This is what I get.
>>>
>>>> ccf(do1,dr1)
>>> Errore in na.fail.default(ts.intersect(as.ts(x), as.ts(y))) :
>>> valore mancante nell'oggetto #italian translation of 'missing
>>> values in
>>> object'
>>>> ccf(do1,dr2)
>>> Errore in na.fail.default(ts.intersect(as.ts(x), as.ts(y))) :
>>> valore mancante nell'oggetto #italian translation of 'missing
>>> values in
>>> object'
>>>
>>> Could the problem be in a different version of the ccf function i
>>> have?
>>>
>>>
>>>
>>>
>>> David Winsemius wrote:
>>>>
>>>> When I remake those variables and try ccf(do1,dr1), the plot  
>>>> appears
>>>> reasonable. What problem were you experiencing? It looks as though
>>>> your method of differencing (whatever it was) offset the date
>>>> registration of the zoo series in dr2,  but ccf(do1, dr2) still  
>>>> does
>>>> not appear to choke on that input.
>>>>
>>>> -- 
>>>> David
>>>>
>>>> On Apr 21, 2009, at 4:06 PM, manta wrote:
>>>>
>>>>> DW:  Modifications of that output to reconstruct the series:
>>>>
>>>>>
>>>>> do1 <- structure(c(0.0800000000000018, 0.009999999999998,
>>>>> 0.170000000000002,
>>>>> -0.0300000000000011, 0, 0.629999999999999, -0.319999999999997,
>>>>> -0.430000000000003, -0.469999999999999, -0.359999999999999),  
>>>>> index =
>>>>> structure(c(9497,
>>>>> 9498, 9499, 9500, 9503, 9504, 9505, 9506, 9507, 9510), class =
>>>>> "Date"),
>>>>> class = "zoo");
>>>>
>>>>>
>>>>> dr1 <- structure(c(0.000581439553993701, -0.00237250002417344,
>>>>> -0.00728359151384361,
>>>>> 0.00745364483017663, -0.000700422111259091, -0.00100249660582796,
>>>>> 0.00198943708754806, 0.000342959230417050, -0.00113732213621109,
>>>>> -0.00205039624417003), index = structure(c(9497, 9498, 9499,
>>>>> 9500, 9503, 9504, 9505, 9506, 9507, 9510), class = "Date"),  
>>>>> class =
>>>>> "zoo");
>>>>
>>>>>
>>>>> dr2 <- structure(c(-0.00295393957816714, -0.00491109148967017,
>>>>> 0.0147372363440202,
>>>>> -0.00815406694143572, -0.000302074494568871, 0.00299193369337603,
>>>>> -0.00164647785713101, -0.00148028136662814, -0.000913074107958933,
>>>>> -0.00247839573899256), index = structure(c(9498, 9499, 9500,
>>>>> 9503, 9504, 9505, 9506, 9507, 9510, 9511), class = "Date"),  
>>>>> class =
>>>>> "zoo")
>>>>
>>>>>
>>>>>
>>>>> total number of observations is 3393 for the original data set  
>>>>> (i.e.
>>>>> for do1
>>>>> is 3392, for do2 is 3391 and so on)
>>>>>
>>>>>
>>>>>
>>>>> David Winsemius wrote:
>>>>>>
>>>>>> We still have an inadequate characterization of the data to answe
>>>>>> the
>>>>>> question ( as I remember it from yesterday). Missing, for
>>>>>> example, is
>>>>>> any information about lengths which would seem essential since
>>>>>> (as I
>>>>>> remember) you wantted to know why the result was so short. Why  
>>>>>> not
>>>>>> put
>>>>>> in a full working example with an extract of the data. Suggest  
>>>>>> you
>>>>>> try
>>>>>> using dput as a method of creating a working example. That way we
>>>>>> (and
>>>>>> the R interpreter) would get labels and class information.
>>>>>>
>>>>>> -- 
>>>>>> David Winsemius
>>>>>>
>>>>>> On Apr 21, 2009, at 10:56 AM, manta wrote:
>>>>>>
>>>>>>>
>>>>>>> Sorry, my bad, i did not mean to 'be mean'.
>>>>>>> Here are the first five observations for three variables (dr1,  
>>>>>>> dr2
>>>>>>> and doil)
>>>>>>>
>>>>>>> dr1
>>>>>>> 1996-01-02    1996-01-03    1996-01-04    1996-01-05     
>>>>>>> 1996-01-08
>>>>>>> 0.0005814396 -0.0023725000 -0.0072835915  0.0074536448
>>>>>>> -0.0007004221
>>>>>>>
>>>>>>> dr2
>>>>>>> 1996-01-03    1996-01-04    1996-01-05    1996-01-08     
>>>>>>> 1996-01-09
>>>>>>> -0.0029539396 -0.0049110915  0.0147372363 -0.0081540669
>>>>>>> -0.0003020745
>>>>>>>
>>>>>>> do1
>>>>>>> 1996-01-02 1996-01-03 1996-01-04 1996-01-05 1996-01-08
>>>>>>>   0.08       0.01       0.17      -0.03       0.00
>>>>>>>
>>>>>>> As you can see, dr2 is nothing but the 1st difference of dr1. In
>>>>>>> my
>>>>>>> case,
>>>>>>> I'm trying to find out the cross-correlation between the two
>>>>>>> variables do1
>>>>>>> and dr1 up to their 10th lag (i.e. do1 with do2, do3, ...,
>>>>>>> do10,dr1,dr2,...,dr10, and the same for dr1).
>>>>>>>
>>>>>>> Hope it helps,
>>>>>>> Marco
>>>>>>>
>>>>
>>>>
>>>>>>> In response to "??"
>>>>
>>>>>>> David Winsemius wrote:
>>>>>>>>
>>>>>>>> Are you trying to imply that people should be able to answer a
>>>>>>>> question that included no data? As others have pointed out, our
>>>>>>>> powers of telepathy are generally less than commonly assumed.
>>>>>>>>
>>>>
>>>> David Winsemius, MD
>>>> Heritage Laboratories
>>>> West Hartford, CT
>>>>
>>>> ______________________________________________
>>>> R-help at r-project.org mailing list
>>>> https://stat.ethz.ch/mailman/listinfo/r-help
>>>> PLEASE do read the posting guide
>>>> http://www.R-project.org/posting-guide.html
>>>> and provide commented, minimal, self-contained, reproducible code.
>>>>
>>>>
>>>
>>> -- 
>>> View this message in context:
>>> http://www.nabble.com/Cross-Correlation-function-%28CCF%29-issues-tp23145411p23165218.html
>>> Sent from the R help mailing list archive at Nabble.com.
>>>
>>> ______________________________________________
>>> R-help at r-project.org mailing list
>>> https://stat.ethz.ch/mailman/listinfo/r-help
>>> PLEASE do read the posting guide
>>> http://www.R-project.org/posting-guide.html
>>> and provide commented, minimal, self-contained, reproducible code.
>>
>> David Winsemius, MD
>> Heritage Laboratories
>> West Hartford, CT
>>
>> ______________________________________________
>> R-help at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide
>> http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>>
>>
>
> -- 
> View this message in context: http://www.nabble.com/Cross-Correlation-function-%28CCF%29-issues-tp23145411p23165521.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

David Winsemius, MD
Heritage Laboratories
West Hartford, CT




More information about the R-help mailing list