The _point_ is to explain the story of the research so people can compare easily with other work. A story interrupted by tedious details is not very comprehensible. And I _did_ recommend providing a link to a code repository and using reproducible coding tools. On December 30, 2024 7:35:37 PM PST, "Ebert,Timothy Aaron" <tebert at ufl.edu> wrote:>Maybe I misunderstand, but if the results cannot be reproduced, what is the point? I did some secret stuff (after talking to my friend the witch doctor) and here are my results. Some analyses preclude exact reproduction, but then researchers should rerun the analysis several times to provide a range or field of possible/probable results. > >-----Original Message----- >From: Jeff Newmiller <jdnewmil at dcn.davis.ca.us> >Sent: Monday, December 30, 2024 7:52 PM >To: r-help at r-project.org; Ebert,Timothy Aaron <tebert at ufl.edu>; Erin Hodgess <erinm.hodgess at gmail.com>; r-help at r-project.org >Subject: Re: [R] Citation for stock price data from Quantmod > >[External Email] > >While asking if you should document what you did and give credit where due seems... unnecessary (of course you should) ... I believe we are beyond the point where a paper alone can allow me to reproduce most relevant published analyses. That is, including a link to a reproducible code repository with a list of exact package/versions used and to the exact data used as input are necessary to achieve that degree of completeness. It is non-trivial even with tools like renv and a complete repo to document all of the decisions required to reproduce a published result months or years later... expecting citations and technical discussion alone to catch everything is IMO an unrealistic goal. The paper can only cover the general outline of the work, and should be complete enough to allow someone else to perform a validation study... most likely with different tools and data sets to check how robust the results are. > >If the results can only be reproduced with one data source, it may not deserve high regard in general, and documenting that you used a narrow slice of information as the foundation of your conclusions might be a sort of "YMMV" caution to the reader. > >On December 30, 2024 4:02:08 PM PST, "Ebert,Timothy Aaron" <tebert at ufl.edu> wrote: >>Yes, you need to cite the source of data and the method for retrieval. You also need to cite programs used in manipulating the data, cleaning the data, and analyzing the data. I should be able to read what you wrote, and using those methods recover the data independently from you and finish all other steps in the analysis. I should not have to guess. >> >>Tim >> >>-----Original Message----- >>From: R-help <r-help-bounces at r-project.org> On Behalf Of Erin Hodgess >>Sent: Monday, December 30, 2024 12:17 AM >>To: r-help at r-project.org >>Subject: [R] Citation for stock price data from Quantmod >> >>[External Email] >> >>Hello! >> >>Happy Holidays! >> >>I have a question about citing stock price data downloaded via Quantmod, please. Of course, I will cite Quantmod. Do I also need to cite Yahoo Finance as the actual source of the data, please? >>Also, I'm not sure if this is a question for the Finance sig, but thought I would start here. >> >>Thank you. >> >>Erin Hodgess, PhD >>mailto: erinm.hodgess at gmail.com >> >> [[alternative HTML version deleted]] >> >>______________________________________________ >>R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see >>https://stat/. >>ethz.ch%2Fmailman%2Flistinfo%2Fr-help&data=05%7C02%7Ctebert%40ufl.edu%7 >>C63f10a3f3aed465b4cfc08dd29354696%7C0d4da0f84a314d76ace60a62331e1b84%7C >>0%7C0%7C638712030988681340%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRy >>dWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3 >>D%7C0%7C%7C%7C&sdata=ykK%2BBt78wpifx16tATeYOx1kZk6Nh52r27u0O30p3kM%3D&r >>eserved=0 PLEASE do read the posting guide >>https://www.r/ >>-project.org%2Fposting-guide.html&data=05%7C02%7Ctebert%40ufl.edu%7C63f >>10a3f3aed465b4cfc08dd29354696%7C0d4da0f84a314d76ace60a62331e1b84%7C0%7C >>0%7C638712030988696546%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUs >>IlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C >>0%7C%7C%7C&sdata=RH3My8IjG6fXIdHGQF36PY6kDDG%2FpdgW9BGRAfHY1cE%3D&reser >>ved=0 and provide commented, minimal, self-contained, reproducible >>code. >> >>______________________________________________ >>R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see >>https://stat/. >>ethz.ch%2Fmailman%2Flistinfo%2Fr-help&data=05%7C02%7Ctebert%40ufl.edu%7 >>C63f10a3f3aed465b4cfc08dd29354696%7C0d4da0f84a314d76ace60a62331e1b84%7C >>0%7C0%7C638712030988704618%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRy >>dWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3 >>D%7C0%7C%7C%7C&sdata=TM0NCMmYxYx5%2FIUldYRX%2FCdpuzby7HaNOccXX6t1H8Y%3D >>&reserved=0 PLEASE do read the posting guide >>https://www.r/ >>-project.org%2Fposting-guide.html&data=05%7C02%7Ctebert%40ufl.edu%7C63f >>10a3f3aed465b4cfc08dd29354696%7C0d4da0f84a314d76ace60a62331e1b84%7C0%7C >>0%7C638712030988712694%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUs >>IlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C >>0%7C%7C%7C&sdata=CGXXrN%2Bb7thp88QaB9GCipUnFwujDCJkNwGPF6kgshI%3D&reser >>ved=0 and provide commented, minimal, self-contained, reproducible >>code. > >-- >Sent from my phone. Please excuse my brevity.-- Sent from my phone. Please excuse my brevity.
This isn't my field. But I'd have expected a sentence along the lines of: Stock prices were obtained from Yahoo Stocks[1] using the Quantmod R statistics package[2]. 1. Yahoo Citation 2. Quantmod citation That is readable. A further sentence: All analytical code is available from a publicly accessible repository[3]. 3. GitHub/FigShare repo Let's you then document minutia. Afterall, you presumably aren't writing an article that says "downloading stocks from Yahoo gives great results, but using any other method sucks". Instead, you are likely saying something like "stock prices fall and bounce back quickly after a pandemic". So even though you used Yahoo, if the result is true, someone else should get the same result using Yeaha (my made up alternative) and pen and paper... The versions, the packages used for cleaning etc, matter if someone can't reproduce your results even using Yahoo. But that level of detail doesn't need to be in the paper unless you know there are reproducibility issues! It just needs to be documented somewhere. On Tue, 31 Dec 2024, 04:23 Jeff Newmiller via R-help, <r-help at r-project.org> wrote:> The _point_ is to explain the story of the research so people can compare > easily with other work. A story interrupted by tedious details is not very > comprehensible. And I _did_ recommend providing a link to a code repository > and using reproducible coding tools. > > On December 30, 2024 7:35:37 PM PST, "Ebert,Timothy Aaron" <tebert at ufl.edu> > wrote: > >Maybe I misunderstand, but if the results cannot be reproduced, what is > the point? I did some secret stuff (after talking to my friend the witch > doctor) and here are my results. Some analyses preclude exact reproduction, > but then researchers should rerun the analysis several times to provide a > range or field of possible/probable results. > > > >-----Original Message----- > >From: Jeff Newmiller <jdnewmil at dcn.davis.ca.us> > >Sent: Monday, December 30, 2024 7:52 PM > >To: r-help at r-project.org; Ebert,Timothy Aaron <tebert at ufl.edu>; Erin > Hodgess <erinm.hodgess at gmail.com>; r-help at r-project.org > >Subject: Re: [R] Citation for stock price data from Quantmod > > > >[External Email] > > > >While asking if you should document what you did and give credit where > due seems... unnecessary (of course you should) ... I believe we are beyond > the point where a paper alone can allow me to reproduce most relevant > published analyses. That is, including a link to a reproducible code > repository with a list of exact package/versions used and to the exact data > used as input are necessary to achieve that degree of completeness. It is > non-trivial even with tools like renv and a complete repo to document all > of the decisions required to reproduce a published result months or years > later... expecting citations and technical discussion alone to catch > everything is IMO an unrealistic goal. The paper can only cover the general > outline of the work, and should be complete enough to allow someone else to > perform a validation study... most likely with different tools and data > sets to check how robust the results are. > > > >If the results can only be reproduced with one data source, it may not > deserve high regard in general, and documenting that you used a narrow > slice of information as the foundation of your conclusions might be a sort > of "YMMV" caution to the reader. > > > >On December 30, 2024 4:02:08 PM PST, "Ebert,Timothy Aaron" < > tebert at ufl.edu> wrote: > >>Yes, you need to cite the source of data and the method for retrieval. > You also need to cite programs used in manipulating the data, cleaning the > data, and analyzing the data. I should be able to read what you wrote, and > using those methods recover the data independently from you and finish all > other steps in the analysis. I should not have to guess. > >> > >>Tim > >> > >>-----Original Message----- > >>From: R-help <r-help-bounces at r-project.org> On Behalf Of Erin Hodgess > >>Sent: Monday, December 30, 2024 12:17 AM > >>To: r-help at r-project.org > >>Subject: [R] Citation for stock price data from Quantmod > >> > >>[External Email] > >> > >>Hello! > >> > >>Happy Holidays! > >> > >>I have a question about citing stock price data downloaded via Quantmod, > please. Of course, I will cite Quantmod. Do I also need to cite Yahoo > Finance as the actual source of the data, please? > >>Also, I'm not sure if this is a question for the Finance sig, but > thought I would start here. > >> > >>Thank you. > >> > >>Erin Hodgess, PhD > >>mailto: erinm.hodgess at gmail.com > >> > >> [[alternative HTML version deleted]] > >> > >>______________________________________________ > >>R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > >>https://stat/. > >>ethz.ch%2Fmailman%2Flistinfo%2Fr-help&data=05%7C02%7Ctebert%40ufl.edu%7 > >>C63f10a3f3aed465b4cfc08dd29354696%7C0d4da0f84a314d76ace60a62331e1b84%7C > >>0%7C0%7C638712030988681340%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRy > >>dWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3 > >>D%7C0%7C%7C%7C&sdata=ykK%2BBt78wpifx16tATeYOx1kZk6Nh52r27u0O30p3kM%3D&r > >>eserved=0 PLEASE do read the posting guide > >>https://www.r/ > >>-project.org%2Fposting-guide.html&data=05%7C02%7Ctebert%40ufl.edu%7C63f > >>10a3f3aed465b4cfc08dd29354696%7C0d4da0f84a314d76ace60a62331e1b84%7C0%7C > >>0%7C638712030988696546%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUs > >>IlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C > >>0%7C%7C%7C&sdata=RH3My8IjG6fXIdHGQF36PY6kDDG%2FpdgW9BGRAfHY1cE%3D&reser > >>ved=0 and provide commented, minimal, self-contained, reproducible > >>code. > >> > >>______________________________________________ > >>R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > >>https://stat/. > >>ethz.ch%2Fmailman%2Flistinfo%2Fr-help&data=05%7C02%7Ctebert%40ufl.edu%7 > >>C63f10a3f3aed465b4cfc08dd29354696%7C0d4da0f84a314d76ace60a62331e1b84%7C > >>0%7C0%7C638712030988704618%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRy > >>dWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3 > >>D%7C0%7C%7C%7C&sdata=TM0NCMmYxYx5%2FIUldYRX%2FCdpuzby7HaNOccXX6t1H8Y%3D > >>&reserved=0 PLEASE do read the posting guide > >>https://www.r/ > >>-project.org%2Fposting-guide.html&data=05%7C02%7Ctebert%40ufl.edu%7C63f > >>10a3f3aed465b4cfc08dd29354696%7C0d4da0f84a314d76ace60a62331e1b84%7C0%7C > >>0%7C638712030988712694%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUs > >>IlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C > >>0%7C%7C%7C&sdata=CGXXrN%2Bb7thp88QaB9GCipUnFwujDCJkNwGPF6kgshI%3D&reser > >>ved=0 and provide commented, minimal, self-contained, reproducible > >>code. > > > >-- > >Sent from my phone. Please excuse my brevity. > > -- > Sent from my phone. Please excuse my brevity. > > ______________________________________________ > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide > https://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. >[[alternative HTML version deleted]]
Fair enough. You do not put citations in the abstract or summary. The level of
detail in the methods can be modified by including a link to a repository or by
including supplemental material, or appendix, or foot notes, or something
equivalent. If all programs/packages are used with system defaults the version
number is sufficient. If the packages are customized and such customization
materially alters the results, then that information should be included in some
form. If only the outcome matters, then one is unlikely to read past the
abstract.
Write to your audience. The approach to a peer reviewed scientific
publication will be different from a 2-minute presentation to the board of
directors. If there are protocols mandating that the research is reproducible,
then you will need enough detail in the methods that someone can reproduce it
(or hope that nobody ever checks). Some places use different definitions for
reproducible versus replicable, but here one option:
https://www.amstat.org/asa/files/pdfs/POL-ReproducibleResearchRecommendations.pdf.
The rules for citations depend on your final goal and how others may use your
results. The expectations of your peers and professionalism should guide your
choices.
-----Original Message-----
From: Jeff Newmiller <jdnewmil at dcn.davis.ca.us>
Sent: Monday, December 30, 2024 11:23 PM
To: Ebert,Timothy Aaron <tebert at ufl.edu>; r-help at r-project.org; Erin
Hodgess <erinm.hodgess at gmail.com>
Subject: RE: [R] Citation for stock price data from Quantmod
[External Email]
The _point_ is to explain the story of the research so people can compare easily
with other work. A story interrupted by tedious details is not very
comprehensible. And I _did_ recommend providing a link to a code repository and
using reproducible coding tools.
On December 30, 2024 7:35:37 PM PST, "Ebert,Timothy Aaron" <tebert
at ufl.edu> wrote:>Maybe I misunderstand, but if the results cannot be reproduced, what is the
point? I did some secret stuff (after talking to my friend the witch doctor) and
here are my results. Some analyses preclude exact reproduction, but then
researchers should rerun the analysis several times to provide a range or field
of possible/probable results.
>
>-----Original Message-----
>From: Jeff Newmiller <jdnewmil at dcn.davis.ca.us>
>Sent: Monday, December 30, 2024 7:52 PM
>To: r-help at r-project.org; Ebert,Timothy Aaron <tebert at ufl.edu>;
Erin
>Hodgess <erinm.hodgess at gmail.com>; r-help at r-project.org
>Subject: Re: [R] Citation for stock price data from Quantmod
>
>[External Email]
>
>While asking if you should document what you did and give credit where due
seems... unnecessary (of course you should) ... I believe we are beyond the
point where a paper alone can allow me to reproduce most relevant published
analyses. That is, including a link to a reproducible code repository with a
list of exact package/versions used and to the exact data used as input are
necessary to achieve that degree of completeness. It is non-trivial even with
tools like renv and a complete repo to document all of the decisions required to
reproduce a published result months or years later... expecting citations and
technical discussion alone to catch everything is IMO an unrealistic goal. The
paper can only cover the general outline of the work, and should be complete
enough to allow someone else to perform a validation study... most likely with
different tools and data sets to check how robust the results are.
>
>If the results can only be reproduced with one data source, it may not
deserve high regard in general, and documenting that you used a narrow slice of
information as the foundation of your conclusions might be a sort of
"YMMV" caution to the reader.
>
>On December 30, 2024 4:02:08 PM PST, "Ebert,Timothy Aaron"
<tebert at ufl.edu> wrote:
>>Yes, you need to cite the source of data and the method for retrieval.
You also need to cite programs used in manipulating the data, cleaning the data,
and analyzing the data. I should be able to read what you wrote, and using those
methods recover the data independently from you and finish all other steps in
the analysis. I should not have to guess.
>>
>>Tim
>>
>>-----Original Message-----
>>From: R-help <r-help-bounces at r-project.org> On Behalf Of Erin
Hodgess
>>Sent: Monday, December 30, 2024 12:17 AM
>>To: r-help at r-project.org
>>Subject: [R] Citation for stock price data from Quantmod
>>
>>[External Email]
>>
>>Hello!
>>
>>Happy Holidays!
>>
>>I have a question about citing stock price data downloaded via Quantmod,
please. Of course, I will cite Quantmod. Do I also need to cite Yahoo Finance
as the actual source of the data, please?
>>Also, I'm not sure if this is a question for the Finance sig, but
thought I would start here.
>>
>>Thank you.
>>
>>Erin Hodgess, PhD
>>mailto: erinm.hodgess at gmail.com
>>
>> [[alternative HTML version deleted]]
>>
>>______________________________________________
>>R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
>>https://stat/.
>>ethz.ch%2Fmailman%2Flistinfo%2Fr-help&data=05%7C02%7Ctebert%40ufl.edu%
>>7
>>C63f10a3f3aed465b4cfc08dd29354696%7C0d4da0f84a314d76ace60a62331e1b84%7
>>C
>>0%7C0%7C638712030988681340%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnR
>>y
>>dWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%
>>3
>>D%7C0%7C%7C%7C&sdata=ykK%2BBt78wpifx16tATeYOx1kZk6Nh52r27u0O30p3kM%3D&
>>r
>>eserved=0 PLEASE do read the posting guide
>>https://nam10.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.
>>r%2F&data=05%7C02%7Ctebert%40ufl.edu%7C2622b5fa1e4549852d3908dd2952c9a
>>1%7C0d4da0f84a314d76ace60a62331e1b84%7C0%7C0%7C638712157762461251%7CUn
>>known%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOi
>>JXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=B3us1I75
>>EoHTxXDVAu4w0vYauKU0tFhI0S2yo94qQK0%3D&reserved=0
>>-project.org%2Fposting-guide.html&data=05%7C02%7Ctebert%40ufl.edu%7C63
>>f
>>10a3f3aed465b4cfc08dd29354696%7C0d4da0f84a314d76ace60a62331e1b84%7C0%7
>>C
>>0%7C638712030988696546%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWU
>>s
>>IlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7
>>C
>>0%7C%7C%7C&sdata=RH3My8IjG6fXIdHGQF36PY6kDDG%2FpdgW9BGRAfHY1cE%3D&rese
>>r
>>ved=0 and provide commented, minimal, self-contained, reproducible
>>code.
>>
>>______________________________________________
>>R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
>>https://stat/.
>>ethz.ch%2Fmailman%2Flistinfo%2Fr-help&data=05%7C02%7Ctebert%40ufl.edu%
>>7
>>C63f10a3f3aed465b4cfc08dd29354696%7C0d4da0f84a314d76ace60a62331e1b84%7
>>C
>>0%7C0%7C638712030988704618%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnR
>>y
>>dWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%
>>3
>>D%7C0%7C%7C%7C&sdata=TM0NCMmYxYx5%2FIUldYRX%2FCdpuzby7HaNOccXX6t1H8Y%3
>>D
>>&reserved=0 PLEASE do read the posting guide
>>https://nam10.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.
>>r%2F&data=05%7C02%7Ctebert%40ufl.edu%7C2622b5fa1e4549852d3908dd2952c9a
>>1%7C0d4da0f84a314d76ace60a62331e1b84%7C0%7C0%7C638712157762481129%7CUn
>>known%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOi
>>JXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=ybXgUREq
>>pyEDmJRTUS5ycIHsKG4SlWiQ4pdoB3fYvag%3D&reserved=0
>>-project.org%2Fposting-guide.html&data=05%7C02%7Ctebert%40ufl.edu%7C63
>>f
>>10a3f3aed465b4cfc08dd29354696%7C0d4da0f84a314d76ace60a62331e1b84%7C0%7
>>C
>>0%7C638712030988712694%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWU
>>s
>>IlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7
>>C
>>0%7C%7C%7C&sdata=CGXXrN%2Bb7thp88QaB9GCipUnFwujDCJkNwGPF6kgshI%3D&rese
>>r
>>ved=0 and provide commented, minimal, self-contained, reproducible
>>code.
>
>--
>Sent from my phone. Please excuse my brevity.
--
Sent from my phone. Please excuse my brevity.