Hi Bianca and everyone,

Am 07.03.19 um 14:03 schrieb Bianca Peterson:
> Good day everyone,
>
> Some of my colleagues are planning to develop a Biostatistics course
> to bridge the gap between undergraduate and postgraduate students.
> They are planning to develop their material on using SPSS, and I am
> trying to convince them to rather use R/RStudio. They are reluctant to
> switch, because (1) they have been using SPSS quite some time, (2)
> SPSS is "easier" than R, and
- r4stats has a post on popularity for several data analysis  packages:
http://r4stats.com/articles/popularity/
There are some graphs there that are very much in favor of R over SPSS.
- Of particular interest: Job offers asking for R vs. job offers asking
for SPSS
- a not-very-up-to-date trend for publications. However, according to
that, SPSS had its peak in 2009 (with SPSS : R ratio somewhere around
10:1). I did a quick comparison for 2018 using the search terms as
described in
http://r4stats.com/articles/how-to-search-for-data-science-articles/ and
the ratio is now about 3 : 2 (75000 SPSS vs. some 50000 for R)

- Basically, I haven't had anything to do with SPSS, so I don't know how
easy this is in SPSS. But the point that gets most researchers and
students very interested in R is when I tell them about reproducible
data analysis.
  - knitr documents and not needing to copy and paste stuff over into
Word & Co and tediously checking for typos.
  - with ease  ("just") being sure that you can look up all details on
your data analysis if necessary.
  - the possibilty to re-run without any need to worry whether your
re-did everything exactly as before.

  The reply ususally is that this is something they wish they'd known
before: these are points (i.e. the not-so-reproducible workflows) that
cause a lot of stress in real world academia.

> (3) they don't seem to think that funding might become a problem in
> future.

- I've been in a field where Matlab was (or still is?) the main data
analysis package. I've heard that as well. And I've seen people
switching to python or R in a rather abrupt fashion when that premise
turned out to be wrong.
- Even if their group doesn't run out of funding, the students are
likely to work in places where such considerations mean that there won't
be SPSS (nor Matlab)


>
> I came across the "Data Carpentry for Biologists" material in the
> discuss list http://datacarpentry.org/semester-biology/ and I'm
> looking for something similar specifically for
> Biostatistics/Biomedical statistics.
>
> Any resources or referrals will be greatly appreciated!

I'd be happy to give a hand after mid of April :-)
I don't know of any online resource I can particularly recommend, but
depending on how similar your biomed stats are to my biomed stats I may
be able contribute "explanation story lines" on some topics.

Best,

Claudia

>
> Kind regards,
> Bianca
>
> Bianca Peterson, Ph.D. Environmental Sciences (Genetics)
> Post-doctoral Research Fellow: Pharmaceutics
> Potchefstroom Campus
> North-West University
> South Africa
> 2531
> <https://twitter.com/BinxiePeterson?lang=en> 
> https://www.linkedin.com/in/bianca-peterson-007b5b117/
> <https://www.linkedin.com/in/bianca-peterson-007b5b117/>  
> https://github.com/BinxiePeterson <https://github.com/BinxiePeterson>
> *The Carpentries <https://carpentries.topicbox.com/latest>* / discuss
> / see discussions <https://carpentries.topicbox.com/groups/discuss> +
> participants <https://carpentries.topicbox.com/groups/discuss/members>
> + delivery options
> <https://carpentries.topicbox.com/groups/discuss/subscription>
> Permalink
> <https://carpentries.topicbox.com/groups/discuss/T7aec92fdeda8ec4b-Meb1f4b1ce6c1e7593be3691e>
>

-- 
Claudia Beleites Chemometric Consulting
Södeler Weg 19
61200 Wölfersheim
Germany

phone:  +49 (15 23) 1 83 74 18
e-mail: [email protected]
USt-ID: DE305606151


------------------------------------------
The Carpentries: discuss
Permalink: 
https://carpentries.topicbox.com/groups/discuss/T7aec92fdeda8ec4b-M7356ed3ddf9ceacfcd4ed027
Delivery options: https://carpentries.topicbox.com/groups/discuss/subscription

Reply via email to