Skip to content

longitudinal analysis when one group switched from control to treatment

1 message · Thierry Onkelinx

#
Please keep the mailing list in cc

1) Both boxplots display the same information. Choose the one you find the
most clear.
2) In an ideal world, all boxplots should look similar. Determining if they
are sufficiently similar is the point where statistics becomes an art
instead of science.
3) You could consider a random effect of the year-school interaction
(1|scid:year). This has the downside that each year-school combination gets
an independent estimate, ignoring a common school effect. It's up to you to
compare an improvement in fit vs the interpretability of the model.

Best regards,

Thierry

ir. Thierry Onkelinx
Statisticus / Statistician

Vlaamse Overheid / Government of Flanders
INSTITUUT VOOR NATUUR- EN BOSONDERZOEK / RESEARCH INSTITUTE FOR NATURE AND
FOREST
Team Biometrie & Kwaliteitszorg / Team Biometrics & Quality Assurance
thierry.onkelinx at inbo.be
Havenlaan 88 bus 73, 1000 Brussel
www.inbo.be

///////////////////////////////////////////////////////////////////////////////////////////
To call in the statistician after the experiment is done may be no more
than asking him to perform a post-mortem examination: he may be able to say
what the experiment died of. ~ Sir Ronald Aylmer Fisher
The plural of anecdote is not data. ~ Roger Brinner
The combination of some data and an aching desire for an answer does not
ensure that a reasonable answer can be extracted from a given body of data.
~ John Tukey
///////////////////////////////////////////////////////////////////////////////////////////

<https://www.inbo.be>


Op di 19 mei 2020 om 15:26 schreef Simon Harmel <sim.harmel at gmail.com>: