Skip to content

How the interpret non-significant Intercept value in Fixed Effects Table?

2 messages · Ben Bolker, Ilgim Hepdarcan

#
On Sun, Mar 19, 2017 at 3:19 PM, Ilgim Hepdarcan
<ilgim.hepdarcan at izmirekonomi.edu.tr> wrote:
These statements seem a little surprising and inconsistent with what I
understand about your
design.  "participants are nested within Nback types" would suggest
that each participant
gets only a single Nback type (and that there are multiple patients
per Nback type),
which seems inconsistent with your statement "each participant had 12
n-back conditions".
(Does each participant get each of the 4 n-back conditions exactly 3
times?  That isn't
necessary but would probably maximize statistical power.) Also, you
say "my random variable
is Nback types", which seems surprising and is inconsistent with the
formulas you give
below (which include Nback type as a fixed effect)
Yes: "random slopes" for categorical predictors equates to
"among-individual variation in effects".
You might want to make your null model

 ~ 1 + (1 | participant/NbackType)

and your subsequent (non-random-slope) models should probably use the
same random effect term. This makes participants *crossed* with NbackType (there
is a random effect of participant, potentially a fixed effect of NbackType, and
a random effect of the interaction between NbackType and participant).

  Your anova above suggests that the *combination* of NbackType and variation
of NbackType within participant is significant.

While it's not impossible for the overall anova result to be
significant while the individual
levels aren't, in this case I think the mismatch comes from the
mismatch in the random
effects term between the full and null models.
#
Sorry for the inconsistency,

I would say repeated measures are nested within participants. Each of the participants completed 4 NbackTypes for 3 times which is my independent variable (random effect). Gender of the participant (fixed effect) is also my other independent variable. My dependent variables are oxygenated hemoglobin from 16 channels.

So, I understand that I can use random slope model.

But, how about the none-significance of Intercept. 

Thank you for your quick answer Mr. Bolker.

Ilg?m 


----- Original Message -----
From: "Ben Bolker" <bbolker at gmail.com>
To: "Ilgim Hepdarcan" <ilgim.hepdarcan at izmirekonomi.edu.tr>
Cc: r-sig-mixed-models at r-project.org
Sent: Sunday, March 19, 2017 10:55:22 PM
Subject: Re: How the interpret non-significant Intercept value in Fixed Effects Table?

On Sun, Mar 19, 2017 at 3:19 PM, Ilgim Hepdarcan
<ilgim.hepdarcan at izmirekonomi.edu.tr> wrote:
These statements seem a little surprising and inconsistent with what I
understand about your
design.  "participants are nested within Nback types" would suggest
that each participant
gets only a single Nback type (and that there are multiple patients
per Nback type),
which seems inconsistent with your statement "each participant had 12
n-back conditions".
(Does each participant get each of the 4 n-back conditions exactly 3
times?  That isn't
necessary but would probably maximize statistical power.) Also, you
say "my random variable
is Nback types", which seems surprising and is inconsistent with the
formulas you give
below (which include Nback type as a fixed effect)
Yes: "random slopes" for categorical predictors equates to
"among-individual variation in effects".
You might want to make your null model

 ~ 1 + (1 | participant/NbackType)

and your subsequent (non-random-slope) models should probably use the
same random effect term. This makes participants *crossed* with NbackType (there
is a random effect of participant, potentially a fixed effect of NbackType, and
a random effect of the interaction between NbackType and participant).

  Your anova above suggests that the *combination* of NbackType and variation
of NbackType within participant is significant.

While it's not impossible for the overall anova result to be
significant while the individual
levels aren't, in this case I think the mismatch comes from the
mismatch in the random
effects term between the full and null models.