Enum: ModelFamily¶
Statistical model family used to estimate the effect. Open vocabulary: write the source's own wording in the field when nothing here fits.
Permissible Values¶
| Value | Meaning | Description |
|---|---|---|
| glm | None | An ordinary least-squares general linear model, including the summary-statist... |
| mixed_effects | None | A model estimating random effects directly, rather than by summarizing a firs... |
| anova | None | Analysis of variance, with no continuous covariate |
| ancova | None | Analysis of covariance: a factorial design with a continuous covariate contro... |
| robust_regression | None | A regression fitted to resist outliers, such as an iteratively reweighted or ... |
In Subsets¶
Identifier and Mapping Information¶
Schema Source¶
- from schema: https://neurostuff.org/schemas/neuroimaging-study-storage
LinkML Source¶
name: ModelFamily
description: 'Statistical model family used to estimate the effect. Open vocabulary:
write the source''s own wording in the field when nothing here fits.'
in_subset:
- mvp
- model_extracted
from_schema: https://neurostuff.org/schemas/neuroimaging-study-storage
rank: 1000
permissible_values:
glm:
text: glm
description: 'An ordinary least-squares general linear model, including the summary-statistics
two-stage approach that fMRI calls a random-effects analysis: the group stage
is still a GLM on contrast images.'
in_subset:
- mvp
- model_extracted
mixed_effects:
text: mixed_effects
description: A model estimating random effects directly, rather than by summarizing
a first stage -- a linear mixed model, a hierarchical model.
in_subset:
- mvp
- model_extracted
anova:
text: anova
description: Analysis of variance, with no continuous covariate.
in_subset:
- mvp
- model_extracted
ancova:
text: ancova
description: 'Analysis of covariance: a factorial design with a continuous covariate
controlled for.'
in_subset:
- mvp
- model_extracted
robust_regression:
text: robust_regression
description: A regression fitted to resist outliers, such as an iteratively reweighted
or M-estimator fit.
in_subset:
- mvp
- model_extracted