nimare.meta.esma¶
Effect-size meta-analysis functions
Functions
fishers (z_maps[, two_sided]) |
Run a Fisher’s image-based meta-analysis on z-statistics. |
rfx_glm (con_maps[, null, n_iters, two_sided]) |
Run a random-effects (RFX) GLM on contrast maps. |
stouffers (z_maps[, inference, null, …]) |
Run a Stouffer’s image-based meta-analysis on z-statistic maps. |
weighted_stouffers (z_maps, sample_sizes[, …]) |
Run a Stouffer’s image-based meta-analysis on z-statistic maps. |
-
fishers
(z_maps, two_sided=True)[source]¶ Run a Fisher’s image-based meta-analysis on z-statistics.
Parameters: - z_maps ((n_contrasts, n_voxels)
numpy.ndarray
) – A 2D array of z-statistics. - two_sided (
bool
, optional) – Whether to do a two- or one-sided test. Default is True.
Returns: result – Dictionary containing maps for test statistics, p-values, and negative log(p) values.
Return type: - z_maps ((n_contrasts, n_voxels)
-
rfx_glm
(con_maps, null='theoretical', n_iters=None, two_sided=True)[source]¶ Run a random-effects (RFX) GLM on contrast maps.
Parameters: - con_maps ((n_contrasts, n_voxels)
numpy.ndarray
) – A 2D array of contrast maps in the same space, after masking. - null ({'theoretical', 'empirical'}, optional) – Whether to use a theoretical null T distribution or an empirically- derived null distribution determined via sign flipping. Default is ‘theoretical’.
- n_iters (
int
orNone
, optional) – The number of iterations to run in estimating the null distribution. Only used ifnull = 'empirical'
. - two_sided (
bool
, optional) – Whether to do a two- or one-sided test. Default is True.
Returns: result – Dictionary object containing maps for test statistics, p-values, and negative log(p) values.
Return type: - con_maps ((n_contrasts, n_voxels)
-
stouffers
(z_maps, inference='ffx', null='theoretical', n_iters=None, two_sided=True)[source]¶ Run a Stouffer’s image-based meta-analysis on z-statistic maps.
Parameters: - z_maps ((n_contrasts, n_voxels)
numpy.ndarray
) – A 2D array of z-statistic maps in the same space, after masking. - inference ({'ffx', 'rfx'}, optional) – Whether to use fixed-effects inference (default) or random-effects inference.
- null ({'theoretical', 'empirical'}, optional) – Whether to use a theoretical null T distribution or an empirically-
derived null distribution determined via sign flipping. Empirical null
is only possible if
inference = 'rfx'
. - n_iters (
int
orNone
, optional) – The number of iterations to run in estimating the null distribution. Only used ifinference = 'rfx'
andnull = 'empirical'
. - two_sided (
bool
, optional) – Whether to do a two- or one-sided test. Default is True.
Returns: result – Dictionary containing maps for test statistics, p-values, and negative log(p) values.
Return type: - z_maps ((n_contrasts, n_voxels)
-
weighted_stouffers
(z_maps, sample_sizes, two_sided=True)[source]¶ Run a Stouffer’s image-based meta-analysis on z-statistic maps.
Parameters: - z_maps ((n_contrasts, n_voxels)
numpy.ndarray
) – A 2D array of z-statistic maps in the same space, after masking. - sample_sizes ((n_contrasts,)
numpy.ndarray
) – A 1D array of sample sizes associated with contrasts inz_maps
. Must be in same order as rows inz_maps
. - two_sided (
bool
, optional) – Whether to do a two- or one-sided test. Default is True.
Returns: result – Dictionary containing maps for test statistics, p-values, and negative log(p) values.
Return type: - z_maps ((n_contrasts, n_voxels)