LMGroup.column_ttest(term, return_data=False, popmean=0, *args, **kwargs)

One-sample t-test on a single model column

  • term (str) – Name of the term to test.

  • return_data (bool) – Return the individual subjects’ coefficients along with test results.

  • popmean (scalar) – Value to compare y against (default is 0).

  • tail (0 | 1 | -1) – Which tail of the t-distribution to consider: 0: both (two-tailed); 1: upper tail (one-tailed); -1: lower tail (one-tailed).

  • samples (None | int) – Number of samples for permutation cluster test. For None, no clusters are formed. Use 0 to compute clusters without performing any permutations.

  • pmin (None | scalar (0 < pmin < 1)) – Threshold for forming clusters: use a t-value equivalent to an uncorrected p-value.

  • tmin (None | scalar) – Threshold for forming clusters.

  • tfce (bool) – Use threshold-free cluster enhancement (Smith & Nichols, 2009). Default is False.

  • tstart (scalar) – Restrict time window for permutation cluster test.

  • tstop (scalar) – Restrict time window for permutation cluster test.

  • mintime (scalar) – Minimum duration for clusters (in seconds).

  • minsource (int) – Minimum number of sources per cluster.


  • result (TTestOneSample) – T-test result.

  • data (Dataset (only with return_data=True)) – Dataset with subjects’ coefficients.


Performs a one-sample t-test on coefficient estimates from all subjects to test the hypothesis that the coefficient is different from popmean in the population.