The phrase "dataset distribution" is grammatically correct and can be used in written English.
It refers to the way in which data is spread or allocated within a dataset. Here is an example sentence using "dataset distribution": "The dataset distribution shows that the majority of the data is concentrated in the first three categories, with minimal representation in the remaining categories."
Indeed, Fig. 6d shows that there is a strong correlation between magnitude and PGTA (or PGRV), whereas, for the other datasets, the magnitudes are better "distributed" along the whole dataset distribution (see Fig. 3).
We accessed this dataset (Distribution 7.0) from http://www.nimhgenetics.org/ through NIMH approval.
The dataset distribution of mutational changes was as follows: transition-type mutations (where a purine is substituted for a purine or pyrimidine for a pyrimidine) made up 74.8% of sequences identified as exonic and 67.8% of sequences identified as intronic.
In the primary (unfiltered) dataset, distribution of correlation coefficients for β2 log2MRIPA was distinctly bimodal, with a major mode occurring between 0 and −0.5, and a minor mode occurring between 0.25 and 0.75.
Individual dataset distributions split by 24 brain-related datasets, 14 blood, 5 liver, 3 fat and 7 other tissue datasets are shown in [Additional file 11].
BMI z scores and onset variables were derived from imputed BMI within each dataset; distributions were similar for observed and imputed values.
The chi-squared test was employed to compare the observed numbers of plasmid-encoded orphans, pairs, triads and tetrads, with those expected from whole dataset distributions.
In our dataset this distribution is statistically compatible with a Gaussian distribution with a coefficient of variation of approximately 8% (standard deviation/mean =0.08).
When using the 'common' promoter dataset the distribution of observed gene-wise PCCs resembles a normal distribution (mean = median: 0·04) in which extreme absolute values of PCCs are less common (Fig. 4).
In the case of the 'identical' promoter dataset, the distribution of PCCs is best characterized by an almost uniform distribution, with a slightly higher frequency of positive PCC values (mean/median: 0·08/0·12; Fig. 4).
Data sampling techniques attempt to alleviate the problem of class imbalance by altering a training dataset's distribution.
