---
myst:
    substitutions:
        sentence1: ""
        sentence2: "methods"
        sentence3: "pre-defined laws"
        sentence4: "[](#statistics_random_proba_distribution)"
        sentence5: |
            In order to get this drawing, the variable are normalised from 0 to 1 and a random drawing 
            is performed in this range. The obtained value is computed calling the inverse CDF function 
            corresponding to the law under study (that one can see from 
            {numref}`dataserver_tuniform_distribution` until {numref}`dataserver_tstudent_distribution`).
        sentence6: |
            In order to get this drawing, the variable are normalised from 0 to 1 and this range is 
            split into the requested number of points for the {{doe}}. Thanks to this, a grid is 
            prepared, assuring equi-probability in every sub-space. Finally, a random drawing is 
            performed in every sub-range. The obtained value is computed calling the inverse CDF 
            function corresponding to the law under study (that one can see from 
            {numref}`dataserver_tuniform_distribution` until {numref}`dataserver_tstudent_distribution`).
        sentence7: ""
        sentence8: " which"
        sentence9: "[](#sampler_stochastic_method_maximin_lhs)."
        sentence10: "[](#sampler_stochastic_method_constrained_lhs)."
        sentence11: |
            It is doable by defining a correlation coefficient but the way it is treated from one 
            sampler to the other is tricky and is further discussed in the next section.
---
```{include} /../core/sampler/stochastic_method/introduction.md
```