You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: contributing.html
+7-7Lines changed: 7 additions & 7 deletions
Original file line number
Diff line number
Diff line change
@@ -323,14 +323,14 @@ <h2 class="anchored" data-anchor-id="quick-start-with-github-codespaces">Quick S
323
323
<spanid="cb1-4"><ahref="#cb1-4" aria-hidden="true" tabindex="-1"></a><spanclass="ex">pixi</span> run <spanclass="at">-e</span> dev maturin-develop</span></code></pre></div><buttontitle="Copy to Clipboard" class="code-copy-button"><iclass="bi"></i></button></div>
324
324
<p><code>pixi</code> will install the development environment and all dependencies.</p>
325
325
<p>Now, create a new Python script <code>debug.py</code> at the root of the repository and paste the following:</p>
Copy file name to clipboardExpand all lines: marginaleffects.html
+10-10Lines changed: 10 additions & 10 deletions
Original file line number
Diff line number
Diff line change
@@ -307,7 +307,7 @@ <h1 class="title">Marginal Effects and Hypothesis Tests via <code>marginaleffect
307
307
308
308
309
309
<p>We can compute marginal effects and linear and non-linear hypothesis tests via the excellent <ahref="https://github.com/vincentarelbundock/pymarginaleffects">marginaleffects</a> package.</p>
@@ -443,7 +443,7 @@ <h1 class="title">Marginal Effects and Hypothesis Tests via <code>marginaleffect
443
443
</div>
444
444
<p>Suppose we were interested in testing the hypothesis that <spanclass="math inline">\(X_{1} = X_{2}\)</span>. Given the relatively large differences in coefficients and small standard errors, we will likely reject the null that the two parameters are equal.</p>
445
445
<p>We can run the formal test via the <code>hypotheses</code> function from the <code>marginaleffects</code> package.</p>
<p>We can also test run-linear hypotheses, in which case <code>marginaleffects</code> will automatically compute correct standard errors based on the estimated covariance matrix and the Delta method. This is for example useful for computing inferential statistics for the “relative uplift” in an AB test.</p>
463
463
<p>For the moment, let’s assume that <spanclass="math inline">\(X1\)</span> is a randomly assigned treatment variable. As before, <spanclass="math inline">\(Y\)</span> is our variable / KPI of interest.</p>
464
464
<p>Under randomization, the model intercept measures the “baseline”, i.e. the population average of <spanclass="math inline">\(Y\)</span> in the absence of treatment. To compute a relative uplift, we might compute</p>
0 commit comments