{
  "name": "seaborn.regplot arguments that change the fit, interval or points",
  "description": "Defaults and documented behaviour of twelve seaborn.regplot arguments, compiled from the official seaborn regplot reference page and regression tutorial, with whether the documentation names statsmodels for each.",
  "page": "https://casrai.org/guides/sns-regplot",
  "publisher": "CASRAI",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "dateModified": "2026-11-15T16:02:19Z",
  "temporalCoverage": null,
  "spatialCoverage": null,
  "columns": [
    {
      "name": "Argument",
      "unit": "",
      "description": ""
    },
    {
      "name": "Default",
      "unit": "",
      "description": ""
    },
    {
      "name": "Documented effect",
      "unit": "",
      "description": ""
    },
    {
      "name": "Needs statsmodels per documentation",
      "unit": "",
      "description": ""
    },
    {
      "name": "Documented note",
      "unit": "",
      "description": ""
    }
  ],
  "rows": [
    {
      "Argument": "ci",
      "Default": "95",
      "Documented effect": "Size of the bootstrapped confidence band around the regression estimate; None skips the bootstrap",
      "Needs statsmodels per documentation": "Not stated",
      "Documented note": "May be advisable to set None for large datasets"
    },
    {
      "Argument": "n_boot",
      "Default": "1000",
      "Documented effect": "Number of bootstrap resamples used for the interval",
      "Needs statsmodels per documentation": "Not stated",
      "Documented note": "Raise for final figures"
    },
    {
      "Argument": "order",
      "Default": "1",
      "Documented effect": "Polynomial regression when greater than 1",
      "Needs statsmodels per documentation": "No (numpy.polyfit)",
      "Documented note": ""
    },
    {
      "Argument": "logistic",
      "Default": "False",
      "Documented effect": "Logistic regression for a binary y",
      "Needs statsmodels per documentation": "Yes",
      "Documented note": "Substantially more computationally intensive"
    },
    {
      "Argument": "lowess",
      "Default": "False",
      "Documented effect": "Locally weighted nonparametric fit",
      "Needs statsmodels per documentation": "Yes",
      "Documented note": "No confidence interval can be drawn"
    },
    {
      "Argument": "robust",
      "Default": "False",
      "Documented effect": "Robust regression that de-weights outliers",
      "Needs statsmodels per documentation": "Yes",
      "Documented note": "Substantially more computationally intensive"
    },
    {
      "Argument": "logx",
      "Default": "False",
      "Documented effect": "Fits y ~ log(x), plotted in input space",
      "Needs statsmodels per documentation": "Not stated",
      "Documented note": "x must be positive"
    },
    {
      "Argument": "truncate",
      "Default": "True",
      "Documented effect": "Line bounded by data limits; False extends to axis limits",
      "Needs statsmodels per documentation": "Not stated",
      "Documented note": "Drawing extent only"
    },
    {
      "Argument": "x_jitter",
      "Default": "None",
      "Documented effect": "Uniform noise added to a copy of the data after fitting",
      "Needs statsmodels per documentation": "Not stated",
      "Documented note": "Changes scatter appearance only"
    },
    {
      "Argument": "x_bins",
      "Default": "None",
      "Documented effect": "Bins x for the scatter display; implies x_estimator=numpy.mean",
      "Needs statsmodels per documentation": "Not stated",
      "Documented note": "Regression still uses the original data"
    },
    {
      "Argument": "x_estimator",
      "Default": "None",
      "Documented effect": "Function applied to each unique x value",
      "Needs statsmodels per documentation": "Not stated",
      "Documented note": "Interval bootstrapped when x_ci is set"
    },
    {
      "Argument": "units",
      "Default": "None",
      "Documented effect": "Multilevel bootstrap grouping",
      "Needs statsmodels per documentation": "Not stated",
      "Documented note": "Affects confidence intervals only"
    }
  ],
  "sources": [
    {
      "title": "seaborn.regplot",
      "url": "https://seaborn.pydata.org/generated/seaborn.regplot.html",
      "accessed": "2026-11-15"
    },
    {
      "title": "Visualizing regression models",
      "url": "https://seaborn.pydata.org/tutorial/regression.html",
      "accessed": "2026-11-15"
    }
  ]
}