{
  "name": "Stata log-model commands and prediction scales",
  "description": "Original crosswalk compiled from Stata mathematical-function, regression and postestimation documentation and UCLA interpretation guidance. Commands assume separately generated lny=ln(y) and lnx=ln(x); contrasts hold other predictors fixed and have no interactions.",
  "page": "https://casrai.org/guides/log-regression-stata",
  "publisher": "CASRAI",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "dateModified": "2026-11-17T04:35:27Z",
  "temporalCoverage": null,
  "spatialCoverage": null,
  "columns": [
    {
      "name": "Specification",
      "unit": "",
      "description": ""
    },
    {
      "name": "Stata fitting command",
      "unit": "",
      "description": ""
    },
    {
      "name": "Default xb prediction scale",
      "unit": "",
      "description": ""
    },
    {
      "name": "Original-scale contrast",
      "unit": "",
      "description": ""
    },
    {
      "name": "Interpretation source",
      "unit": "",
      "description": ""
    }
  ],
  "rows": [
    {
      "Specification": "Log-linear",
      "Stata fitting command": "regress lny x",
      "Default xb prediction scale": "ln(y)",
      "Original-scale contrast": "exp(b*Δx): fitted geometric-mean ratio for change Δx in x",
      "Interpretation source": "UCLA OARC; Stata regress, predict and mathematical functions"
    },
    {
      "Specification": "Linear-log",
      "Stata fitting command": "regress y lnx",
      "Default xb prediction scale": "y",
      "Original-scale contrast": "b*ln(r): response-unit difference when positive x is multiplied by r",
      "Interpretation source": "UCLA OARC; Stata regress, predict and mathematical functions"
    },
    {
      "Specification": "Log-log",
      "Stata fitting command": "regress lny lnx",
      "Default xb prediction scale": "ln(y)",
      "Original-scale contrast": "r^b: fitted geometric-mean ratio when positive x is multiplied by r",
      "Interpretation source": "UCLA OARC; Stata regress, predict and mathematical functions"
    }
  ],
  "sources": [
    {
      "title": "Mathematical functions",
      "url": "https://www.stata.com/manuals/fnmathematicalfunctions.pdf",
      "accessed": "2026-11-17"
    },
    {
      "title": "regress — Linear regression",
      "url": "https://www.stata.com/manuals/rregress.pdf",
      "accessed": "2026-11-17"
    },
    {
      "title": "regress postestimation — Postestimation tools for regress",
      "url": "https://www.stata.com/manuals/rregresspostestimation.pdf",
      "accessed": "2026-11-17"
    },
    {
      "title": "FAQ How do I interpret a regression model when some variables are log transformed? – OARC Stats",
      "url": "https://stats.oarc.ucla.edu/other/mult-pkg/faq/general/faqhow-do-i-interpret-a-regression-model-when-some-variables-are-log-transformed/",
      "accessed": "2026-11-17"
    }
  ]
}