A major limitation of the direction of causation model

Non-shared environmental confounding

Stig Hebbelstrup Rye Rasmussen, Steven Ludeke, Jacob v. B. Hjelmborg

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

Determining (1) the direction of causation and (2) the size of causal effects between two constructs is a central challenge of the scientific study of humans. In the early 1990s, researchers in behavioral genetics invented what was termed the direction of causation (DoC) model to address exactly these two concerns. The model claims that for any two traits whose mode of inheritance is sufficiently different, the direction of causation can be ascertained using a sufficiently large genetically informative sample. Using a series of simulation studies, we demonstrate a major challenge to the DoC model, namely that it is extremely sensitive to even tiny amounts of non-shared confounding. Even under ideal conditions for the DoC model (a large sample, N = 10,000), a large causal relationship (e.g., a causal correlation of .50) with very different modes of inheritance between the two traits (e.g., a pure AE model for one trait and a pure CE model for another trait) and a modest degree (correlation of .10) of non-shared confounding between the two traits results in the choice of the wrong causal models and estimating the wrong causal effects.
Original languageEnglish
JournalTwin Research and Human Genetics
Volume22
Issue number1
Pages (from-to)14-26
ISSN1832-4274
DOIs
Publication statusPublished - 1. Feb 2019

Fingerprint

Causality
Research Personnel
Direction compound

Keywords

  • behavior genetics
  • causal inference
  • direction of causation
  • methods
  • twin studies

Cite this

@article{d805d03e76de4ee7b78515a8a3879001,
title = "A major limitation of the direction of causation model: Non-shared environmental confounding",
abstract = "Determining (1) the direction of causation and (2) the size of causal effects between two constructs is a central challenge of the scientific study of humans. In the early 1990s, researchers in behavioral genetics invented what was termed the direction of causation (DoC) model to address exactly these two concerns. The model claims that for any two traits whose mode of inheritance is sufficiently different, the direction of causation can be ascertained using a sufficiently large genetically informative sample. Using a series of simulation studies, we demonstrate a major challenge to the DoC model, namely that it is extremely sensitive to even tiny amounts of non-shared confounding. Even under ideal conditions for the DoC model (a large sample, N = 10,000), a large causal relationship (e.g., a causal correlation of .50) with very different modes of inheritance between the two traits (e.g., a pure AE model for one trait and a pure CE model for another trait) and a modest degree (correlation of .10) of non-shared confounding between the two traits results in the choice of the wrong causal models and estimating the wrong causal effects.",
keywords = "behavior genetics, causal inference, direction of causation, methods, twin studies",
author = "{Hebbelstrup Rye Rasmussen}, Stig and Steven Ludeke and Hjelmborg, {Jacob v. B.}",
year = "2019",
month = "2",
day = "1",
doi = "10.1017/thg.2018.67",
language = "English",
volume = "22",
pages = "14--26",
journal = "Twin Research and Human Genetics",
issn = "1832-4274",
publisher = "Heinemann",
number = "1",

}

A major limitation of the direction of causation model : Non-shared environmental confounding. / Hebbelstrup Rye Rasmussen, Stig; Ludeke, Steven; Hjelmborg, Jacob v. B.

In: Twin Research and Human Genetics, Vol. 22, No. 1, 01.02.2019, p. 14-26.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - A major limitation of the direction of causation model

T2 - Non-shared environmental confounding

AU - Hebbelstrup Rye Rasmussen, Stig

AU - Ludeke, Steven

AU - Hjelmborg, Jacob v. B.

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Determining (1) the direction of causation and (2) the size of causal effects between two constructs is a central challenge of the scientific study of humans. In the early 1990s, researchers in behavioral genetics invented what was termed the direction of causation (DoC) model to address exactly these two concerns. The model claims that for any two traits whose mode of inheritance is sufficiently different, the direction of causation can be ascertained using a sufficiently large genetically informative sample. Using a series of simulation studies, we demonstrate a major challenge to the DoC model, namely that it is extremely sensitive to even tiny amounts of non-shared confounding. Even under ideal conditions for the DoC model (a large sample, N = 10,000), a large causal relationship (e.g., a causal correlation of .50) with very different modes of inheritance between the two traits (e.g., a pure AE model for one trait and a pure CE model for another trait) and a modest degree (correlation of .10) of non-shared confounding between the two traits results in the choice of the wrong causal models and estimating the wrong causal effects.

AB - Determining (1) the direction of causation and (2) the size of causal effects between two constructs is a central challenge of the scientific study of humans. In the early 1990s, researchers in behavioral genetics invented what was termed the direction of causation (DoC) model to address exactly these two concerns. The model claims that for any two traits whose mode of inheritance is sufficiently different, the direction of causation can be ascertained using a sufficiently large genetically informative sample. Using a series of simulation studies, we demonstrate a major challenge to the DoC model, namely that it is extremely sensitive to even tiny amounts of non-shared confounding. Even under ideal conditions for the DoC model (a large sample, N = 10,000), a large causal relationship (e.g., a causal correlation of .50) with very different modes of inheritance between the two traits (e.g., a pure AE model for one trait and a pure CE model for another trait) and a modest degree (correlation of .10) of non-shared confounding between the two traits results in the choice of the wrong causal models and estimating the wrong causal effects.

KW - behavior genetics

KW - causal inference

KW - direction of causation

KW - methods

KW - twin studies

U2 - 10.1017/thg.2018.67

DO - 10.1017/thg.2018.67

M3 - Journal article

VL - 22

SP - 14

EP - 26

JO - Twin Research and Human Genetics

JF - Twin Research and Human Genetics

SN - 1832-4274

IS - 1

ER -