Causal diagrams

Causal loop diagram

A causal loop diagram (CLD) is a causal diagram that aids in visualizing how different variables in a system are causally interrelated. The diagram consists of a set of words and arrows. Causal loop diagrams are accompanied by a narrative which describes the causally closed situation the CLD describes. Closed loops, or causal feedback loops, in the diagram are very important features of CLDs. The words with arrows coming in and out represent variables, or quantities whose value changes over time and the links represent a causal relationship between the two variables (i.e., they do not represent a material flow). A link marked + indicates a positive relation where an increase in the causal variable leads, all else equal, to an increase in the effect variable, or a decrease in the causal variable leads, all else equal, to a decrease in the effect variable. A link marked - indicates a negative relation where an increase in the causal variable leads, all else equal, to a decrease in the effect variable, or a decrease in the causal variable leads, all else equal, to an increase in the effect variable. A positive causal link can be said to lead to a change in the same direction, and an opposite link can be said to lead to change in the opposite direction, i.e. if the variable in which the link starts increases, the other variable decreases and vice versa. The words without arrows are loop labels. As with the links, feedback loops have either positive (i.e., reinforcing) or negative (i.e., balancing) polarity. CLDs contain labels for these processes, often using numbering (e.g., B1 for the first balancing loop being described in a narrative, B2 for the second one, etc.), and phrases that describe the function of the loop (i.e., "haste makes waste"). A reinforcing loop is a cycle in which the effect of a variation in any variable propagates through the loop and returns to reinforce the initial deviation (i.e. if a variable increases in a reinforcing loop the effect through the cycle will return an increase to the same variable and vice versa). A balancing loop is the cycle in which the effect of a variation in any variable propagates through the loop and returns to the variable a deviation opposite to the initial one (i.e. if a variable increases in a balancing loop the effect through the cycle will return a decrease to the same variable and vice versa). Balancing loops are typically goal-seeking, or error-sensitive, processes and are presented with the variable indicating the goal of the loop. Reinforcing loops are typically vicious or virtuous cycles. Example of positive reinforcing loop: * The amount of the Bank Balance will affect the amount of the Earned Interest, as represented by the top blue arrow, pointing from Bank Balance to Earned Interest. * Since an increase in Bank balance results in an increase in Earned Interest, this link is positive, which is denoted with a "+". * The Earned interest gets added to the Bank balance, also a positive link, represented by the bottom blue arrow. * The causal effect between these variables forms a positive reinforcing loop, represented by the green arrow, which is denoted with an "R". (Wikipedia).

Causal loop diagram
Video thumbnail

Causal diagrams to understand causality

This shows how to draw causal diagrams to understand what things are inputs and which are outputs

From playlist Examples

Video thumbnail

D-Separation - Causal Inference

Today I talk about association in causal diagrams, e.g., D-separation. By applying the rules I outline in this video you will be able to determine if two variables are associated.

From playlist Causal Inference - The Science of Cause and Effect

Video thumbnail

Causal Diagrams - Causal Inference

Today I talk about causal diagrams, e.g., dag, inline. This is one of the most important tools in Causal Inference, and we learn how to draw these tools out. Later we will learn how to use them in analysis.

From playlist Causal Inference - The Science of Cause and Effect

Video thumbnail

Double Blind - Causal Inference

In this video, I talk about the double blind assumption (both placebo effects and scientist preference effects) which serves as a good segue to causal diagrams, which I also go over. Enjoy!

From playlist Causal Inference - The Science of Cause and Effect

Video thumbnail

Thinking in Patterns - Level 6 - Causal Patterns

Thinking Slides: https://docs.google.com/presentation/d/1Wvjb5nDXz_HtCcWEmLGrOn9SEUNxfzvhwfZln-wGMfE/edit?usp=sharing The Wonder of Science: https://thewonderofscience.com/mlccc16 In this video Paul Andersen shows conceptual thinking in a mini-lesson on causal patterns. Two examples are

From playlist Conceptual Thinking Mini-Lessons

Video thumbnail

Feedforward and Feedback control strategies Lecture 2018-01-05

High level descriptions of feedforward vs feedback with reference to causality

From playlist CPB Theme 1

Video thumbnail

The Physics of Driving Through a Vertical Loop

This animation shows some of the physics involved in vertical loops, including driving a loop at constant speed as well as coasting through the loop. This animation can be a starting point for discussions about Newton's Laws, Energy, reaction forces and more!

From playlist Circular Motion

Video thumbnail

Causal Inference Introduction

Causal Inference is a set of tools used to scientifically prove cause and effect, very commonly used in economics and medicine. This series will go over the basics that any data scientist should understand about causal inference - and point them to the tools they would need to perform it.

From playlist Causal Inference - The Science of Cause and Effect

Video thumbnail

System Dynamics: Systems Thinking and Modeling for a Complex World

MIT RES.15-004 System Dynamics: Systems Thinking and Modeling for a Complex World, IAP 2020 Instructor: James Paine View the complete course: https://ocw.mit.edu/RES-15-004IAP20 YouTube Playlist: https://www.youtube.com/playlist?list=PLUl4u3cNGP63Dur3imUjY08z92ypMphQ3 This one-day worksho

From playlist MIT OCW: RES.15-004 System Dynamics: Systems Thinking and Modeling for a Complex World, IAP 2020

Video thumbnail

Overview of Loops in Graph Theory | Graph Loop, Multigraphs, Pseudographs

What are loops in graph theory? Sometimes called self loops, a loop in a graph is an edge that connects a vertex to itself. These are not allowed in what are often called "simple graphs", which are the graphs we usually study when we begin studying graph theory. In simple graphs, loop ed

From playlist Graph Theory

Video thumbnail

AdS Locality and the Conformal Bootstrap by Simon Caron-Huot

ORGANIZERS : Pallab Basu, Avinash Dhar, Rajesh Gopakumar, R. Loganayagam, Gautam Mandal, Shiraz Minwalla, Suvrat Raju, Sandip Trivedi and Spenta Wadia DATE : 21 May 2018 to 02 June 2018 VENUE : Ramanujan Lecture Hall, ICTS Bangalore In the past twenty years, the discovery of the AdS/C

From playlist AdS/CFT at 20 and Beyond

Video thumbnail

Wolfram Physics Project: Working Session Wednesday, May 6, 2020 [Finding Black Hole Structures]

This is a Wolfram Physics Project working session on finding black hole structures in the Wolfram Model. Begins at 3:02 Originally livestreamed at: https://twitch.tv/stephen_wolfram Stay up-to-date on this project by visiting our website: http://wolfr.am/physics Check out the announcemen

From playlist Wolfram Physics Project Livestream Archive

Video thumbnail

ETH Lecture 05. Systems Dynamics I: Modelling (20/10/2011)

Course: Systems Dynamics and Complexity (Fall 2011) from ETH Zurich. Source: http://www.video.ethz.ch/lectures/d-mtec/2011/autumn/351-0541-00L.html

From playlist ETH Zürich: Systems Dynamics and Complexity (Fall 2011) | CosmoLearning Mathematics

Video thumbnail

Statistical Rethinking Winter 2019 Lecture 06

Lecture 06 of the Dec 2018 through March 2019 edition of Statistical Rethinking: A Bayesian Course with R and Stan. This lecture covers Chapter 6, multiple regression and basic causal inference, collider bias, back-door criterion.

From playlist Statistical Rethinking Winter 2019

Video thumbnail

Lec 14 | MIT 6.451 Principles of Digital Communication II

Introduction to Convolutional Codes View the complete course: http://ocw.mit.edu/6-451S05 License: Creative Commons BY-NC-SA More information at http://ocw.mit.edu/terms More courses at http://ocw.mit.edu

From playlist MIT 6.451 Principles of Digital Communication II

Video thumbnail

Modeling Vehicle Dynamics

Get a Free Trial: https://goo.gl/C2Y9A5 Get Pricing Info: https://goo.gl/kDvGHt Ready to Buy: https://goo.gl/vsIeA5 Model your vehicle dynamics for lap-time simulation, prediction of energy consumption, or to tune your suspension system. Christoph Hahn, Sebastian Castro, and Swarooph Ses

From playlist MATLAB and Simulink Racing Lounge

Video thumbnail

Measurement Error - Causal Inference

In this video, I introduce our next assumption: measurement error, and make use of causal diagrams to further explain the assumption. Enjoy!

From playlist Causal Inference - The Science of Cause and Effect

Related pages

Directed acyclic graph | Feedback | Path analysis (statistics) | Negative feedback | System dynamics | Directed graph | Bayesian network | Positive feedback