diff --git a/_quarto-website.yml b/_quarto-website.yml index d538c92..1325b15 100644 --- a/_quarto-website.yml +++ b/_quarto-website.yml @@ -14,6 +14,7 @@ project: render: - index.qmd - intro-causal.qmd + - philosophy-of-causality.qmd - collider-bias.qmd - bias-analyses.qmd - d_in_d.qmd @@ -40,6 +41,8 @@ website: menu: - text: "Introduction to causal inference" href: intro-causal.qmd + - text: "Philosophy of causality" + href: philosophy-of-causality.qmd - text: "Collider bias" href: collider-bias.qmd - text: "Bias analyses" @@ -55,6 +58,7 @@ website: contents: - index.qmd - intro-causal.qmd + - philosophy-of-causality.qmd - collider-bias.qmd - bias-analyses.qmd - d_in_d.qmd diff --git a/definitions/_def-counterfactual-account.qmd b/definitions/_def-counterfactual-account.qmd new file mode 100644 index 0000000..e245c53 --- /dev/null +++ b/definitions/_def-counterfactual-account.qmd @@ -0,0 +1,11 @@ +:::{#def-counterfactual-account} + +#### Counterfactual account of causation + +On the **counterfactual account**, +event $A$ causes event $B$ if +$A$ and $B$ both occurred, +and, had $A$ not occurred, +$B$ would not have occurred. + +::: diff --git a/definitions/_def-manipulability.qmd b/definitions/_def-manipulability.qmd new file mode 100644 index 0000000..7964a3e --- /dev/null +++ b/definitions/_def-manipulability.qmd @@ -0,0 +1,11 @@ +:::{#def-manipulability} + +#### Manipulability account of causation + +On the **manipulability account**, +$A$ is a cause of $B$ +if an intervention that changes $A$, +and that affects nothing else that bears on $B$, +would change $B$ [@woodward2003making]. + +::: diff --git a/definitions/_def-mechanistic-view.qmd b/definitions/_def-mechanistic-view.qmd new file mode 100644 index 0000000..1e86e19 --- /dev/null +++ b/definitions/_def-mechanistic-view.qmd @@ -0,0 +1,11 @@ +:::{#def-mechanistic-view} + +#### Mechanistic view of causation + +On the **mechanistic view**, +$A$ causes $B$ if +there is a mechanism, +an organized set of entities and activities, +that links $A$ to $B$ [@machamer2000thinking]. + +::: diff --git a/definitions/_def-probabilistic-view.qmd b/definitions/_def-probabilistic-view.qmd new file mode 100644 index 0000000..28b3026 --- /dev/null +++ b/definitions/_def-probabilistic-view.qmd @@ -0,0 +1,10 @@ +:::{#def-probabilistic-view} + +#### Probabilistic view of causation + +On the **probabilistic view**, +$A$ causes $B$ if +$A$ raises the probability of $B$ +after other relevant factors are held fixed [@suppes1970probabilistic]. + +::: diff --git a/definitions/_def-regularity-view.qmd b/definitions/_def-regularity-view.qmd new file mode 100644 index 0000000..3dfdfc7 --- /dev/null +++ b/definitions/_def-regularity-view.qmd @@ -0,0 +1,12 @@ +:::{#def-regularity-view} + +#### Regularity view of causation + +On the **regularity view**, +saying that $A$ causes $B$ means that +every event like $A$ is followed by an event like $B$ +(a "constant conjunction"), +with $A$ coming first +and the two occurring close together in space and time. + +::: diff --git a/definitions/_exm-counterfactual-account.qmd b/definitions/_exm-counterfactual-account.qmd new file mode 100644 index 0000000..383f978 --- /dev/null +++ b/definitions/_exm-counterfactual-account.qmd @@ -0,0 +1,15 @@ +:::{#exm-counterfactual-account} + + +#### Counterfactual account and smoking cessation + +Suppose a patient quit smoking +and did not develop lung cancer. +On the counterfactual account, +quitting prevented the cancer +only if the patient would have developed lung cancer +had they kept smoking. +We never observe that second scenario. +It is the [counterfactual outcome](intro-causal.qmd#def-counterfactual). + +::: diff --git a/definitions/_exm-interventions.qmd b/definitions/_exm-interventions.qmd new file mode 100644 index 0000000..9df2b67 --- /dev/null +++ b/definitions/_exm-interventions.qmd @@ -0,0 +1,19 @@ +:::{#exm-interventions} + + +#### A well-defined and an ill-defined question + +"What would a patient's blood pressure be +if they took 10 mg of a particular antihypertensive daily for a year?" +names a specific intervention, +so $Y(a)$ is meaningful. + +"What would a patient's blood pressure be +if they had a lower body weight?" +does not. +Diet, exercise, surgery, and illness all lower weight, +and they plausibly affect blood pressure differently. +We would need to specify a particular intervention +to define the causal question. + +::: diff --git a/definitions/_exm-manipulability.qmd b/definitions/_exm-manipulability.qmd new file mode 100644 index 0000000..b59719e --- /dev/null +++ b/definitions/_exm-manipulability.qmd @@ -0,0 +1,15 @@ +:::{#exm-manipulability} + + +#### Manipulability and a patient's sex + +"What is the effect of a smoking-cessation program on lung cancer risk?" +names an intervention that can be assigned, +so it fits the manipulability account. + +"What is the effect of a patient's sex on lung cancer risk?" +does not name an intervention. +On this account the question is not well posed +until we say which intervention is meant. + +::: diff --git a/definitions/_exm-mechanistic-view.qmd b/definitions/_exm-mechanistic-view.qmd new file mode 100644 index 0000000..52e451e --- /dev/null +++ b/definitions/_exm-mechanistic-view.qmd @@ -0,0 +1,14 @@ +:::{#exm-mechanistic-view} + + +#### Mechanism and smoking + +A mechanistic account of smoking and lung cancer +would describe the steps between inhaling smoke +and the growth of a tumor, +such as damage to cells' DNA. +Evidence about such steps +can support the causal claim +alongside the statistical evidence. + +::: diff --git a/definitions/_exm-probabilistic-view.qmd b/definitions/_exm-probabilistic-view.qmd new file mode 100644 index 0000000..a845bd1 --- /dev/null +++ b/definitions/_exm-probabilistic-view.qmd @@ -0,0 +1,12 @@ +:::{#exm-probabilistic-view} + + +#### Probability raising and smoking + +Smoking raises the probability of lung cancer +among people who are alike in age and other relevant factors, +and it does not make lung cancer certain. +Under the probabilistic view, +that is enough for smoking to be a cause of lung cancer. + +::: diff --git a/definitions/_exm-regularity.qmd b/definitions/_exm-regularity.qmd new file mode 100644 index 0000000..deed4b6 --- /dev/null +++ b/definitions/_exm-regularity.qmd @@ -0,0 +1,11 @@ +:::{#exm-regularity} + + +#### Regularity and smoking + +Under a strict reading of the regularity view, +"smoking causes lung cancer" would be false, +because many smokers never develop lung cancer +and some non-smokers do. + +::: diff --git a/philosophy-of-causality.qmd b/philosophy-of-causality.qmd new file mode 100644 index 0000000..14ffa63 --- /dev/null +++ b/philosophy-of-causality.qmd @@ -0,0 +1,203 @@ +--- +title: "Philosophy of causality" +metadata-files: + - _chapter-formats.yml +format: + html: default + revealjs: + output-file: philosophy-of-causality-slides.html + pdf: + output-file: philosophy-of-causality-handout.pdf +--- + +{{< include latex-macros/macros.qmd >}} + +::: {.callout-note} +## Optional reading + +This chapter is background. +Nothing later in the book depends on it. +It explains where the potential-outcomes definitions in +[the introduction](intro-causal.qmd) come from, +and why they carry the assumptions they do. +::: + +## Why look at philosophy at all? + +The book defines a cause in terms of potential outcomes +([the definition of a cause](intro-causal.qmd#def-cause)). +That definition is one answer among several +to a question philosophers have argued over for centuries: +what does it mean to say that one thing causes another? +Seeing the other answers +makes it easier to see what the potential-outcomes answer includes, +what it leaves out, +and why. + +Each account below is a family of views, +and this chapter simplifies all of them. +The cited sources give the full arguments. + +## Five accounts of causation + +### Regularity {#sec-regularity} + +{{< include definitions/_def-regularity-view.qmd >}} + +Hume's discussion of causation is the standard starting point +[@hume1748enquiry, sec. 7]. +His point is that we never observe a necessary connection +between cause and effect. +We observe only that one kind of event reliably follows another. + +{{< include definitions/_exm-regularity.qmd >}} + +@exm-regularity shows the main weakness: +strict regularities are rare in epidemiology, +where outcomes are stochastic +and have many contributing causes. +Mackie's refinement treats a cause as +an insufficient but necessary part of a condition +that is itself unnecessary but sufficient for the effect +[@mackie1965causes]. +That version fits "component causes" better. + +### Counterfactual dependence {#sec-counterfactual-account} + +{{< include definitions/_def-counterfactual-account.qmd >}} + +Hume also wrote a second, counterfactual formulation of his definition +[@hume1748enquiry, sec. 7]. +Lewis later developed it into a full theory +based on comparing the actual world +with the closest possible worlds in which $A$ does not occur +[@lewis1973causation]. + +{{< include definitions/_exm-counterfactual-account.qmd >}} + +This account is the closest to [the definition of a cause](intro-causal.qmd#def-cause). +A potential outcome $Y(a')$ for an action $a'$ that did not occur +is a counterfactual outcome, +so the potential-outcomes framework makes counterfactual dependence +something a statistical model can describe +[@holland1986]. + +The account has two well-known difficulties. +First, "the closest possible world" is a philosophical notion +that has no obvious empirical meaning. +Second, it handles redundant causes badly: +if two sufficient causes were both present, +removing either one leaves the effect in place, +so neither counts as a cause. +The potential-outcomes framework avoids the first difficulty +by defining the counterfactual in terms of a specific action +([actions](intro-causal.qmd#def-action), @sec-manipulability), +and mostly sidesteps the second +by asking about the effect of one well-specified action at a time. + +### Manipulation and intervention {#sec-manipulability} + +{{< include definitions/_def-manipulability.qmd >}} + +Here the cause is something that someone could in principle change. +Holland summarized this view as "no causation without manipulation" +[@holland1986]. + +{{< include definitions/_exm-manipulability.qmd >}} + +This account is the one that the book's definitions +([actions](intro-causal.qmd#def-action) and [causes](intro-causal.qmd#def-cause)) take on: +a cause is an *action*, +and the effect is a contrast between outcomes under different actions. + +### Probabilistic causation {#sec-probabilistic} + +{{< include definitions/_def-probabilistic-view.qmd >}} + +This view repairs the regularity view for stochastic outcomes. +It also matches how epidemiologists work: +a risk factor changes the probability of disease +and does not determine it. + +{{< include definitions/_exm-probabilistic-view.qmd >}} + +Its main difficulty is the one every observational study faces. +Probability raising can come from confounding, +so "after other relevant factors are held fixed" does the heavy lifting, +and the view does not say which factors those are. +[The chapter on bias analyses](bias-analyses.qmd) +discusses how to handle that question in practice. + +### Mechanisms {#sec-mechanisms} + +{{< include definitions/_def-mechanistic-view.qmd >}} + +{{< include definitions/_exm-mechanistic-view.qmd >}} + +Mechanistic evidence, +such as a known biological pathway, +often strengthens a causal conclusion +even when the statistical evidence is limited. +The potential-outcomes framework does not require a mechanism +to define an effect. +It defines the effect of an action on an outcome +without describing how the action works. + +## What the potential-outcomes framework takes from these accounts + +@tbl-accounts summarizes how each account relates to this book. + +| Account | Core idea | Relation to this book | +|---|---|---| +| Regularity | Events of type $A$ are followed by events of type $B$ | Motivates asking whether an association is causal; too strict for stochastic outcomes | +| Counterfactual | $B$ would not have occurred without $A$ | Basis of [potential outcomes](intro-causal.qmd#def-potential-outcome) and [counterfactual outcomes](intro-causal.qmd#def-counterfactual) | +| Manipulability | A cause is something one could change | Basis of the definitions of [actions](intro-causal.qmd#def-action) and [causes](intro-causal.qmd#def-cause) | +| Probabilistic | Causes raise probabilities | Matches estimands defined on risks and means | +| Mechanistic | Causes work through mechanisms | Not needed for definitions; useful as supporting evidence | + +: Philosophical accounts of causation and where they appear in this book. {#tbl-accounts} + +Two assumptions in the book +come straight from the counterfactual and manipulability accounts: + +- **Consistency** ([definition](intro-causal.qmd#def-consistency)) + says that the outcome we observe under action $a$ + equals the potential outcome $Y(a)$. + That statement is only meaningful + if "action $a$" names one thing. + @hernan2008obesity and @hernan2016water + argue this using examples such as obesity and body mass index: + different ways of changing the exposure + can lead to different outcomes, + so a question about "the" effect of the exposure is ambiguous + until the intervention is specified. + @vanderweele2013versions formalize the point as + the problem of multiple versions of treatment. +- **Well-defined interventions** + are the practical form of the manipulability account. + If we cannot say what intervention would set $A$ to $a$, + we cannot say what $Y(a)$ refers to, + and consistency has nothing to hold on to. + +{{< include definitions/_exm-interventions.qmd >}} + +## Not everyone agrees + +The manipulability requirement is contested. +Some authors hold that causal questions about attributes +such as race or sex are meaningful without a specified intervention. +Others reply that +such questions can only mean something +once they are tied to an intervention on a related, manipulable variable. +This book follows the potential-outcomes tradition +and requires a specified intervention. +That choice is a design decision for the course, +and the other accounts above remain legitimate frameworks. + +## Further reading + +- The original discussion of the regularity and counterfactual formulations is Hume's *Enquiry* [@hume1748enquiry]. +- @lewis1973causation is the standard statement of the counterfactual account. +- @woodward2003making develops the interventionist (manipulability) account in detail. +- @holland1986 connects the philosophical discussion to statistical causal inference. +- @hernan2016water gives an epidemiologist's argument for well-defined interventions. diff --git a/references/references.bib b/references/references.bib index d50d427..1f87f55 100644 --- a/references/references.bib +++ b/references/references.bib @@ -195,6 +195,95 @@ @misc{bcallaway_cic } +@book{hume1748enquiry, + author = {Hume, David}, + title = {An Enquiry Concerning Human Understanding}, + year = {1748}, + address = {London}, + note = {First published 1748 as Philosophical Essays Concerning Human Understanding} +} + +@article{lewis1973causation, + author = {Lewis, David}, + title = {Causation}, + journal = {The Journal of Philosophy}, + volume = {70}, + number = {17}, + pages = {556--567}, + year = {1973}, + doi = {10.2307/2025310} +} + +@article{mackie1965causes, + author = {Mackie, J. L.}, + title = {Causes and Conditions}, + journal = {American Philosophical Quarterly}, + volume = {2}, + number = {4}, + pages = {245--264}, + year = {1965} +} + +@book{suppes1970probabilistic, + author = {Suppes, Patrick}, + title = {A Probabilistic Theory of Causality}, + publisher = {North-Holland}, + address = {Amsterdam}, + year = {1970} +} + +@book{woodward2003making, + author = {Woodward, James}, + title = {Making Things Happen: A Theory of Causal Explanation}, + publisher = {Oxford University Press}, + address = {New York}, + year = {2003} +} + +@article{machamer2000thinking, + author = {Machamer, Peter and Darden, Lindley and Craver, Carl F.}, + title = {Thinking about Mechanisms}, + journal = {Philosophy of Science}, + volume = {67}, + number = {1}, + pages = {1--25}, + year = {2000}, + doi = {10.1086/392759} +} + +@article{hernan2008obesity, + author = {Hern{\'a}n, M. A. and Taubman, S. L.}, + title = {Does obesity shorten life? {The} importance of well-defined interventions to answer causal questions}, + journal = {International Journal of Obesity}, + volume = {32}, + number = {S3}, + pages = {S8--S14}, + year = {2008}, + doi = {10.1038/ijo.2008.82} +} + +@article{hernan2016water, + author = {Hern{\'a}n, Miguel A.}, + title = {Does water kill? {A} call for less casual causal inferences}, + journal = {Annals of Epidemiology}, + volume = {26}, + number = {10}, + pages = {674--680}, + year = {2016}, + doi = {10.1016/j.annepidem.2016.08.016} +} + +@article{vanderweele2013versions, + author = {VanderWeele, Tyler J. and Hern{\'a}n, Miguel A.}, + title = {Causal Inference under Multiple Versions of Treatment}, + journal = {Journal of Causal Inference}, + volume = {1}, + number = {1}, + pages = {1--20}, + year = {2013}, + doi = {10.1515/jci-2012-0002} +} + @article{hernan2018cword, author = {Miguel A. Hern{\'a}n}, title = {The {C}-Word: Scientific Euphemisms Do Not Improve Causal Inference From Observational Data},