Mendelian Randomization - Revision history

Davebrid1: /* 5. Decision Matrix: Which Results to Report */ Updated interpretation with directional pleiotropy

2026-08-03T23:26:12Z

5. Decision Matrix: Which Results to Report: Updated interpretation with directional pleiotropy

← Older revision		Revision as of 23:26, 3 August 2026
Line 216:		Line 216:
	\| '''3. Weak Instruments''' \|\| Mean F < 10 OR Relaxed criteria (p < 5e-6) used. \|\| "MR-RAPS. Baseline IVW is vulnerable to weak instrument bias."		\| '''3. Weak Instruments''' \|\| Mean F < 10 OR Relaxed criteria (p < 5e-6) used. \|\| "MR-RAPS. Baseline IVW is vulnerable to weak instrument bias."
	\|-		\|-
	\| '''4. Directional Pleiotropy''' \|\| Egger Intercept p < 0.05 '''or''' clear funnel asymmetry (§3.5). \|\| "Weighted Mode (if ~~I2GX~~ < 0.90) ~~OR MR~~-~~Egger Slope~~ (~~if I2GX >= 0.90~~)~~. IVW is discarded~~."		\| '''4. Directional Pleiotropy''' \|\| Egger Intercept p < 0.05 '''or''' clear funnel asymmetry (§3.5). \|\| "Report consensus of Weighted Median, Weighted Mode, and MR-Egger slope (disregard the MR-Egger slope as diluted if I²_GX < 0.90"). If the estimators disagree in sign, or by >2× in magnitude, treat as pleiotropy-limited (→ Scenario 6, Inconclusive) rather than forcing a single estimate."
	\|-		\|-
	\| '''5. Correlated Pleiotropy''' \|\| CAUSE model comparison p > 0.05 (Sharing Model wins). \|\| "Null Result (Discard Causality). The traits are correlated due to shared genetics, not a direct causal pathway."		\| '''5. Correlated Pleiotropy''' \|\| CAUSE model comparison p > 0.05 (Sharing Model wins). \|\| "Null Result (Discard Causality). The traits are correlated due to shared genetics, not a direct causal pathway."

Davebrid1: /* 5. Decision Matrix: Which Results to Report */ Updated decision tree

2026-07-31T21:02:03Z

5. Decision Matrix: Which Results to Report: Updated decision tree

← Older revision		Revision as of 21:02, 31 July 2026
Line 204:		Line 204:

	== 5. Decision Matrix: Which Results to Report ==		== 5. Decision Matrix: Which Results to Report ==
	~~Use~~ the ~~following adjudication criteria to synthesize~~ the ~~results from~~ the ~~models above~~.
			Every scenario below is adjudicated '''together with the scatter and funnel plots''' ([[#3.5 Visual Diagnostics: Scatter and Funnel Plots\|§3.5]]): visual identification of outlier SNPs or funnel asymmetry can select MR-PRESSO or an Egger/mode model even when the numeric trigger (Cochran's ''Q'', the Egger intercept) is borderline. Record the model used and the visual rationale per association.

	{\| class="wikitable"		{\| class="wikitable"
	\|-
	! Scenario !! Data Presentation !! Adjudicated Result to Report		! Scenario !! Data Presentation !! Adjudicated Result to Report
	\|-		\|-
	\| '''1. Clean Signal'''		\| '''1. Clean Signal''' \|\| F > 10. Cochran's Q p > 0.05. Egger Intercept p > 0.05. CAUSE Causal Model p < 0.05. \|\| "IVW (Fixed Effects). All assumptions are met."
	\| F > 10. Cochran's Q p > 0.05. Egger Intercept p > 0.05. CAUSE Causal Model p < 0.05.
	\| ~~'''~~IVW (Fixed Effects)~~'''~~. All assumptions are met.
	\|-		\|-
	\| '''2. Balanced Pleiotropy'''		\| '''2. Balanced Pleiotropy''' \|\| F > 10. Cochran's Q p < 0.05 '''or''' one/few outlier SNPs visible in the scatter/funnel (§3.5). Egger Intercept p > 0.05. \|\| "MR-PRESSO (Outlier Corrected) or IVW (Random Effects). Support with Weighted Median."
	\| F > 10. Cochran's Q p < 0.05. Egger Intercept p > 0.05.
	\| ~~'''~~MR-PRESSO (Outlier Corrected)~~'''~~ or ~~'''~~IVW (Random Effects)~~'''~~. Support with Weighted Median.
	\|-		\|-
	\| '''3. Weak Instruments'''		\| '''3. Weak Instruments''' \|\| Mean F < 10 OR Relaxed criteria (p < 5e-6) used. \|\| "MR-RAPS. Baseline IVW is vulnerable to weak instrument bias."
	\| Mean F < 10 OR Relaxed criteria (p < 5e-6) used.
	\| ~~'''~~MR-RAPS~~'''~~. Baseline IVW is vulnerable to weak instrument bias.
	\|-		\|-
	\| '''4. Directional Pleiotropy'''		\| '''4. Directional Pleiotropy''' \|\| Egger Intercept p < 0.05 '''or''' clear funnel asymmetry (§3.5). \|\| "Weighted Mode (if I2GX < 0.90) OR MR-Egger Slope (if I2GX >= 0.90). IVW is discarded."
	\| Egger Intercept p < 0.05.
	\| '''~~Weighted Mode~~''' (if I2GX < 0.90) OR ~~'''~~MR-Egger Slope~~'''~~ (if I2GX >= 0.90). IVW is discarded.
	\|-		\|-
	\| '''5. Correlated Pleiotropy'''		\| '''5. Correlated Pleiotropy''' \|\| CAUSE model comparison p > 0.05 (Sharing Model wins). \|\| "Null Result (Discard Causality). The traits are correlated due to shared genetics, not a direct causal pathway."
	\| CAUSE model comparison p > 0.05 (Sharing Model wins).
	\| ~~'''~~Null Result (Discard Causality)~~'''~~. The traits are correlated due to shared genetics, not a direct causal pathway. ~~Any significant IVW results are false positives.~~
	\|-		\|-
	\| '''6. Inconclusive'''		\| '''6. Inconclusive''' \|\| MR-PRESSO removes >30% of SNPs causing power loss, OR Median and Mode significantly contradict each other. \|\| "Unresolved / Inconclusive. State that genetic evidence is too pleiotropic to reliably disentangle."
	\| MR-PRESSO removes >30% of SNPs causing power loss, OR Median and Mode significantly contradict each other.
	\| ~~'''~~Unresolved / Inconclusive~~'''~~. State that genetic evidence is too pleiotropic to reliably disentangle.
	\|-		\|-
	\| '''7. Selection/collider bias''' \|\| Both arms present AND predicted bias same sign as observed		\| '''7. Selection/collider bias''' \|\| Both arms present AND predicted bias same sign as observed AND predicted ≈ observed magnitude. \|\| "Report as selection-bias-consistent, not causal. Give uncorrected + corrected estimates."
	AND predicted ≈ observed magnitude
	\| - Report as ~~'''~~selection-bias-consistent, not causal~~'''~~.
	Give uncorrected + corrected estimates. ~~Escalate to a design-based test before any causal claim.~~
	\|}		\|}

Davebrid1: /* 3. Analytical Models to Test */ Added section about making funnel and scatter plots

2026-07-31T21:01:11Z

3. Analytical Models to Test: Added section about making funnel and scatter plots

@@ Line 90: / Line 90: @@
 print(paste("I^2_GX =", round(i2gx_value, 3)))
 </syntaxhighlight>
 == 4 Selection and Collider Bias (Survival / Ascertainment) ==

Davebrid1: /* 3.4 Calculating I-squared GX for MR-Egger */ Fixed error in I2 calculation

2026-07-18T18:11:39Z

3.4 Calculating I-squared GX for MR-Egger: Fixed error in I2 calculation

← Older revision		Revision as of 18:11, 18 July 2026
Line 80:		Line 80:

	calculate_i2gx <- function(dat) {		calculate_i2gx <- function(dat) {
	~~beta_x~~ <- dat$beta.exposure		y <- dat$beta.exposure; s <- dat$se.exposure
	~~se_x~~ <- dat$se.exposure		k <- length(y); w <- 1/s^2
			mu <- sum(y * w) / sum(w) # inverse-variance weighted mean
	~~# Variance of the exposure estimates~~		Q <- sum(w * (y - mu)^2) # Cochran's Q for the exposure effects
	~~var_beta_x~~ <- ~~var~~(~~beta_x~~)		max(0, (Q - (k - 1)) / Q)

	~~# Mean of the squared standard errors~~
	~~mean_se_x2~~ <- ~~mean~~(~~se_x^2~~)

	# ~~Calculate I^2_GX~~
	~~I2gx~~ <- 1 - ~~(mean_se_x2 / var_beta_x~~)

	# ~~Constrain between 0 and 1~~
	~~I2gx <-~~ max(0, ~~I2gx~~)

	~~return(I2gx~~)
	}		}

Davebrid1: /* 4.3 Step 2 — Direction check (free; resolves most cases) */ minor error in section link

2026-07-18T18:11:03Z

4.3 Step 2 — Direction check (free; resolves most cases): minor error in section link

← Older revision		Revision as of 18:11, 18 July 2026
Line 131:		Line 131:
	Compute the predicted induced effect:		Compute the predicted induced effect:
	predicted bias = b_SH × (X→S)		predicted bias = b_SH × (X→S)
	where b_SH is the selection slope (§4.5.4). Then:		where b_SH is the selection slope (§4.4). Then:
	* '''Bias OPPOSITE in sign to the observed effect''' → bias is conservative; the true effect is		* '''Bias OPPOSITE in sign to the observed effect''' → bias is conservative; the true effect is
	if anything larger. Note it and proceed to normal adjudication.		if anything larger. Note it and proceed to normal adjudication.

Davebrid1: Added category tags

2026-07-18T18:10:28Z

Added category tags

← Older revision		Revision as of 18:10, 18 July 2026
Line 1:		Line 1:
	= Mendelian Randomization Standard Operating Procedure (SOP) =		= Mendelian Randomization Standard Operating Procedure (SOP) =
			[[ Category: Genetics ]]

	This SOP outlines the standardized pipeline for conducting two-sample Mendelian Randomization (MR) analyses, from instrument selection through to causal inference adjudication.		This SOP outlines the standardized pipeline for conducting two-sample Mendelian Randomization (MR) analyses, from instrument selection through to causal inference adjudication.

Davebrid1: /* 5. Decision Matrix: Which Results to Report */ minor typo

2026-07-18T18:09:55Z

5. Decision Matrix: Which Results to Report: minor typo

← Older revision		Revision as of 18:09, 18 July 2026
Line 207:		Line 207:
	\| - Report as '''selection-bias-consistent, not causal'''.		\| - Report as '''selection-bias-consistent, not causal'''.
	Give uncorrected + corrected estimates. Escalate to a design-based test before any causal claim.		Give uncorrected + corrected estimates. Escalate to a design-based test before any causal claim.
	\|}}		\|}

	==Reproducible Reporting of Results==		==Reproducible Reporting of Results==

	In addition to loading code into shareable repository, for our lab Github, once the manuscript is written complete the [https://www.strobe-mr.org/ STROBE-MR checklist] to ensure robust and clear reporting of key aspects of study design. Include this as supplementary data to the submission even if not strictly required by the journal.		In addition to loading code into shareable repository, for our lab Github, once the manuscript is written complete the [https://www.strobe-mr.org/ STROBE-MR checklist] to ensure robust and clear reporting of key aspects of study design. Include this as supplementary data to the submission even if not strictly required by the journal.

Davebrid1: /* 5. Decision Matrix: Which Results to Report */ Added row to results to report table

2026-07-18T18:08:03Z

5. Decision Matrix: Which Results to Report: Added row to results to report table

← Older revision		Revision as of 18:08, 18 July 2026
Line 202:		Line 202:
	\| MR-PRESSO removes >30% of SNPs causing power loss, OR Median and Mode significantly contradict each other.		\| MR-PRESSO removes >30% of SNPs causing power loss, OR Median and Mode significantly contradict each other.
	\| '''Unresolved / Inconclusive'''. State that genetic evidence is too pleiotropic to reliably disentangle.		\| '''Unresolved / Inconclusive'''. State that genetic evidence is too pleiotropic to reliably disentangle.
	\|}		\|-
			\| '''7. Selection/collider bias''' \|\| Both arms present AND predicted bias same sign as observed
			AND predicted ≈ observed magnitude
			\| - Report as '''selection-bias-consistent, not causal'''.
			Give uncorrected + corrected estimates. Escalate to a design-based test before any causal claim.
			\|}}

	==Reproducible Reporting of Results==		==Reproducible Reporting of Results==

	In addition to loading code into shareable repository, for our lab Github, once the manuscript is written complete the [https://www.strobe-mr.org/ STROBE-MR checklist] to ensure robust and clear reporting of key aspects of study design. Include this as supplementary data to the submission even if not strictly required by the journal.		In addition to loading code into shareable repository, for our lab Github, once the manuscript is written complete the [https://www.strobe-mr.org/ STROBE-MR checklist] to ensure robust and clear reporting of key aspects of study design. Include this as supplementary data to the submission even if not strictly required by the journal.

Davebrid1: /* 4 Selection and Collider Bias (Survival / Ascertainment) */ Added remainder of collider bias adjustement

2026-07-18T18:06:23Z

4 Selection and Collider Bias (Survival / Ascertainment): Added remainder of collider bias adjustement

← Older revision		Revision as of 18:06, 18 July 2026
Line 103:		Line 103:
	== 4 Selection and Collider Bias (Survival / Ascertainment) ==		== 4 Selection and Collider Bias (Survival / Ascertainment) ==

	Every model in §4 targets '''pleiotropy''' or '''weak instruments'''. None detects		Every model in Section 3 targets '''pleiotropy''' or '''weak instruments'''. None detects
	'''selection bias'''. A signal can pass Cochran's Q, the Egger intercept, MR-PRESSO and		'''selection bias'''. A signal can pass Cochran's Q, the Egger intercept, MR-PRESSO and
	the weighted median while being entirely generated by conditioning on sample membership.		the weighted median while being entirely generated by conditioning on sample membership.
Line 121:		Line 121:
	pre-registered bound δ, '''not''' p>0.05:		pre-registered bound δ, '''not''' p>0.05:
	* '''equivalence-null''' — 95% CI ⊂ ±δ → that arm is absent; collider cannot operate; stop.		* '''equivalence-null''' — 95% CI ⊂ ±δ → that arm is absent; collider cannot operate; stop.
	* '''real association''' — CI excludes 0 → arm present; go to 4.5.3.		* '''real association''' — CI excludes 0 → arm present; go to 4.3.
	* '''inconclusive''' — CI covers 0 but exceeds ±δ → '''report as unresolved''', never as "clean".		* '''inconclusive''' — CI covers 0 but exceeds ±δ → '''report as unresolved''', never as "clean".

Line 134:		Line 134:
	if anything larger. Note it and proceed to normal adjudication.		if anything larger. Note it and proceed to normal adjudication.
	* '''Bias SAME sign as the observed effect''' → the estimate may be partly or wholly induced.		* '''Bias SAME sign as the observed effect''' → the estimate may be partly or wholly induced.
	Go to 4.5.4.		Go to 4.4.

	For a life-shortening exposure the induced bias is '''protective'''. Therefore		For a life-shortening exposure the induced bias is '''protective'''. Therefore
Line 141:		Line 141:

	=== 4.4 Step 3 — Index-event correction (sensitivity only) ===		=== 4.4 Step 3 — Index-event correction (sensitivity only) ===
	Estimate the selection slope with SlopeHunter (incidence = survival		Estimate the selection slope with SlopeHunter (incidence = survival axis, prognosis = outcome).
			Because IVW is linear the correction is exact:
			corrected(X→Y) = (X→Y) − b_SH × (X→S)

			'''Requirements — an underpowered fit is worse than none:'''
			* Use '''full genome-wide summary statistics''', LD-clumped (r²<0.01, 1 Mb, ancestry-matched panel). Clumped tophits from an API are '''not sufficient''' (a 10-SNP fit is unidentified).
			* Target '''≳1,000 independent SNPs'''; report the fitted n and the slope CI.
			* Report fits '''with and without major pleiotropic loci''' (e.g. APOE for AD/lifespan) and without the locus under test if the analysis is locus-specific.
			* b_SH is a property of the (survival axis → outcome) pair, '''not''' of the exposure — fit once per outcome and reuse across exposures. Refit if the outcome dataset changes.

			'''Coherence check (the falsifiable quantity).''' Report predicted induced effect vs observed
			effect. If predicted ≈ observed, the selection pathway alone reproduces the signal.

			=== 4.5 Reporting requirements ===
			Always report '''uncorrected and corrected estimates side by side'''. The corrected value is a
			'''sensitivity bound, never the primary estimate'''.

			'''Stated limitation (include in all manuscripts using this section):''' the correction removes
			the component collinear with the survival axis and '''cannot distinguish collider-induced
			association from a genuine effect acting along that same axis'''. Because most exposures affect
			mortality, mechanical application will attenuate real effects. Correction '''diagnoses''';
			only '''design''' resolves — incident cohorts, age-stratified analyses, or younger-onset outcomes.

			'''Worked example.''' Smoking → Alzheimer's. Passed stringent instrument criteria, mean F>10,
			Egger intercept p=0.108, adjudicated Scenario 2 → MR-PRESSO b=−0.112, p=0.0015 (a reportable
			positive). Both collider arms were present (instruments→lung cancer p=10⁻⁵¹; AD liability→shorter
			lifespan p=0.003). A genome-wide index-event correction (2,346 SNPs, b_SH=−0.944) reduced the
			pooled estimate from −0.129 to +0.005 (p=0.91), and the collider structure predicted 89–117% of
			the observed effect across three instrument sets. The standard toolkit — including a
			proxy-ascertainment sensitivity analysis that was '''falsely reassuring''' — did not detect this.

	== 5. Decision Matrix: Which Results to Report ==		== 5. Decision Matrix: Which Results to Report ==

Davebrid1: Added section about survival bias and how to address it

2026-07-18T18:02:37Z

Added section about survival bias and how to address it

@@ Line 101: / Line 101: @@
 </syntaxhighlight>
-== 4. Decision Matrix: Which Results to Report ==
+== 4 Selection and Collider Bias (Survival / Ascertainment) ==
 Use the following adjudication criteria to synthesize the results from the models above.