Mediation Analysis in Neuroimaging Studies

Size: px
Start display at page:

Download "Mediation Analysis in Neuroimaging Studies"

Transcription

1 Mediation Analysis in Neuroimaging Studies Yi Zhao Department of Biostatistics Johns Hopkins Bloomberg School of Public Health January 15, 2019

2 Overview Introduction Functional mediation analysis High-dimensional mediation analysis Multimodal neuroimaging data integration Discussion 2 / 35

3 Mediation analysis α Mediator (M β Treatment (X γ Outcome (Y Quantifies the intermediate effect of the mediator 3 / 35

4 Mediation analysis α Mediator (M β Treatment (X γ Outcome (Y Quantifies the intermediate effect of the mediator Helps clarify the underlying causal mechanism 3 / 35

5 Mediation analysis α Mediator (M β Treatment (X γ Outcome (Y Quantifies the intermediate effect of the mediator Helps clarify the underlying causal mechanism Popular approach: structural equation modeling (SEM M = Xα + ɛ 1 Y = Xγ + Mβ + ɛ 2 αβ: indirect (mediation effect γ: direct effect 3 / 35

6 Neuroimaging studies Non-invasive techniques e.g. structural/diffusion/functional MRI, PET, MEG/EEG Functional MRI (fmri brain activity: changes in brain hemodynamics resting-state and task-based fmri Credit: NSF 4 / 35

7 Neuroimaging studies Non-invasive techniques e.g. structural/diffusion/functional MRI, PET, MEG/EEG Functional MRI (fmri brain activity: changes in brain hemodynamics resting-state and task-based fmri Objective Resting-state fmri brain co-activation (functional connectivity impact on cognitive behaviors Credit: NSF 4 / 35

8 Neuroimaging studies Non-invasive techniques e.g. structural/diffusion/functional MRI, PET, MEG/EEG Functional MRI (fmri brain activity: changes in brain hemodynamics resting-state and task-based fmri Objective Resting-state fmri brain co-activation (functional connectivity impact on cognitive behaviors Task-based fmri causal effect of stimulus on brain activity brain connectivity (effective connectivity Credit: NSF 4 / 35

9 Challenges Large n with hierarchically nested data structure participants ( sessions tasks/trials population level inference Large p uniformly spaced voxels > 100 putative functional/anatomical regions high-dimensional problem Complex data output time series functional data 5 / 35

10 Challenges Large n with hierarchically nested data structure participants ( sessions tasks/trials population level inference Large p uniformly spaced voxels > 100 putative functional/anatomical regions high-dimensional problem Complex data output time series functional data 5 / 35

11 Motivating example: response conflict task Response conflict task GO trial: button press STOP trial: withhold pressing Brain regions of interest primary motor cortex (M1: responsible for movement presupplementary motor area (presma: primary region for motor response prohibition Objective: quantify causal effects stimulus presma, stimulus M1 presma M1 (Obeso et al., / 35

12 Motivating example: response conflict task Response conflict task GO trial: button press STOP trial: withhold pressing Brain regions of interest primary motor cortex (M1: responsible for movement presupplementary motor area (presma: primary region for motor response prohibition Objective: quantify causal effects stimulus presma, stimulus M1 presma M1 (Obeso et al., / 35

13 Motivating example: response conflict task Response conflict task GO trial: button press STOP trial: withhold pressing Brain regions of interest primary motor cortex (M1: responsible for movement presupplementary motor area (presma: primary region for motor response prohibition Objective: quantify causal effects stimulus presma, stimulus M1 presma M1 (Obeso et al., / 35

14 Mediation analysis Mediator M(t Treatment X(t Outcome Y (t Conflict response task: STOP/GO Mediator region: presma, outcome region: M1 Mediation model on functional measures Dynamic causal effects 7 / 35

15 Functional mediation model For t [0, T ], Concurrent model Treatment X(t Mediator M(t Outcome Y (t M(t = X(tα(t + ɛ 1 (t Y (t = X(tγ(t + M(tβ(t + ɛ 2 (t Historical influence model M(t = X(sα(s, t ds + ɛ 1 (t Y (t = Ω 1 t Ω 2 t X(sγ(s, t ds + M(sβ(s, t ds + ɛ 2 (t Ω 3 t Ω k t = [(t δ k 0, t], δ k (0, + ], k = 1, 2, 3 if δ k [T, + ]: whole history 8 / 35

16 Concurrent model DE(t = E [ Y (t; {x(s, m(s} Ht Y (t; {x (s, m(s} Ht ] = ( x(t x (t γ(t IE(t = E [ Y (t; {x(s, m(s; {x(u} Hs } Ht Y (t; {x(s, m(s; {x (u} Hs } Ht ] = ( x(t x (t α(tβ(t Historical influence model [ ] DE(t = E Y (t; {x(s, m(s} Ht Y (t; {x (s, m(s} Ht ( = x(s x (s γ(s, t ds Ω 2 t [ ] IE(t = E Y (t; {x(s, m(s; {x(u} Hs } Ht Y (t; {x(s, m(s; {x (u} Hs } Ht ( = Ω 3 t Ω 1 s {x(s} Ht : history of variable x, H t = [0, t] (x(u x (uα(u, s du β(s, t ds M(t; {x(s} Ht : potential outcome of M at time t if X has the history {x(s} Ht Y (t; {x(s, m(s} Ht : potential outcome of Y at time t when the history X and M at level {x(s} Ht and {m(s} Ht 9 / 35

17 Historical influence model Direct effect (DE Indirect effect (IE (x(u x (uα(u, sβ(s, t DE(t = t t δ 0 (x(s x (sγ(s, t ds (x(s x (sγ(s, t t δ t s t 2δ t δ t s t δ u t IE(t = t s (x(u t δ 0 s δ 0 x (uα(u, sβ(s, t duds δ 1 = δ 2 = δ 3 = δ, δ small 10 / 35

18 Historical influence model Direct effect (DE Indirect effect (IE (x(u x (uα(u, sβ(s, t DE(t = t 0 (x(s x (sγ(s, t ds (x(s x (sγ(s, t 0 t s t s t u IE(t = t s (x(u 0 0 x (uα(u, sβ(s, t duds δ 1 = δ 2 = δ 3 = δ, δ [T, + ] 10 / 35

19 Response conflict task fmri study 1 N = 121 right-handed healthy participants randomized STOP/GO trials: 90 GO trials and 32 STOP trials mediator region: presma-post (MNI: (-4,-8,60 outcome region: M1 (MNI: (-41,-20,62 TR = 2 s, 184 time points X(t: convolution of event onsets and canonical HRF M(t and Y (t: BOLD signals after motion correction 1 OpenfMRI ds / 35

20 Concurrent model M(t = X(tα(t + ɛ 1 (t Y (t = X(tγ(t + M(tβ(t + ɛ 2 (t Historical influence model M(t = X(sα(s, t ds + ɛ 1 (t Y (t = Ω 1 t Ω 2 t X(sγ(s, t ds + M(sβ(s, t ds + ɛ 2 (t Ω 3 t Ω k t = [(t δ k 0, t], δ k (0, + ], k = 1, 2, 3 if δ k [T, + ]: whole history δ = 2, 4, 6, 10, 20, 30, (seconds 12 / 35

21 Model selection mean squared error: θ i observed M i or Y i MSE(ˆθ = 1 N N i=1 0 T (ˆθ i (t θ i (t 2 dt Concurrent Historical Historical ( X ( M δ = 2 δ = 4 δ = 6 δ = 10 δ = 20 δ = 30 δ = M δ = δ = δ = Y δ = δ = δ = δ = / 35

22 Mediator: presma-post (MNI: ( 4, 8, 60 STOP trial: δ MX = 20, δ Y X = 6, δ Y M = 4 14 / 35

23 Challenges Large n with hierarchically nested data structure participants ( sessions tasks/trials population level inference Large p uniformly spaced voxels > 100 putative functional/anatomical regions high-dimensional problem Complex data output time series functional data 15 / 35

24 Single modality Mediator p (M p Treatment (X a 1 a p a 2. Mediator 2 (M 2 b 2 Mediator 1 (M 1 b 1 c b p Outcome (Y 16 / 35

25 Single modality Mediator p (M p a p d 1p Mediator 2 (M 2. d 2p b p Treatment (X a 1 a 2 d 12 Mediator 1 (M 1 c b 1 b 2 Outcome (Y 16 / 35

26 Single modality Mediator p (M p a p d 1p Mediator 2 (M 2. d 2p b p Treatment (X a 1 a 2 d 12 Mediator 1 (M 1 c b 1 b 2 Outcome (Y Objective Identify significant brain regions (mediators Estimate mediation effects 16 / 35

27 Single modality Mediator p (M p a p d 1p Mediator 2 (M 2. d 2p b p Treatment (X a 1 a 2 d 12 Mediator 1 (M 1 c b 1 b 2 Outcome (Y Challenges Ordering of the mediators unknown Large number of mediators (> number of observations 16 / 35

28 Zhao and Luo (2016 Full model Reduced model ɛ 1p η 1p M p M p a p M 2 d 1p. ɛ 12 d 2p b p α p M 2. η 12 β p X a 1 a 2 d 12 ɛ M 11 1 c b 1 b 2 Y ɛ 2 X α 1 α 2 M 1 γ η 11 β 1 β 2 Y η 2 M 1 = Xa 1 + ɛ 11 M 2 = Xa 2 + M 1 d 12 + ɛ 12. M p = Xa p + M 1 d 1p + + M p 1 d p 1,p + ɛ 1p Y = Xc + M 1 b M pb p + ɛ 2 M 1 = Xα 1 + η 11 M 2 = Xα 2 + η 12. M p = Xα K + η 1p Y = Xγ + M 1 β M pβ p + η 2 17 / 35

29 Zhao and Luo (2016 Full model Reduced model ɛ 1p η 1p M p M p a p M 2 d 1p. ɛ 12 d 2p b p α p M 2. η 12 β p X a 1 a 2 d 12 ɛ M 11 1 c b 1 b 2 Y ɛ 2 X α 1 α 2 M 1 γ η 11 β 1 β 2 Y η 2 M 1 = Xa 1 + ɛ 11 M 2 = Xa 2 + M 1 d 12 + ɛ 12. M p = Xa p + M 1 d 1p + + M p 1 d p 1,p + ɛ 1p Y = Xc + M 1 b M pb p + ɛ 2 M 1 = Xα 1 + η 11 M 2 = Xα 2 + η 12. M p = Xα K + η 1p Y = Xγ + M 1 β M pβ p + η 2 17 / 35

30 Zhao and Luo (2016 Full model Reduced model ɛ 1p η 1p M p M p a p M 2 d 1p. ɛ 12 d 2p b p α p M 2. η 12 β p X a 1 a 2 d 12 ɛ M 11 1 c b 1 b 2 Y ɛ 2 X α 1 α 2 M 1 γ η 11 β 1 β 2 Y η 2 M 1 = Xa 1 + ɛ 11 M 2 = Xa 2 + M 1 d 12 + ɛ 12. M p = Xa p + M 1 d 1p + + M p 1 d p 1,p + ɛ 1p Y = Xc + M 1 b M pb p + ɛ 2 M 1 = Xα 1 + η 11 M 2 = Xα 2 + η 12. M p = Xα K + η 1p Y = Xγ + M 1 β M pβ p + η 2 17 / 35

31 adjacency matrix of mediators: Full Model 0 d 12 d 13 d 1p 0 d 23 d 2p. = dp 1,p 0 p p X a1 a2 Mp d2p. d1p ap ɛ12 M2 d12 b2 ɛ11 M1 b1 c ɛ1p bp Y ɛ2 influence matrix: (I p 1 Reduced Model γ = c, β 1 = b 1,..., β p = b p ( α 1 α p = (a 1 a p (I p 1 ( η 11 η 1p = (ɛ 11 ɛ 1p (I p 1 X α1 α2 αp M2 η11 M1 γ Mp. η12 β2 β1 η1p βp Y η2 18 / 35

32 Example with 3 mediators Full Model ɛ M 13 3 Reduced Model M 3 η 13 X d d a 3 ɛ M 12 2 b 3 a 2 d 12 b 2 ɛ M 11 a 1 1 b 1 c α 3 η 12 M 2 β 3 α 2 ɛ β 2 2 η 11 α 1 M 1 β 1 Y X γ 0 d 12 d 13 1 d 12 d 13 + d 12d 23 = 0 0 d 23, (I 3 1 = 0 1 d (α 1 α 2 α 3 = (a 1 a 2 a 3 (I 3 1 = (a 1 a 1 d 12 + a 2 a 1 (d 13 + d 12 d 23 + a 2 d 23 + a 3 Y η 2 19 / 35

33 Example with 3 mediators Full Model ɛ M 13 3 Reduced Model M 3 η 13 X d d a 3 ɛ M 12 2 b 3 a 2 d 12 b 2 ɛ M 11 a 1 1 b 1 c α 3 η 12 M 2 β 3 α 2 ɛ β 2 2 η 11 α 1 M 1 β 1 Y X γ 0 d 12 d 13 1 d 12 d 13 + d 12d 23 = 0 0 d 23, (I 3 1 = 0 1 d (α 1 α 2 α 3 = (a 1 a 2 a 3 (I 3 1 = (a 1 a 1 d 12 + a 2 a 1 (d 13 + d 12 d 23 + a 2 d 23 + a 3 Y η 2 19 / 35

34 Example with 3 mediators Full Model ɛ M 13 3 Reduced Model M 3 η 13 X d d a 3 ɛ M 12 2 b 3 a 2 d 12 b 2 ɛ M 11 a 1 1 b 1 c α 3 η 12 M 2 β 3 α 2 ɛ β 2 2 η 11 α 1 M 1 β 1 Y X γ 0 d 12 d 13 1 d 12 d 13 + d 12d 23 = 0 0 d 23, (I 3 1 = 0 1 d (α 1 α 2 α 3 = (a 1 a 2 a 3 (I 3 1 = (a 1 a 1 d 12 + a 2 a 1 (d 13 + d 12 d 23 + a 2 d 23 + a 3 Y η 2 19 / 35

35 Example with 3 mediators Full Model ɛ M 13 3 Reduced Model M 3 η 13 X d d a 3 ɛ M 12 2 b 3 a 2 d 12 b 2 ɛ M 11 a 1 1 b 1 c α 3 η 12 M 2 β 3 α 2 ɛ β 2 2 η 11 α 1 M 1 β 1 Y X γ 0 d 12 d 13 1 d 12 d 13 + d 12d 23 = 0 0 d 23, (I 3 1 = 0 1 d (α 1 α 2 α 3 = (a 1 a 2 a 3 (I 3 1 = (a 1 a 1 d 12 + a 2 a 1 (d 13 + d 12 d 23 + a 2 d 23 + a 3 Y η 2 19 / 35

36 Example with 3 mediators Full Model ɛ M 13 3 Reduced Model M 3 η 13 X d d a 3 ɛ M 12 2 b 3 a 2 d 12 b 2 ɛ M 11 a 1 1 b 1 c α 3 η 12 M 2 β 3 α 2 ɛ β 2 2 η 11 α 1 M 1 β 1 Y X γ 0 d 12 d 13 1 d 12 d 13 + d 12d 23 = 0 0 d 23, (I 3 1 = 0 1 d (α 1 α 2 α 3 = (a 1 a 2 a 3 (I 3 1 = (a 1 a 1 d 12 + a 2 a 1 (d 13 + d 12 d 23 + a 2 d 23 + a 3 Y η 2 19 / 35

37 Example with 3 mediators Full Model ɛ M 13 3 Reduced Model M 3 η 13 X d d a 3 ɛ M 12 2 b 3 a 2 d 12 b 2 ɛ M 11 a 1 1 b 1 c α 3 η 12 M 2 β 3 α 2 ɛ β 2 2 η 11 α 1 M 1 β 1 Y X γ 0 d 12 d 13 1 d 12 d 13 + d 12d 23 = 0 0 d 23, (I 3 1 = 0 1 d (α 1 α 2 α 3 = (a 1 a 2 a 3 (I 3 1 = (a 1 a 1 d 12 + a 2 a 1 (d 13 + d 12 d 23 + a 2 d 23 + a 3 Y η 2 19 / 35

38 Example with 3 mediators Full Model ɛ M 13 3 Reduced Model M 3 η 13 X d d a 3 ɛ M 12 2 b 3 a 2 d 12 b 2 ɛ M 11 a 1 1 b 1 c α 3 η 12 M 2 β 3 α 2 ɛ β 2 2 η 11 α 1 M 1 β 1 Y X γ 0 d 12 d 13 1 d 12 d 13 + d 12d 23 = 0 0 d 23, (I 3 1 = 0 1 d (α 1 α 2 α 3 = (a 1 a 2 a 3 (I 3 1 = (a 1 a 1 d 12 + a 2 a 1 (d 13 + d 12 d 23 + a 2 d 23 + a 3 Y η 2 19 / 35

39 (η 11 η 1p = (ɛ ɛ 1p (I p 1 } {{ } } 11 {{ } reduced model full model Sequential ignorability of mediators (sequentially conditionally independent Cov [vec(ɛ 1 ] = Ω I n = diag{ω 2 1,..., ω 2 p} I n Cov [vec(η 1 ] = ( I p 1 Ω ( Ip 1 In = Σ 1 I n Σ 1 diagonal matrix = 0 (mediators causally independent ( I p 1 Ω ( Ip 1 LDL decomposition of Σ1 Σ 1 positive-definite, decomposition unique p > n, ˆΣ 1 not of full rank decomposition not unique require knowledge of ordering of the mediators 20 / 35

40 Full Model Reduced Model ɛ1p η1p Mp Mp ap d1p. d2p αp. M2 ɛ12 bp M2 η12 βp a2 d12 b2 α2 β2 X a1 M1 c ɛ11 b1 Y ɛ2 X α1 M1 γ η11 β1 Y η2 α j : total effect of X on M j (e.g., α 2 = a 1d 12 + a 2 α j β j : M j mediation effect as the last mediator in pathway to Y dependency in M j s correlation in η 1j s (e.g., η 12 = η 11d 12 + ɛ / 35

41 Pathway Lasso min 1 p ( 2 l+λ α j β j + φ j (αj 2 + βj 2 + γ +ω j=1 } {{ } P 1 :pathway lasso penalty p ( α j + β j j=1 }{{} P 2 :lasso penalty loss function l = tr [ W 1(M Xα (M Xα ] + w 2(Y Xγ Mβ (Y Xγ Mβ λ 0, φ j > 1/2, ω 0 tuning parameters λ = 0: lasso penalty ω = 0: pathway lasso 22 / 35

42 Multimodal neuroimaging (Liu et al / 35

43 Structural and functional imaging Exposure Outcome Hypothesis: structural functional Objective: integrating DTI and fmri through mediation analysis 24 / 35

44 γ p2 ω p1p 2 M 2p2 M 1p1 θ p1 ω 2p2 π p2 X α p1 φ 1p1 α 1 α 2 ω p12... ω p11 φ 2p1 δ M 12 φ 12 ω 1p2 θ 2 ω ψ 2p2 ψ 1p2 θ 1 M 22 π 2 Y M 11 ω 12 ω 21 γ 2 ψ 12 π 1 γ 1 ω 11 M 21 Two blocks of mediators: {M 11,..., M 1p1 } and {M 21,..., M 2p2 } Within block, ordering unknown 25 / 35

45 Full model Reduced model β = α(i Φ 1, ζ = γ(i Ψ 1, Λ = Ω(I Ψ 1 26 / 35 γp2 ωp1p2 M2p2 ζp2 λp1p2 M2p2 M1p1 θp1 ω2p2 πp2 M1p1 θp1 λ2p2 πp2 X αp1 ωp12. φ1p1.. ωp11 δ φ2p1 α2 M12 α1 φ12... ψ2p2 ω1p2 ψ1p2 θ2 ω22 θ1 M22 π2 Y X βp1 β1 β2 λp12... λp11 δ M12 θ2 λ1p2 λ22... θ1 M22 π2 Y M11 ω12 ω21 γ2 ψ12 π1 M11 λ12 λ21 ζ2 π1 γ1 Full model ω11 M21 ( M 1 M 2 Y = Reduced model ( M 1 M 2 Y = α γ δ (X M 1 M 2 Φ Ω θ (ɛ + η ξ β ζ δ (X M 1 M 2 Λ θ (ε + ϑ ξ Ψ ζ1 π π λ11 M21

46 Full model Reduced model γp2 ωp1p2 M2p2 ζp2 λp1p2 M2p2 M1p1 θp1 ω2p2 πp2 M1p1 θp1 λ2p2 πp2 X αp1 ωp12. φ1p1.. ωp11 δ φ2p1 α2 M12 α1 φ12... ψ2p2 ω1p2 ψ1p2 θ2 ω22 θ1 M22 π2 Y X βp1 β1 β2 λp12... λp11 δ M12 θ2 λ1p2 λ22... θ1 M22 π2 Y M11 ω12 ω21 γ2 ψ12 π1 M11 λ12 λ21 ζ2 π1 γ1 ω11 M21 ζ1 λ11 M21 β jθ j: indirect effect of M 1j not through either M 1s s (for s > j or M 2 s ζ k π k : indirect effect of M 2k not through either M 1 s or M 2t s (for t > k β jλ jk π k : indirect effect through M 1j and M 2k but not through either M 1s s (for s > j or (M 1t for t > k dependency in M 1j s correlation in ε 1j s dependency in M 2k s correlation in ϑ 2k s 27 / 35

47 min tr [ W 1 (M 1 Xβ (M 1 Xβ ] + tr [ W 2 (M 2 Xζ M 1 Λ (M 2 Xζ M 1 Λ ] + w (Y Xδ M 1 θ M 2 π (Y Xδ M 1 θ M 2 π such that p 1 β j θ j t 1, j=1 p 2 ζ k π k t 2, k=1 p 1 p 2 β j λ jk π k t 3, j=1 k=1 δ t 4 p 1 j=1 p 2 k=1 p 1 p 2 j=1 k=1 δ t 4 ( βj θ j + ν 1 (β 2 j + θ2 j r 1, ( ζk π k + ν 2 (ζ 2 k + π2 k r 2, λ jk r 3, ν 1, ν 2 1/2 r 1 t 1, r 2 t 2, r 3 t 3 ν 1 ν 2 /r 1 r 2 28 / 35

48 A multimodal neuroimaging study N = 30 primary progressive aphasia (PPA patients semantic (7: fluent speech, impaired word comprehension nonfluent (9: difficulty producing grammatical sentences and/or motor speech impairment (apraxia of speech logopenic (14: word-finding difficulties and disproportionately impaired sentence repetition X = 1 if semantic, X = 0 otherwise Outcome (Y : word naming accuracy total effect: (p-value= Imaging modalities: DTI (M 1 and resting-state fmri (M 2 Baseline covariates: age, sex, year of onset, language severity Study interest: brain structural and functional pathways on word naming accuracy comparing semantic vs. non-semantic 29 / 35

49 DTI: FA value of p1 = 12 fiber tracks UNC (uncinate fasciculus ILF (inferior longitudinal fasciculus IFO (inferior fronto-occipital fasciculus SLF (superior longitudinal fasciculus: FP (fronto-parietal, FT (fronto-temporal, PT (parietal-temporal (Dick and Tremblay, 2012 both left and right fmri: functional connectivity of 19 regions (p2 = language areas IFG_opercularis IFG_orbitalis IFG_triangularis SMG FuG STG STG_pole MTG MTG_pole ITG 6 DMN MFG_DPFC AG PCC 30 / 35

50 Single-modality result DTI: 4.01% effect mediated fmri: 25.02% effect mediated ITG_L MFG_DPFC_R MTG_L AG_R MTG_L MFG_DPFC_R X Y MTG_L MTG_L_pole SMG_L MFG_DPFC_R X SMG_L MTG_L Y IFG_triangularis_R SMG_L IFG_triangularis_L STG_L_pole UNC_L IFG_orbitalis_R PCC_R IFG_opercularis_R SMG_L IFG_opercularis_L STG_L_pole 31 / 35

51 Single-modality result DTI: 4.01% effect mediated fmri: 25.02% effect mediated 31 / 35

52 Two-modality result X DTI fmri Y : 4.19% effect mediated MTG_L_pole MFG_DPFC_R MTG_L MTG_L_pole ILF_L STG_L_pole AG_R STG_L PCC_L STG_L AG_L STG_L MTG_L_pole STG_L MTG_L X UNC_L SMG_L PCC_R Y SMG_L AG_R SMG_L MTG_L SMG_L STG_L IFG_triangularis_L AG_R SLF_PT_L IFG_opercularis_L MTG_L_pole IFG_opercularis_L STG_L IFG_opercularis_L IFG_orbitalis_R 32 / 35

53 Two-modality result X DTI fmri Y : 4.19% effect mediated 32 / 35

54 Two-modality result X DTI fmri Y : 4.19% effect mediated (Petrides, / 35

55 Discussion Mediation analysis in neuroimaging applications Functional mediation analysis dynamic effective connectivity limitations and future directions unmeasured confounding, sensitivity analysis covariates: scalar and functional dense/sparse functional data High-dimensional mediation analysis ordering of the mediators simultaneous mediator selection and mediation effect estimation multimodal/multiview data integration: imaging and omics R packages: macc, gma, cfma, spcma (github 33 / 35

56 Acknowledgements Brown University Xi (Rossi Luo, PhD Department of Biostatistics Joseph Hogan, ScD Department of Biostatistics Yen-Tsung Huang, MD, ScD Departments of Epidemiology and Biostatistics Johns Hopkins University Brian Caffo, PhD Department of Biostatistics Martin Lindquist, PhD Department of Biostatistics Jerome Sanes, PhD Department of Neuroscience Eli Upfal, PhD Department of Computer Science UC Berkeley Kyrana Tsapkini, PhD Department of Neurology Lexin Li, PhD Department of Biostatistics and Epidemiology R01 DC by the National Institutes of Health (National Institute of Deafness and Communication Disorders 34 / 35

57 Thank you! 35 / 35

Granger Mediation Analysis of Functional Magnetic Resonance Imaging Time Series

Granger Mediation Analysis of Functional Magnetic Resonance Imaging Time Series Granger Mediation Analysis of Functional Magnetic Resonance Imaging Time Series Yi Zhao and Xi Luo Department of Biostatistics Brown University June 8, 2017 Overview 1 Introduction 2 Model and Method 3

More information

arxiv: v4 [stat.ap] 7 Jul 2017

arxiv: v4 [stat.ap] 7 Jul 2017 Estimating Causal Mediation Effects under Correlated Errors arxiv:40.77v4 [stat.ap] 7 Jul 07 Yi Zhao Brown University, Providence RI, USA. Xi Luo Brown University, Providence RI, USA. E-mail: xi.rossi.luo@gmail.com

More information

arxiv: v1 [stat.me] 15 Sep 2017

arxiv: v1 [stat.me] 15 Sep 2017 Biometrics XXX, 1 26 XXX XXX DOI: 10.1111/j.1541-0420.2005.00454.x Granger Mediation Analysis of Multiple Time Series with an Application to fmri arxiv:1709.05328v1 [stat.me] 15 Sep 2017 Yi Zhao Department

More information

Functional Causal Mediation Analysis with an Application to Brain Connectivity. Martin Lindquist Department of Biostatistics Johns Hopkins University

Functional Causal Mediation Analysis with an Application to Brain Connectivity. Martin Lindquist Department of Biostatistics Johns Hopkins University Functional Causal Mediation Analysis with an Application to Brain Connectivity Martin Lindquist Department of Biostatistics Johns Hopkins University Introduction Functional data analysis (FDA) and causal

More information

MIXED EFFECTS MODELS FOR TIME SERIES

MIXED EFFECTS MODELS FOR TIME SERIES Outline MIXED EFFECTS MODELS FOR TIME SERIES Cristina Gorrostieta Hakmook Kang Hernando Ombao Brown University Biostatistics Section February 16, 2011 Outline OUTLINE OF TALK 1 SCIENTIFIC MOTIVATION 2

More information

Functional Mediation Analysis with an Application to Functional Magnetic Resonance Imaging Data

Functional Mediation Analysis with an Application to Functional Magnetic Resonance Imaging Data Functional Mediation Analysis with an Application to Functional Magnetic Resonance Imaging Data arxiv:1805.06923v1 [stat.ap] 17 May 2018 Yi Zhao Department of Biostatistics, Johns Hopkins School of Public

More information

Tract-Specific Analysis for DTI of Brain White Matter

Tract-Specific Analysis for DTI of Brain White Matter Tract-Specific Analysis for DTI of Brain White Matter Paul Yushkevich, Hui Zhang, James Gee Penn Image Computing & Science Lab Department of Radiology University of Pennsylvania IPAM Summer School July

More information

Overview of Spatial Statistics with Applications to fmri

Overview of Spatial Statistics with Applications to fmri with Applications to fmri School of Mathematics & Statistics Newcastle University April 8 th, 2016 Outline Why spatial statistics? Basic results Nonstationary models Inference for large data sets An example

More information

The General Linear Model (GLM)

The General Linear Model (GLM) he General Linear Model (GLM) Klaas Enno Stephan ranslational Neuromodeling Unit (NU) Institute for Biomedical Engineering University of Zurich & EH Zurich Wellcome rust Centre for Neuroimaging Institute

More information

Dynamic Causal Modelling for fmri

Dynamic Causal Modelling for fmri Dynamic Causal Modelling for fmri André Marreiros Friday 22 nd Oct. 2 SPM fmri course Wellcome Trust Centre for Neuroimaging London Overview Brain connectivity: types & definitions Anatomical connectivity

More information

Integrative Methods for Functional and Structural Connectivity

Integrative Methods for Functional and Structural Connectivity Integrative Methods for Functional and Structural Connectivity F. DuBois Bowman Department of Biostatistics Columbia University SAMSI Challenges in Functional Connectivity Modeling and Analysis Research

More information

Event-related fmri. Christian Ruff. Laboratory for Social and Neural Systems Research Department of Economics University of Zurich

Event-related fmri. Christian Ruff. Laboratory for Social and Neural Systems Research Department of Economics University of Zurich Event-related fmri Christian Ruff Laboratory for Social and Neural Systems Research Department of Economics University of Zurich Institute of Neurology University College London With thanks to the FIL

More information

Extracting fmri features

Extracting fmri features Extracting fmri features PRoNTo course May 2018 Christophe Phillips, GIGA Institute, ULiège, Belgium c.phillips@uliege.be - http://www.giga.ulg.ac.be Overview Introduction Brain decoding problem Subject

More information

Part 2: Multivariate fmri analysis using a sparsifying spatio-temporal prior

Part 2: Multivariate fmri analysis using a sparsifying spatio-temporal prior Chalmers Machine Learning Summer School Approximate message passing and biomedicine Part 2: Multivariate fmri analysis using a sparsifying spatio-temporal prior Tom Heskes joint work with Marcel van Gerven

More information

Experimental design of fmri studies & Resting-State fmri

Experimental design of fmri studies & Resting-State fmri Methods & Models for fmri Analysis 2016 Experimental design of fmri studies & Resting-State fmri Sandra Iglesias With many thanks for slides & images to: Klaas Enno Stephan, FIL Methods group, Christian

More information

Towards a Regression using Tensors

Towards a Regression using Tensors February 27, 2014 Outline Background 1 Background Linear Regression Tensorial Data Analysis 2 Definition Tensor Operation Tensor Decomposition 3 Model Attention Deficit Hyperactivity Disorder Data Analysis

More information

Beyond Univariate Analyses: Multivariate Modeling of Functional Neuroimaging Data

Beyond Univariate Analyses: Multivariate Modeling of Functional Neuroimaging Data Beyond Univariate Analyses: Multivariate Modeling of Functional Neuroimaging Data F. DuBois Bowman Department of Biostatistics and Bioinformatics Center for Biomedical Imaging Statistics Emory University,

More information

Experimental design of fmri studies

Experimental design of fmri studies Experimental design of fmri studies Zurich SPM Course 2016 Sandra Iglesias Translational Neuromodeling Unit (TNU) Institute for Biomedical Engineering (IBT) University and ETH Zürich With many thanks for

More information

Spectral Perturbation of Small-World Networks with Application to Brain Disease Detection

Spectral Perturbation of Small-World Networks with Application to Brain Disease Detection Spectral Perturbation of Small-World Networks with Application to Brain Disease Detection Chenhui Hu May 4, 22 Introduction Many real life systems can be described by complex networks, which usually consist

More information

Experimental design of fmri studies

Experimental design of fmri studies Methods & Models for fmri Analysis 2017 Experimental design of fmri studies Sara Tomiello With many thanks for slides & images to: Sandra Iglesias, Klaas Enno Stephan, FIL Methods group, Christian Ruff

More information

Experimental design of fmri studies

Experimental design of fmri studies Experimental design of fmri studies Sandra Iglesias With many thanks for slides & images to: Klaas Enno Stephan, FIL Methods group, Christian Ruff SPM Course 2015 Overview of SPM Image time-series Kernel

More information

T 1 (p) T 3 (p) 2 (p) + T

T 1 (p) T 3 (p) 2 (p) + T εt) ut) Ep) ɛp) Tp) Sp) Ep) ɛp) T p) Up) T 2 p) T 3 p) Sp) Ep) ɛp) Cp) Up) Tp) Sp) Ep) ɛp) T p) Up) T 2 p) Cp) T 3 p) Sp) Ep) εp) K p Up) Tp) Sp) Cp) = Up) εp) = K p. ε i Tp) = Ks Np) p α Dp) α = ε i =

More information

Optimization of Designs for fmri

Optimization of Designs for fmri Optimization of Designs for fmri UCLA Advanced Neuroimaging Summer School August 2, 2007 Thomas Liu, Ph.D. UCSD Center for Functional MRI Why optimize? Scans are expensive. Subjects can be difficult to

More information

University of California, Berkeley

University of California, Berkeley University of California, Berkeley U.C. Berkeley Division of Biostatistics Working Paper Series Year 2004 Paper 155 Estimation of Direct and Indirect Causal Effects in Longitudinal Studies Mark J. van

More information

Effective Connectivity & Dynamic Causal Modelling

Effective Connectivity & Dynamic Causal Modelling Effective Connectivity & Dynamic Causal Modelling Hanneke den Ouden Donders Centre for Cognitive Neuroimaging Radboud University Nijmegen Advanced SPM course Zurich, Februari 13-14, 2014 Functional Specialisation

More information

Data Analysis I: Single Subject

Data Analysis I: Single Subject Data Analysis I: Single Subject ON OFF he General Linear Model (GLM) y= X fmri Signal = Design Matrix our data = what we CAN explain x β x Betas + + how much x of it we CAN + explain ε Residuals what

More information

HST 583 FUNCTIONAL MAGNETIC RESONANCE IMAGING DATA ANALYSIS AND ACQUISITION A REVIEW OF STATISTICS FOR FMRI DATA ANALYSIS

HST 583 FUNCTIONAL MAGNETIC RESONANCE IMAGING DATA ANALYSIS AND ACQUISITION A REVIEW OF STATISTICS FOR FMRI DATA ANALYSIS HST 583 FUNCTIONAL MAGNETIC RESONANCE IMAGING DATA ANALYSIS AND ACQUISITION A REVIEW OF STATISTICS FOR FMRI DATA ANALYSIS EMERY N. BROWN AND CHRIS LONG NEUROSCIENCE STATISTICS RESEARCH LABORATORY DEPARTMENT

More information

Causal mediation analysis: Definition of effects and common identification assumptions

Causal mediation analysis: Definition of effects and common identification assumptions Causal mediation analysis: Definition of effects and common identification assumptions Trang Quynh Nguyen Seminar on Statistical Methods for Mental Health Research Johns Hopkins Bloomberg School of Public

More information

Testing for group differences in brain functional connectivity

Testing for group differences in brain functional connectivity Testing for group differences in brain functional connectivity Junghi Kim, Wei Pan, for ADNI Division of Biostatistics, School of Public Health, University of Minnesota, Minneapolis, MN 55455 Banff Feb

More information

Multivariate Regression Generalized Likelihood Ratio Tests for FMRI Activation

Multivariate Regression Generalized Likelihood Ratio Tests for FMRI Activation Multivariate Regression Generalized Likelihood Ratio Tests for FMRI Activation Daniel B Rowe Division of Biostatistics Medical College of Wisconsin Technical Report 40 November 00 Division of Biostatistics

More information

Casual Mediation Analysis

Casual Mediation Analysis Casual Mediation Analysis Tyler J. VanderWeele, Ph.D. Upcoming Seminar: April 21-22, 2017, Philadelphia, Pennsylvania OXFORD UNIVERSITY PRESS Explanation in Causal Inference Methods for Mediation and Interaction

More information

Revision list for Pearl s THE FOUNDATIONS OF CAUSAL INFERENCE

Revision list for Pearl s THE FOUNDATIONS OF CAUSAL INFERENCE Revision list for Pearl s THE FOUNDATIONS OF CAUSAL INFERENCE insert p. 90: in graphical terms or plain causal language. The mediation problem of Section 6 illustrates how such symbiosis clarifies the

More information

Inference With Interference Between Units in an f MRI Experiment of Motor Inhibition

Inference With Interference Between Units in an f MRI Experiment of Motor Inhibition University of Pennsylvania ScholarlyCommons Statistics Papers Wharton Faculty Research 2012 Inference With Interference Between Units in an f MRI Experiment of Motor Inhibition Xi Luo Dylan S. Small University

More information

New Procedures for False Discovery Control

New Procedures for False Discovery Control New Procedures for False Discovery Control Christopher R. Genovese Department of Statistics Carnegie Mellon University http://www.stat.cmu.edu/ ~ genovese/ Elisha Merriam Department of Neuroscience University

More information

Bayesian Analysis. Bayesian Analysis: Bayesian methods concern one s belief about θ. [Current Belief (Posterior)] (Prior Belief) x (Data) Outline

Bayesian Analysis. Bayesian Analysis: Bayesian methods concern one s belief about θ. [Current Belief (Posterior)] (Prior Belief) x (Data) Outline Bayesian Analysis DuBois Bowman, Ph.D. Gordana Derado, M. S. Shuo Chen, M. S. Department of Biostatistics and Bioinformatics Center for Biomedical Imaging Statistics Emory University Outline I. Introduction

More information

Contents. design. Experimental design Introduction & recap Experimental design «Take home» message. N εˆ. DISCOS SPM course, CRC, Liège, 2009

Contents. design. Experimental design Introduction & recap Experimental design «Take home» message. N εˆ. DISCOS SPM course, CRC, Liège, 2009 DISCOS SPM course, CRC, Liège, 2009 Contents Experimental design Introduction & recap Experimental design «Take home» message C. Phillips, Centre de Recherches du Cyclotron, ULg, Belgium Based on slides

More information

High-dimensional Multivariate Mediation with Application to Neuroimaging Data

High-dimensional Multivariate Mediation with Application to Neuroimaging Data High-dimensional Multivariate Mediation with Application to Neuroimaging Data arxiv:1511.09354v2 [stat.me] 5 Sep 2016 Oliver Y. Chén 1, Ciprian M. Crainiceanu 1, Elizabeth L. Ogburn 1, Brian S. Caffo 1,

More information

Neuroimaging for Machine Learners Validation and inference

Neuroimaging for Machine Learners Validation and inference GIGA in silico medicine, ULg, Belgium http://www.giga.ulg.ac.be Neuroimaging for Machine Learners Validation and inference Christophe Phillips, Ir. PhD. PRoNTo course June 2017 Univariate analysis: Introduction:

More information

The General Linear Model. Guillaume Flandin Wellcome Trust Centre for Neuroimaging University College London

The General Linear Model. Guillaume Flandin Wellcome Trust Centre for Neuroimaging University College London The General Linear Model Guillaume Flandin Wellcome Trust Centre for Neuroimaging University College London SPM Course Lausanne, April 2012 Image time-series Spatial filter Design matrix Statistical Parametric

More information

Causal modeling of fmri: temporal precedence and spatial exploration

Causal modeling of fmri: temporal precedence and spatial exploration Causal modeling of fmri: temporal precedence and spatial exploration Alard Roebroeck Maastricht Brain Imaging Center (MBIC) Faculty of Psychology & Neuroscience Maastricht University Intro: What is Brain

More information

Package gma. September 19, 2017

Package gma. September 19, 2017 Type Package Title Granger Mediation Analysis Version 1.0 Date 2018-08-23 Package gma September 19, 2017 Author Yi Zhao , Xi Luo Maintainer Yi Zhao

More information

Contents. Introduction The General Linear Model. General Linear Linear Model Model. The General Linear Model, Part I. «Take home» message

Contents. Introduction The General Linear Model. General Linear Linear Model Model. The General Linear Model, Part I. «Take home» message DISCOS SPM course, CRC, Liège, 2009 Contents The General Linear Model, Part I Introduction The General Linear Model Data & model Design matrix Parameter estimates & interpretation Simple contrast «Take

More information

SUPPLEMENTARY APPENDICES FOR WAVELET-DOMAIN REGRESSION AND PREDICTIVE INFERENCE IN PSYCHIATRIC NEUROIMAGING

SUPPLEMENTARY APPENDICES FOR WAVELET-DOMAIN REGRESSION AND PREDICTIVE INFERENCE IN PSYCHIATRIC NEUROIMAGING Submitted to the Annals of Applied Statistics SUPPLEMENTARY APPENDICES FOR WAVELET-DOMAIN REGRESSION AND PREDICTIVE INFERENCE IN PSYCHIATRIC NEUROIMAGING By Philip T. Reiss, Lan Huo, Yihong Zhao, Clare

More information

Stochastic Dynamic Causal Modelling for resting-state fmri

Stochastic Dynamic Causal Modelling for resting-state fmri Stochastic Dynamic Causal Modelling for resting-state fmri Ged Ridgway, FIL, Wellcome Trust Centre for Neuroimaging, UCL Institute of Neurology, London Overview Connectivity in the brain Introduction to

More information

13.1 Causal effects with continuous mediator and. predictors in their equations. The definitions for the direct, total indirect,

13.1 Causal effects with continuous mediator and. predictors in their equations. The definitions for the direct, total indirect, 13 Appendix 13.1 Causal effects with continuous mediator and continuous outcome Consider the model of Section 3, y i = β 0 + β 1 m i + β 2 x i + β 3 x i m i + β 4 c i + ɛ 1i, (49) m i = γ 0 + γ 1 x i +

More information

Investigating mediation when counterfactuals are not metaphysical: Does sunlight exposure mediate the effect of eye-glasses on cataracts?

Investigating mediation when counterfactuals are not metaphysical: Does sunlight exposure mediate the effect of eye-glasses on cataracts? Investigating mediation when counterfactuals are not metaphysical: Does sunlight exposure mediate the effect of eye-glasses on cataracts? Brian Egleston Fox Chase Cancer Center Collaborators: Daniel Scharfstein,

More information

Joint Modeling of Longitudinal Item Response Data and Survival

Joint Modeling of Longitudinal Item Response Data and Survival Joint Modeling of Longitudinal Item Response Data and Survival Jean-Paul Fox University of Twente Department of Research Methodology, Measurement and Data Analysis Faculty of Behavioural Sciences Enschede,

More information

Peak Detection for Images

Peak Detection for Images Peak Detection for Images Armin Schwartzman Division of Biostatistics, UC San Diego June 016 Overview How can we improve detection power? Use a less conservative error criterion Take advantage of prior

More information

Lecture 4 Multiple linear regression

Lecture 4 Multiple linear regression Lecture 4 Multiple linear regression BIOST 515 January 15, 2004 Outline 1 Motivation for the multiple regression model Multiple regression in matrix notation Least squares estimation of model parameters

More information

Unbalanced Designs & Quasi F-Ratios

Unbalanced Designs & Quasi F-Ratios Unbalanced Designs & Quasi F-Ratios ANOVA for unequal n s, pooled variances, & other useful tools Unequal nʼs Focus (so far) on Balanced Designs Equal n s in groups (CR-p and CRF-pq) Observation in every

More information

Detecting fmri activation allowing for unknown latency of the hemodynamic response

Detecting fmri activation allowing for unknown latency of the hemodynamic response Detecting fmri activation allowing for unknown latency of the hemodynamic response K.J. Worsley McGill University J.E. Taylor Stanford University January 7, 006 Abstract Several authors have suggested

More information

Dynamic Data Modeling, Recognition, and Synthesis. Rui Zhao Thesis Defense Advisor: Professor Qiang Ji

Dynamic Data Modeling, Recognition, and Synthesis. Rui Zhao Thesis Defense Advisor: Professor Qiang Ji Dynamic Data Modeling, Recognition, and Synthesis Rui Zhao Thesis Defense Advisor: Professor Qiang Ji Contents Introduction Related Work Dynamic Data Modeling & Analysis Temporal localization Insufficient

More information

Contrasts and Classical Inference

Contrasts and Classical Inference Elsevier UK Chapter: Ch9-P3756 8-7-6 7:p.m. Page:6 Trim:7.5in 9.5in C H A P T E R 9 Contrasts and Classical Inference J. Poline, F. Kherif, C. Pallier and W. Penny INTRODUCTION The general linear model

More information

The Harvard community has made this article openly available. Please share how this access benefits you. Your story matters

The Harvard community has made this article openly available. Please share how this access benefits you. Your story matters Sensitivity Analysis for Linear Structural Equation Models, Longitudinal Mediation With Latent Growth Models and Blended Learning in Biostatistics Education The Harvard community has made this article

More information

EXISTENCE OF NEUTRAL STOCHASTIC FUNCTIONAL DIFFERENTIAL EQUATIONS WITH ABSTRACT VOLTERRA OPERATORS

EXISTENCE OF NEUTRAL STOCHASTIC FUNCTIONAL DIFFERENTIAL EQUATIONS WITH ABSTRACT VOLTERRA OPERATORS International Journal of Differential Equations and Applications Volume 7 No. 1 23, 11-17 EXISTENCE OF NEUTRAL STOCHASTIC FUNCTIONAL DIFFERENTIAL EQUATIONS WITH ABSTRACT VOLTERRA OPERATORS Zephyrinus C.

More information

Confidence Thresholds and False Discovery Control

Confidence Thresholds and False Discovery Control Confidence Thresholds and False Discovery Control Christopher R. Genovese Department of Statistics Carnegie Mellon University http://www.stat.cmu.edu/ ~ genovese/ Larry Wasserman Department of Statistics

More information

An Approximate Test for Homogeneity of Correlated Correlation Coefficients

An Approximate Test for Homogeneity of Correlated Correlation Coefficients Quality & Quantity 37: 99 110, 2003. 2003 Kluwer Academic Publishers. Printed in the Netherlands. 99 Research Note An Approximate Test for Homogeneity of Correlated Correlation Coefficients TRIVELLORE

More information

Modelling temporal structure (in noise and signal)

Modelling temporal structure (in noise and signal) Modelling temporal structure (in noise and signal) Mark Woolrich, Christian Beckmann*, Salima Makni & Steve Smith FMRIB, Oxford *Imperial/FMRIB temporal noise: modelling temporal autocorrelation temporal

More information

6. Regularized linear regression

6. Regularized linear regression Foundations of Machine Learning École Centrale Paris Fall 2015 6. Regularized linear regression Chloé-Agathe Azencot Centre for Computational Biology, Mines ParisTech chloe agathe.azencott@mines paristech.fr

More information

Discussion of Papers on the Extensions of Propensity Score

Discussion of Papers on the Extensions of Propensity Score Discussion of Papers on the Extensions of Propensity Score Kosuke Imai Princeton University August 3, 2010 Kosuke Imai (Princeton) Generalized Propensity Score 2010 JSM (Vancouver) 1 / 11 The Theme and

More information

Introduction to functional MRI in humans. Michael Hallquist University of Pittsburgh

Introduction to functional MRI in humans. Michael Hallquist University of Pittsburgh Introduction to functional MRI in humans Michael Hallquist University of Pittsburgh Goals of human neuroimaging Localization of brain function (mapping) Understanding large-scale functional integration

More information

ROI analysis of pharmafmri data: an adaptive approach for global testing

ROI analysis of pharmafmri data: an adaptive approach for global testing ROI analysis of pharmafmri data: an adaptive approach for global testing Giorgos Minas, John A.D. Aston, Thomas E. Nichols and Nigel Stallard Abstract Pharmacological fmri (pharmafmri) is a new highly

More information

Analysis of Longitudinal Data. Patrick J. Heagerty PhD Department of Biostatistics University of Washington

Analysis of Longitudinal Data. Patrick J. Heagerty PhD Department of Biostatistics University of Washington Analysis of Longitudinal Data Patrick J Heagerty PhD Department of Biostatistics University of Washington Auckland 8 Session One Outline Examples of longitudinal data Scientific motivation Opportunities

More information

Data Mining Stat 588

Data Mining Stat 588 Data Mining Stat 588 Lecture 02: Linear Methods for Regression Department of Statistics & Biostatistics Rutgers University September 13 2011 Regression Problem Quantitative generic output variable Y. Generic

More information

Tests for separability in nonparametric covariance operators of random surfaces

Tests for separability in nonparametric covariance operators of random surfaces Tests for separability in nonparametric covariance operators of random surfaces Shahin Tavakoli (joint with John Aston and Davide Pigoli) April 19, 2016 Analysis of Multidimensional Functional Data Shahin

More information

Supplementary Information. Brain networks involved in tactile speed classification of moving dot patterns: the. effects of speed and dot periodicity

Supplementary Information. Brain networks involved in tactile speed classification of moving dot patterns: the. effects of speed and dot periodicity Supplementary Information Brain networks involved in tactile speed classification of moving dot patterns: the effects of speed and dot periodicity Jiajia Yang, Ryo Kitada *, Takanori Kochiyama, Yinghua

More information

A hierarchical group ICA model for assessing covariate effects on brain functional networks

A hierarchical group ICA model for assessing covariate effects on brain functional networks A hierarchical group ICA model for assessing covariate effects on brain functional networks Ying Guo Joint work with Ran Shi Department of Biostatistics and Bioinformatics Emory University 06/03/2013 Ying

More information

Spectral Graph Wavelets on the Cortical Connectome and Regularization of the EEG Inverse Problem

Spectral Graph Wavelets on the Cortical Connectome and Regularization of the EEG Inverse Problem Spectral Graph Wavelets on the Cortical Connectome and Regularization of the EEG Inverse Problem David K Hammond University of Oregon / NeuroInformatics Center International Conference on Industrial and

More information

HHS Public Access Author manuscript Brain Inform Health (2015). Author manuscript; available in PMC 2016 January 01.

HHS Public Access Author manuscript Brain Inform Health (2015). Author manuscript; available in PMC 2016 January 01. GN-SCCA: GraphNet based Sparse Canonical Correlation Analysis for Brain Imaging Genetics Lei Du 1, Jingwen Yan 1, Sungeun Kim 1, Shannon L. Risacher 1, Heng Huang 2, Mark Inlow 3, Jason H. Moore 4, Andrew

More information

Optimal design for event-related functional magnetic resonance imaging considering both individual stimulus effects and pairwise contrasts

Optimal design for event-related functional magnetic resonance imaging considering both individual stimulus effects and pairwise contrasts Statistics and Applications Volume 6, Nos1 & 2, 2008 (New Series), pp 235-256 Optimal design for event-related functional magnetic resonance imaging considering both individual stimulus effects and pairwise

More information

Extending causal inferences from a randomized trial to a target population

Extending causal inferences from a randomized trial to a target population Extending causal inferences from a randomized trial to a target population Issa Dahabreh Center for Evidence Synthesis in Health, Brown University issa dahabreh@brown.edu January 16, 2019 Issa Dahabreh

More information

Multilevel Analysis, with Extensions

Multilevel Analysis, with Extensions May 26, 2010 We start by reviewing the research on multilevel analysis that has been done in psychometrics and educational statistics, roughly since 1985. The canonical reference (at least I hope so) is

More information

Weighted MCID: Estimation and Statistical Inference

Weighted MCID: Estimation and Statistical Inference Weighted MCID: Estimation and Statistical Inference Jiwei Zhao, PhD Department of Biostatistics SUNY Buffalo JSM 2018 Vancouver, Canada July 28 August 2, 2018 Joint Work with Zehua Zhou and Leslie Bisson

More information

An Implementation of Dynamic Causal Modelling

An Implementation of Dynamic Causal Modelling An Implementation of Dynamic Causal Modelling Christian Himpe 24.01.2011 Overview Contents: 1 Intro 2 Model 3 Parameter Estimation 4 Examples Motivation Motivation: How are brain regions coupled? Motivation

More information

Computationally Efficient Estimation of Multilevel High-Dimensional Latent Variable Models

Computationally Efficient Estimation of Multilevel High-Dimensional Latent Variable Models Computationally Efficient Estimation of Multilevel High-Dimensional Latent Variable Models Tihomir Asparouhov 1, Bengt Muthen 2 Muthen & Muthen 1 UCLA 2 Abstract Multilevel analysis often leads to modeling

More information

Causal Effect Estimation Under Linear and Log- Linear Structural Nested Mean Models in the Presence of Unmeasured Confounding

Causal Effect Estimation Under Linear and Log- Linear Structural Nested Mean Models in the Presence of Unmeasured Confounding University of Pennsylvania ScholarlyCommons Publicly Accessible Penn Dissertations Summer 8-13-2010 Causal Effect Estimation Under Linear and Log- Linear Structural Nested Mean Models in the Presence of

More information

Scaling in Neurosciences: State-of-the-art

Scaling in Neurosciences: State-of-the-art Spatially regularized multifractal analysis for fmri Data Motivation Scaling in Neurosciences: State-of-the-art Motivation Multifractal Multifractal Princeton Experiment Princeton Experimen Van Gogh P.

More information

Basic MRI physics and Functional MRI

Basic MRI physics and Functional MRI Basic MRI physics and Functional MRI Gregory R. Lee, Ph.D Assistant Professor, Department of Radiology June 24, 2013 Pediatric Neuroimaging Research Consortium Objectives Neuroimaging Overview MR Physics

More information

Recipes for the Linear Analysis of EEG and applications

Recipes for the Linear Analysis of EEG and applications Recipes for the Linear Analysis of EEG and applications Paul Sajda Department of Biomedical Engineering Columbia University Can we read the brain non-invasively and in real-time? decoder 1001110 if YES

More information

醫用磁振學 MRM 擴散張量影像 擴散張量影像原理. 本週課程內容 MR Diffusion 擴散張量造影原理 擴散張量造影應用 盧家鋒助理教授國立陽明大學生物醫學影像暨放射科學系

醫用磁振學 MRM 擴散張量影像 擴散張量影像原理. 本週課程內容   MR Diffusion 擴散張量造影原理 擴散張量造影應用 盧家鋒助理教授國立陽明大學生物醫學影像暨放射科學系 本週課程內容 http://www.ym.edu.tw/~cflu 擴散張量造影原理 擴散張量造影應用 醫用磁振學 MRM 擴散張量影像 盧家鋒助理教授國立陽明大學生物醫學影像暨放射科學系 alvin4016@ym.edu.tw MRI The Basics (3rd edition) Chapter 22: Echo Planar Imaging MRI in Practice, (4th edition)

More information

Bayesian Treatments of. Neuroimaging Data Will Penny and Karl Friston. 5.1 Introduction

Bayesian Treatments of. Neuroimaging Data Will Penny and Karl Friston. 5.1 Introduction Bayesian Treatments of 5 Neuroimaging Data Will Penny and Karl Friston 5.1 Introduction In this chapter we discuss the application of Bayesian methods to neuroimaging data. This includes data from positron

More information

Spatial Bayesian Variable Selection Models on Functional Magnetic Resonance Imaging Time-Series Data

Spatial Bayesian Variable Selection Models on Functional Magnetic Resonance Imaging Time-Series Data Spatial Bayesian Variable Selection Models on Functional Magnetic Resonance Imaging Time-Series Data Kuo-Jung Lee Department of Statistics National Cheng Kung University kjlee@stat.ncku.edu.tw Brian S.

More information

A Selective Review of Sufficient Dimension Reduction

A Selective Review of Sufficient Dimension Reduction A Selective Review of Sufficient Dimension Reduction Lexin Li Department of Statistics North Carolina State University Lexin Li (NCSU) Sufficient Dimension Reduction 1 / 19 Outline 1 General Framework

More information

EEG/MEG Inverse Solution Driven by fmri

EEG/MEG Inverse Solution Driven by fmri EEG/MEG Inverse Solution Driven by fmri Yaroslav Halchenko CS @ NJIT 1 Functional Brain Imaging EEG ElectroEncephaloGram MEG MagnetoEncephaloGram fmri Functional Magnetic Resonance Imaging others 2 Functional

More information

arxiv: v2 [stat.ml] 13 Apr 2014

arxiv: v2 [stat.ml] 13 Apr 2014 Estimating Time-varying Brain Connectivity Networks from Functional MRI Time Series arxiv:1310.3863v2 [stat.ml] 13 Apr 2014 Ricardo Pio Monti 1, Peter Hellyer 2, David Sharp 2, Robert Leech 2, Christoforos

More information

Experimental Design. Rik Henson. With thanks to: Karl Friston, Andrew Holmes

Experimental Design. Rik Henson. With thanks to: Karl Friston, Andrew Holmes Experimental Design Rik Henson With thanks to: Karl Friston, Andrew Holmes Overview 1. A Taxonomy of Designs 2. Epoch vs Event-related 3. Mixed Epoch/Event Designs A taxonomy of design Categorical designs

More information

Joint Estimation of Multiple Graphical Models from High Dimensional Time Series

Joint Estimation of Multiple Graphical Models from High Dimensional Time Series Joint Estimation of Multiple Graphical Models from High Dimensional Time Series Huitong Qiu, Fang Han, Han Liu, and Brian Caffo arxiv:1311.0219v2 [stat.ml] 8 Oct 2014 October 8, 2014 Abstract In this manuscript

More information

FIL. Event-related. fmri. Rik Henson. With thanks to: Karl Friston, Oliver Josephs

FIL. Event-related. fmri. Rik Henson. With thanks to: Karl Friston, Oliver Josephs Event-related fmri Rik Henson With thanks to: Karl Friston, Oliver Josephs Overview 1. BOLD impulse response 2. General Linear Model 3. Temporal Basis Functions 4. Timing Issues 5. Design Optimisation

More information

PhD Qualifying Examination Department of Statistics, University of Florida

PhD Qualifying Examination Department of Statistics, University of Florida PhD Qualifying xamination Department of Statistics, University of Florida January 24, 2003, 8:00 am - 12:00 noon Instructions: 1 You have exactly four hours to answer questions in this examination 2 There

More information

Statistical Analysis Aspects of Resting State Functional Connectivity

Statistical Analysis Aspects of Resting State Functional Connectivity Statistical Analysis Aspects of Resting State Functional Connectivity Biswal s result (1995) Correlations between RS Fluctuations of left and right motor areas Why studying resting state? Human Brain =

More information

Hierarchical Dirichlet Processes with Random Effects

Hierarchical Dirichlet Processes with Random Effects Hierarchical Dirichlet Processes with Random Effects Seyoung Kim Department of Computer Science University of California, Irvine Irvine, CA 92697-34 sykim@ics.uci.edu Padhraic Smyth Department of Computer

More information

Jean-Baptiste Poline

Jean-Baptiste Poline Edinburgh course Avril 2010 Linear Models Contrasts Variance components Jean-Baptiste Poline Neurospin, I2BM, CEA Saclay, France Credits: Will Penny, G. Flandin, SPM course authors Outline Part I: Linear

More information

Piotr Majer Risk Patterns and Correlated Brain Activities

Piotr Majer Risk Patterns and Correlated Brain Activities Alena My²i ková Piotr Majer Song Song Alena Myšičková Peter N. C. Mohr Peter N. C. Mohr Wolfgang K. Härdle Song Song Hauke R. Heekeren Wolfgang K. Härdle Hauke R. Heekeren C.A.S.E. Centre C.A.S.E. for

More information

Structural Nested Mean Models for Assessing Time-Varying Effect Moderation. Daniel Almirall

Structural Nested Mean Models for Assessing Time-Varying Effect Moderation. Daniel Almirall 1 Structural Nested Mean Models for Assessing Time-Varying Effect Moderation Daniel Almirall Center for Health Services Research, Durham VAMC & Dept. of Biostatistics, Duke University Medical Joint work

More information

Decoding conceptual representations

Decoding conceptual representations Decoding conceptual representations!!!! Marcel van Gerven! Computational Cognitive Neuroscience Lab (www.ccnlab.net) Artificial Intelligence Department Donders Centre for Cognition Donders Institute for

More information

SUPPLEMENTARY INFORMATION

SUPPLEMENTARY INFORMATION SUPPLEMENTARY INFORMATION 1. Supplementary Tables 2. Supplementary Figures 1/12 Supplementary tables TABLE S1 Response to Expected Value: Anatomical locations of regions correlating with the expected value

More information

Causal Inference for Complex Longitudinal Data: The Continuous Time g-computation Formula

Causal Inference for Complex Longitudinal Data: The Continuous Time g-computation Formula Causal Inference for Complex Longitudinal Data: The Continuous Time g-computation Formula Richard D. Gill Mathematical Institute, University of Utrecht, Netherlands EURANDOM, Eindhoven, Netherlands November

More information

The General Linear Model (GLM)

The General Linear Model (GLM) The General Linear Model (GLM) Dr. Frederike Petzschner Translational Neuromodeling Unit (TNU) Institute for Biomedical Engineering, University of Zurich & ETH Zurich With many thanks for slides & images

More information

Diffusion Tensor Imaging (DTI): An overview of key concepts

Diffusion Tensor Imaging (DTI): An overview of key concepts Diffusion Tensor Imaging (DTI): An overview of key concepts (Supplemental material for presentation) Prepared by: Nadia Barakat BMB 601 Chris Conklin Thursday, April 8 th 2010 Diffusion Concept [1,2]:

More information