Skip to contents

CRAN_Status_Badge metacran downloads

This vignette introduces conditional average treatment effects and CATE scores for binary, count and survival outcomes. The detailed derivations below focus on count and survival outcomes; the binary CATE example illustrates binary score fitting and validation. For population-average effects, see Methods for estimating average treatment effects.

What is a CATE score?

A conditional average treatment effect (CATE) compares outcomes under two treatments among patients with the same measured baseline covariates. For a binary outcome, precmed uses the conditional risk difference: predicted risk under treatment 1 minus predicted risk under treatment 0. For a count outcome, the score is a conditional log rate ratio. For survival, it is a conditional log ratio of restricted mean time lost up to the chosen horizon. Ratios compare treatment 1 with treatment 0. These are averages conditional on measured characteristics, not the unobservable effect for an individual patient.

A CATE score is an estimate of such a conditional contrast. It can be used to rank patients, with the favorable direction depending on the outcome and the treatment contrast. A causal interpretation requires assumptions such as consistency, no unmeasured treatment–outcome confounding given the measured covariates, and adequate treatment overlap, as well as the assumptions of the chosen estimator. Survival analyses also require appropriate censoring assumptions and support at the selected horizon.

How are the scores fitted?

A T-learner fits an outcome model separately in each treatment arm and contrasts their predictions at the same covariate values. For a binary outcome, separate logistic outcome models give a fitted risk-difference score by subtracting the predicted event risk under treatment 0 from that under treatment 1. This score uses the outcome predictions alone. For binary outcomes, catefit() combines outcome predictions and propensity scores from the treatment model to obtain doubly robust estimates of the average risk difference within each score-defined subgroup.

Use outcome_model to specify baseline covariates and terms that let each arm-specific model adequately estimate the conditional outcome and capture variation in the treatment contrast. For binary outcomes, the risk difference can vary with baseline risk even when the treatment odds ratio is constant (Hoogland et al. 2021). A causal interpretation of the T-learner score in observational data requires consistency, treatment overlap, and a set of covariates in the outcome models that suffices to control treatment–outcome confounding. Chapter 17 discusses CATE prediction and its identification assumptions (Hoogland et al. 2026). The fitted scores are fixed before subgroup estimation, so propensity-score adjustment at that stage cannot repair bias in the scores due to omitted effect modifiers, misspecified outcome models, or unmeasured confounding.

An S-learner, by contrast, fits a single outcome model that includes treatment as a predictor, and compares predictions under the two treatment values. The S-learner is described here for context; it is not a selectable CATE score method in the current precmed interface.

The package also implements two-regression and contrast-regression scores. These use cross-fitted initial outcome predictions and a treatment model that estimates propensity scores, followed by different procedures for estimating the score. Their doubly robust properties depend on the estimator’s assumptions and are not the same as a guarantee for a direct T-learner score. For survival outcomes, the censoring model supplies probabilities used for IPCW; treatment-model double robustness does not protect against a misspecified censoring model. The count and survival sections below describe the methods in more detail.

Why validate a score?

catefit() fits scores and estimates effects in score-defined subgroups using the same data. Those subgroup estimates are useful for exploring a fit, but they do not independently validate it. catecv() fits scores on training splits and evaluates score-defined groups on held-out splits, providing an internal assessment. Comparing or selecting methods using those results still benefits from an independent assessment. See the validation section below and the binary, count and survival CATE examples for the available procedures.

Background and further reading

A CATE describes the average treatment effect among patients with the same measured baseline characteristics; it does not identify an individual patient’s unobservable treatment effect. Chapter 17 of Debray et al. (2026) introduces the principles of treatment effect prediction, model development in randomized and non-randomized data, and the assumptions needed to identify CATEs (Hoogland et al. 2026).

Chapter 5 introduces marginal and conditional causal effects (Nguyen et al. 2026).

The primary methodological reference for the two-regression and contrast-regression estimators is Yadlowsky et al. (2021). For practical guidance on interpreting and evaluating the resulting scores, the book provides two complementary chapters:

  • Chapter 19: Validation of prediction models for patient outcomes and individualized treatment effect discusses validation strategies, discrimination, calibration, and decision accuracy (Thao et al. 2026).
  • Chapter 20: Visualization and interpretation of individualized treatment rule results discusses treatment rules, value functions, validation curves, and responder diagnostics, including examples using precmed (Jiang et al. 2026).

Development of CATE scores for count outcomes

For count outcomes, the CATE score is expressed as a log-rate ratio conditional on baseline covariates. It can be estimated with boosting, Poisson regression, negative binomial regression, or the doubly robust two-regression and contrast-regression estimators (Yadlowsky et al. 2021). The two-regression approach models the potential outcomes separately by treatment group, whereas contrast regression directly models the treatment contrast.

Assume that the following data are recorded for each of nn observations:

  • RR is a binary treatment taking value 0 or 1.
  • 𝐗\boldsymbol{X} is a vector of pp baseline covariates.
  • YY is a count outcome.
  • TT is the exposure time during which YY is recorded. It can vary across observations.

The objective is to estimate the ratio-based CATE score defined as

CATE(𝐱)=log(𝔼[Y(1)|𝐗=𝐱,T=1]𝔼[Y(0)|𝐗=𝐱,T=1])CATE(\boldsymbol{x})=\text{log}\left(\frac{\mathbb{E}[Y^{(1)}|\boldsymbol{X}=\boldsymbol{x},T=1]}{\mathbb{E}[Y^{(0)}|\boldsymbol{X}=\boldsymbol{x},T=1]}\right) where Y(r)Y^{(r)} is the potential outcome if the patient received the treatment r∈{0,1}r \in \{0,1\}. CATE(𝐱)CATE(\boldsymbol{x}) is interpreted as the individualized log-rate ratio of treatment 1 over treatment 0 conditional on the baseline covariates.

The package offers 5 methods to estimate the CATE score: Poisson regression, negative binomial regression, boosting, two regressions, and contrast regression.

Poisson

  1. Estimate the conditional mean outcome given baseline covariates and log-transformed exposure time as the offset separately in each treatment group (i.e., log(𝔼[Y(r)|𝐱,t])=log⁡(t)+βr𝐱̃\text{log}(\mathbb{E}[Y^{(r)}|\boldsymbol{x},t])=\log(t)+\beta_r \boldsymbol{\tilde x} for r∈{0,1}r \in \{0,1\} where 𝐱̃\boldsymbol{\tilde x} is the xx with an intercept) with Poisson regression. Denote the prediction for one time unit as Ŷ(r)(𝐱,1)=exp(β̂r𝐱̃)\hat Y^{(r)}(\boldsymbol{x},1)=\text{exp}(\hat \beta_r \boldsymbol{\tilde x}).

  2. The CATE score with Poisson is the plug-in estimator

CATÊPoisson(𝐱)=log(Ŷ(1)(𝐱,1)Ŷ(0)(𝐱,1))\hat{CATE}_{Poisson}(\boldsymbol{x})=\text{log}\left(\frac{\hat Y^{(1)}(\boldsymbol{x},1)}{\hat Y^{(0)}(\boldsymbol{x},1)}\right)

Negative binomial

Follow the same step as in Poisson but replace Poisson regression with negative binomial regression in step 1.

Boosting

Gradient boosting builds an additive prediction model using sequentially fitted learners (Friedman 2001).

  1. Estimate the conditional mean outcome given baseline covariates and log-transformed exposure time as the offset separately in each treatment group (i.e., 𝔼[Y(r)|𝐱,t]\mathbb{E}[Y^{(r)}|\boldsymbol{x},t] for r∈{0,1}r \in \{0,1\}) with Poisson-based gradient boosting regression method. Denote the prediction for one time unit as Ŷ(r)(𝐱,1)\hat Y^{(r)}(\boldsymbol{x},1).

    • The base learners are regression trees with depth specified with the argument tree.depth in catecvcount() and catefitcount(). Default is 2.
    • The number of trees in boosting is selected via cross-validation with a maximum number of trees specificed with the argument n.trees.boosting in catecvcount() and catefitcount(). Default is 200.
  2. The CATE score with boosting is the plug-in estimator

CATÊboosting(𝐱)=log(Ŷ(1)(𝐱,1)Ŷ(0)(𝐱,1))\hat{CATE}_{boosting}(\boldsymbol{x})=\text{log}\left(\frac{\hat Y^{(1)}(\boldsymbol{x},1)}{\hat Y^{(0)}(\boldsymbol{x},1)}\right)

Two regressions

The procedure adapts the ratio-based estimator of Yadlowsky et al. (2021) to count outcomes. Split the observations into treatment-stratified folds DkD_k. For each fold, fit the initial outcome and treatment models on D−kD_{-k} and predict the held-out observations in DkD_k. Pool these out-of-fold predictions, denoting each patient’s arm-specific predicted rate by mrim_{ri} and propensity for the observed arm by prip_{ri}.

For each arm rr, fit a weighted Poisson regression of the observed rate Yi/TiY_i/T_i on log⁡(mri)\log(m_{ri}) and x̃i\tilde x_i, with weight I(Ri=r)/priI(R_i=r)/p_{ri}. Predict the resulting mean qriq_{ri} for every observation, and fit a second unweighted Poisson regression of qriq_{ri} on x̃i\tilde x_i. Denote the resulting coefficients by β̂r\hat\beta_r. The score is

CATÊtworeg(𝐱)=(β̂1−β̂0)Tx̃.\widehat{CATE}_{tworeg}(\boldsymbol{x})=(\hat\beta_1-\hat\beta_0)^T\tilde x.

Repeat the procedure BB times with new random fold assignments and average the coefficient differences. These are repeated cross-fitting splits, not bootstrap samples.

Contrast regression

The contrast estimator uses the same held-out predictions and repeated fold assignments (Yadlowsky et al. 2021). Write ηi=exp⁡(δTx̃i)\eta_i=\exp(\delta^T\tilde x_i), πi\pi_i for the out-of-fold propensity for treatment 1, and m0i,m1im_{0i},m_{1i} for the out-of-fold rate predictions. The fitted score solves

∑ix̃iRi(Yi/Ti−(ηim0i+m1i)/2)(1−πi)−(1−Ri){ηiYi/Ti−(ηim0i+m1i)/2}πiηiπi+1−πi=0.\sum_i \tilde x_i\frac{R_i( Y_i/T_i-(\eta_i m_{0i}+m_{1i})/2)(1-\pi_i)-(1-R_i)\{\eta_iY_i/T_i-(\eta_i m_{0i}+m_{1i})/2\}\pi_i}{\eta_i\pi_i+1-\pi_i}=0.

The final score is δ̂Tx̃\hat\delta^T\tilde x. The coefficients are averaged across converged repetitions; if none converged, the coefficients from all repetitions are averaged. The equation is solved by Newton–Raphson, with numerical minimization as a fallback.

Development of CATE scores for survival outcomes

For survival outcomes, the CATE score is expressed as a log-ratio of restricted mean time lost conditional on baseline covariates. It can be estimated with random forest, boosting, Poisson regression, or adaptations of the doubly robust two-regression and contrast-regression approaches (Yadlowsky et al. 2021). Chapter 20 of the book also discusses restricted mean time lost as an outcome for ratio-based treatment effects (Jiang et al. 2026). For restricted mean event time regression using inverse probability of censoring weighting (IPCW), see Tian et al. (2014); the procedures below adapt these ideas to the RMTL treatment-effect setting.

Assume that the following data are recorded for each of nn observations:

  • RR is a binary treatment taking value 0 or 1.
  • 𝐗\boldsymbol{X} is a vector of pp baseline covariates.
  • TT is a survival time.
  • CC is a censoring time.
  • YY is the minimum between TT and CC.
  • δ\delta is an indicator taking value 1 if Y=TY = T and 0 otherwise.
  • τ\tau is a truncation time for restricted mean time lost.

The objective is to estimate the ratio-based CATE score defined as

CATE(𝐱)=log(𝔼[τ−(T(1)∧τ)|𝐗=𝐱]𝔼[τ−(T(0)∧τ)|𝐗=𝐱])CATE(\boldsymbol{x})=\text{log}\left(\frac{\mathbb{E}[\tau - (T^{(1)} \wedge\tau)|\boldsymbol{X}=\boldsymbol{x}]}{\mathbb{E}[\tau - (T^{(0)} \wedge\tau)|\boldsymbol{X}=\boldsymbol{x}]}\right)

where T(r)T^{(r)} is the potential survival time if the patient received the treatment r∈{0,1}r \in \{0,1\}. CATE(𝐱)CATE(\boldsymbol{x}) is interpreted as the individualized logarithm restricted mean time lost (RMTL) ratio of treatment 1 over treatment 0 conditional on the baseline covariates.

The package offers 5 methods to estimate the CATE score: Poisson regression, random forest, boosting, two regressions, and contrast regression.

Poisson

  1. Estimate the conditional mean RMTL given baseline covariates separately in each treatment group (i.e., log(𝔼[τ−T∧τ|𝐱,r])=βr𝐱̃\text{log}(\mathbb{E}[\tau - T\wedge\tau|\boldsymbol{x}, r])=\beta_r \boldsymbol{\tilde x} for r∈{0,1}r \in \{0,1\} where 𝐱̃\boldsymbol{\tilde x} is the xx with an intercept) with Poisson regression weighted with IPCW. Denote the prediction as Ŷ(r)(𝐱)=exp(β̂r𝐱̃)\hat Y^{(r)}(\boldsymbol{x})=\text{exp}(\hat \beta_r \boldsymbol{\tilde x}).

  2. The CATE score with Poisson is the plug-in estimator

CATÊPoisson(𝐱)=log(Ŷ(1)(𝐱)Ŷ(0)(𝐱))=(β̂1−β̂0)𝐱̃\widehat{CATE}_{Poisson}(\boldsymbol{x})=\text{log}\left(\frac{\hat Y^{(1)}(\boldsymbol{x})}{\hat Y^{(0)}(\boldsymbol{x})}\right) = (\hat \beta_1 - \hat \beta_0) \boldsymbol{\tilde x}

Boosting

Within each treatment arm, the implementation fits IPCW-weighted Gaussian gradient boosting to the restricted survival time divided by τ\tau, followed by a weighted binomial GAM calibration of the predictions and covariates. It converts the resulting predicted restricted mean survival time to RMTL and takes the log ratio. Gradient boosting is described by Friedman (2001). tree.depth controls the boosting trees; n.trees.boosting is the maximum number of trees considered for cross-validation.

Random forest

Random survival forests extend random forests to right-censored data (Ishwaran et al. 2008). A forest is fitted separately in each treatment arm. The predicted survival curve is integrated to τ\tau to estimate RMST; subtracting that integral from τ\tau gives predicted RMTL L̂r(𝐱)\hat L_r(\boldsymbol{x}). The score is

CATÊrandomForest(𝐱)=log⁡(L̂1(𝐱)L̂0(𝐱)).\widehat{CATE}_{randomForest}(\boldsymbol{x})=\log\left(\frac{\hat L_1(\boldsymbol{x})}{\hat L_0(\boldsymbol{x})}\right).

n.trees.rf specifies the number of trees (default 1,000); it is not selected by cross-validation. Optional forest settings can be supplied through rf.control, for example list(mtry = 3, nodesize = 15). tree.depth applies to boosting; use rf.control$nodedepth to set a forest depth limit.

Two regressions

This procedure adapts the ratio-based two-regression approach of Yadlowsky et al. (2021) to survival outcomes, using IPCW for censoring (Tian et al. 2014). Let Ui=min⁡(Yi,τ)U_i=\min(Y_i,\tau) and Di*=I(Yi≥τ)+I(Yi<τ,δi=1)D_i^*=I(Y_i\geq\tau)+I(Y_i<\tau,\delta_i=1). The censoring model is fitted on the full data used for the fit. The weight is

wi=Di*max⁡{Ĝ(Ui∣Xi),𝚜𝚞𝚛𝚟.𝚖𝚒𝚗},w_i=\frac{D_i^*}{\max\{\hat G(U_i\mid X_i),\texttt{surv.min}\}},

normalized to have mean one, where Ĝ\hat G is the estimated probability of remaining uncensored. In catefit(), the censoring model defaults to the outcome-model covariates and treatment. Use censoring_model to specify a different formula.

Split the data into treatment-stratified folds. Fit arm-specific initial survival outcome models and a treatment model on each fold’s complement and predict its held-out observations. The initial model may use random survival forests, weighted Gaussian boosting followed by GAM calibration, or weighted logistic regression. Pool the out-of-fold predictions, cap predicted restricted survival time at 0.99τ0.99\tau, and convert it to predicted RMTL mrim_{ri}.

For each arm rr, fit a Poisson regression of τ−Ui\tau-U_i on log⁡(mri)\log(m_{ri}) and x̃i\tilde x_i, weighted by wiI(Ri=r)/priw_i I(R_i=r)/p_{ri}, where prip_{ri} is the out-of-fold propensity for that arm. Predict the fitted means for all observations and regress them on x̃i\tilde x_i with an unweighted Poisson regression. Denoting the resulting coefficients by β̂r\hat\beta_r, the score is (β̂1−β̂0)Tx̃(\hat\beta_1-\hat\beta_0)^T\tilde x.

The process is repeated for BB random fold assignments and the coefficient differences are averaged. These are repeated cross-fitting splits, not bootstrap samples.

Contrast regression

Use the same IPCW and out-of-fold predictions as above. The contrast-regression approach adapts Yadlowsky et al. (2021) to censored survival outcomes. Let zi=(τ−Ui)/τz_i=(\tau-U_i)/\tau, let mrim_{ri} denote the predicted RMTL divided by τ\tau, and write ηi=exp⁡(δTx̃i)\eta_i=\exp(\delta^T\tilde x_i). With πi\pi_i the out-of-fold propensity for treatment 1, the implementation solves

∑iwix̃iRi{zi−(ηim0i+m1i)/2}(1−πi)−(1−Ri){ηizi−(ηim0i+m1i)/2}πiηiπi+1−πi=0.\sum_i w_i\tilde x_i\frac{R_i\{z_i-(\eta_i m_{0i}+m_{1i})/2\}(1-\pi_i)-(1-R_i)\{\eta_i z_i-(\eta_i m_{0i}+m_{1i})/2\}\pi_i}{\eta_i\pi_i+1-\pi_i}=0.

The final score is δ̂Tx̃\hat\delta^T\tilde x. The coefficients are averaged across converged repetitions; if none converged, the coefficients from all repetitions are averaged. Newton–Raphson is used with numerical minimization as a fallback.

Validation of CATE scores

The following validation curves and ABC statistics apply to count and survival CATE scores supported by catecv(). They assess ranking of treatment benefit and are distinct from the bootstrap inference described in the ATE methods vignette.

Count outcomes

The ABC statistic summarizes the area between the validation curve and the overall ATE reference line (Zhao et al. 2013; Yadlowsky et al. 2021). Chapter 20 provides worked examples of these curves and their interpretation as responder diagnostics (Jiang et al. 2026). Validation curves and ABC assess how well a score ranks patients by treatment benefit. They do not, by themselves, establish calibration of the predicted CATEs or the clinical value of a treatment rule; Chapter 19 discusses these complementary aspects of validation (Thao et al. 2026).

For a single CV iteration, it is implemented in the training and validation sets separately as following:

Step 1. Calculate the ATE in the training or validation sets.

Step 2. Calculate the ATE in 100 nested subgroups based on the estimated CATE score and derive the corresponding validation curve. Subgroups are defined with 100 equally-spaced proportions from min(prop.cutoff) to max(prop.cutoff) to ensure that enough data points are available to build the validation curve.

Step 3. The ABC is calculated with auc() from utility.R using the natural cubic spline interpolation, which calculates the area between the horizontal line with y-intercept at the ATE calculated in step 1 over the range [min(prop.cutoff),max(prop.cutoff)] (y) and the validation curve calculated in step 2 (x).

The function plot() allows the user to combine validation curves from 2 or more CV iterations (i.e., cv.n > 1). There are 2 ways to combine the validation curves:

  1. The option combine=“median” takes the median of the ATEs across all CV iterations in step 1 and the median of the ATEs in the 100 nested subgroups in step 2.

  2. The option combine=“mean” takes the mean of the ATEs across all CV iterations in step 1 and the mean of the ATEs in the 100 nested subgroups in step 2.

In either case, the ABC calculations are carried out as in step 3 with the resulting x and y.

The figure below explains how the ABC is calculated with a simple schema. The ABC calculations are such that larger positive ABC values always indicate more treatment effect heterogeneity. This is implemented by considering separately the cases when larger or smaller outcomes are preferred.

  • If larger count outcomes are preferred (higher.y = TRUE, e.g., positive events like number of motor developmental milestones reached), a validation curve above the ATE line and decreasing towards that line is synonym with treatment effect heterogeneity (top left figure). However, sections of the validation curve below the ATE line indicate inability to capture treatment effect heterogeneity (bottom left figure). Hence, the ABC is defined by subtracting the areas below the ATE line (red) from the areas above the ATE line (green) such that larger positive ABC are preferred.

  • If smaller count outcomes are preferred (higher.y = FALSE, e.g., negative events like number of relapses), a validation curve below the ATE line and increasing towards that line is synonym with treatment effect heterogeneity (top right figure). However, sections of the validation curve above the ATE line indicate inability to capture treatment effect heterogeneity (bottom right figure). Hence, the ABC is defined by subtracting the areas above the ATE line (red) from the areas below the ATE line (green) such that larger positive ABC are preferred.

ABC calculation examples in relation with higher.y argument in catecv() and catefit(). Validation curves are represented with a blue line and the dashed line is the ATE

Survival outcomes

The ABC statistic summarizes the area between the validation curve and the overall ATE reference line (Zhao et al. 2013; Yadlowsky et al. 2021). Chapter 20 provides worked examples of these curves and their interpretation as responder diagnostics (Jiang et al. 2026). For a single CV iteration and a certain CATE score method, it is implemented as following in the training and validation sets separately:

Step 1. Calculate the ATE in the training or validation sets.

Step 2. Calculate the ATE in 100 nested subgroups and derive the corresponding validation curve. Subgroups are defined with 100 equally-spaced proportions from min(prop.cutoff) to max(prop.cutoff) to ensure that enough data points are available to build the validation curve.

Step 3. The ABC is calculated with auc() from utility.R using the natural cubic spline interpolation, which calculates the area between the horizontal line with y-intercept at the ATE calculated in step 1 (y) and the validation curve calculated in step 2 (x) over the range [min(prop.cutoff), max(prop.cutoff)].

The function plot() allows the user combining validation curves from 2 or more CV iterations (i.e., cv.n > 1). There are 2 ways to combine the validation curves:

  1. The option combine ="median" takes the median of the ATEs across all CV iterations in step 1 and the median of the ATEs in the 100 nested subgroups in step 2.

  2. The option combine ="mean" takes the mean of the ATEs across all CV iterations in step 1 and the mean of the ATEs in the 100 nested subgroups in step 2.

In either case, the ABC calculations are carried out as in step 3 with the resulting x and y.

The figure below explains how the ABC is calculated with a simple schema. The ABC calculations are such that larger positive ABC values always indicate more treatment effect heterogeneity. This is implemented by considering separately the cases when larger or smaller outcomes are preferred.

  • If smaller survival outcomes are preferred (higher.y = FALSE, e.g., time to a positive event like recovery), a validation curve above the ATE line which decreases towards it is synonym with treatment effect heterogeneity (top left figure). However, sections of the validation curve below the ATE line indicate inability to capture treatment effect heterogeneity (bottom left figure). Hence, the ABC is defined by subtracting the areas below the ATE line from the areas above the ATE line such that larger positive ABC are preferred.

  • If larger survival outcomes are preferred (higher.y = TRUE, e.g., time to a negative event like symptom onset), a validation curve (in blue) below the ATE line (dashed) which increases towards it is synonym with treatment effect heterogeneity (top right figure). However, sections of the validation curve above the ATE line indicate inability to capture treatment effect heterogeneity (bottom right figure). Hence, the ABC is defined by subtracting the areas above the ATE line (in red) from the areas below the ATE line (in green) such that larger positive ABC are preferred.

ABC calculation examples in relation with higher.y argument in catecv() and catefit(). Validation curves are represented with a blue line and the dashed line is the ATE.

References

Debray, Thomas P. A., Tri-Long Nguyen, and Robert W. Platt, eds. 2026. Comparative Effectiveness and Personalized Medicine Research Using Real-World Data. 1st ed. Chapman & Hall/CRC. https://doi.org/10.1201/9781003300809.
Friedman, Jerome H. 2001. “Greedy Function Approximation: A Gradient Boosting Machine.” The Annals of Statistics 29 (5): 1189–232. https://doi.org/10.1214/aos/1013203451.
Hoogland, Jeroen, Thomas P. A. Debray, Guillaume Desachy, and Tri-Long Nguyen. 2026. “Introduction to Methods for Personalizing Medicine.” Chap. 17 in Comparative Effectiveness and Personalized Medicine Research Using Real-World Data, edited by Thomas P. A. Debray, Tri-Long Nguyen, and Robert W. Platt. Chapman & Hall/CRC. https://doi.org/10.1201/9781003300809-17.
Hoogland, Jeroen, Joanna IntHout, Michail Belias, et al. 2021. “A Tutorial on Individualized Treatment Effect Prediction from Randomized Trials with a Binary Endpoint.” Statistics in Medicine 40 (26): 5961–81. https://doi.org/10.1002/sim.9154.
Ishwaran, Hemant, Udaya B. Kogalur, Eugene H. Blackstone, and Michael S. Lauer. 2008. “Random Survival Forests.” The Annals of Applied Statistics 2 (3): 841–60. https://doi.org/10.1214/08-AOAS169.
Jiang, Xiaotong, Gabrielle Simoneau, Fabio Pellegrini, Changyu Shen, Carl de Moor, and Lu Tian. 2026. “Visualization and Interpretation of Individualized Treatment Rule Results.” Chap. 20 in Comparative Effectiveness and Personalized Medicine Research Using Real-World Data, edited by Thomas P. A. Debray, Tri-Long Nguyen, and Robert W. Platt. Chapman & Hall/CRC. https://doi.org/10.1201/9781003300809-20.
Nguyen, Tri-Long, Jessica L. Rohmann, Tat Thang Vo, Robert W. Platt, and Thomas P. A. Debray. 2026. “Understanding and Defining Causal Effects.” Chap. 5 in Comparative Effectiveness and Personalized Medicine Research Using Real-World Data, edited by Thomas P. A. Debray, Tri-Long Nguyen, and Robert W. Platt. Chapman & Hall/CRC. https://doi.org/10.1201/9781003300809-5.
Thao, Le Thi Phuong, Orestis Efthimiou, Tibor V. Varga, Jeroen Hoogland, and Thomas P. A. Debray. 2026. “Validation of Prediction Models for Patient Outcomes and Individualized Treatment Effect.” Chap. 19 in Comparative Effectiveness and Personalized Medicine Research Using Real-World Data, edited by Thomas P. A. Debray, Tri-Long Nguyen, and Robert W. Platt. Chapman & Hall/CRC. https://doi.org/10.1201/9781003300809-19.
Tian, Lu, Lihui Zhao, and Lee-Jen Wei. 2014. “Predicting the Restricted Mean Event Time with the Subject’s Baseline Covariates in Survival Analysis.” Biostatistics 15 (2): 222–33. https://doi.org/10.1093/biostatistics/kxt050.
Yadlowsky, Steve, Fabio Pellegrini, Federica Lionetto, Stefan Braune, and Lu Tian. 2021. “Estimation and Validation of Ratio-Based Conditional Average Treatment Effects Using Observational Data.” Journal of the American Statistical Association 116 (533): 335–52. https://doi.org/10.1080/01621459.2020.1772080.
Zhao, Lihui, Lu Tian, Tianxi Cai, Brian Claggett, and Lee-Jen Wei. 2013. “Effectively Selecting a Target Population for a Future Comparative Study.” Journal of the American Statistical Association 108 (502): 527–39. https://doi.org/10.1080/01621459.2013.770705.