Sensitivity Analysis: Deficiency vs. E-values

library(causaldef)
set.seed(42)

n <- 500
U <- rnorm(n) # Unmeasured confounder
W <- 0.7 * U + rnorm(n, sd = 0.5) # Observed covariate
A <- rbinom(n, 1, plogis(0.5 * U)) # Treatment
Y <- 2 * A + 1.5 * U + rnorm(n) # Outcome (true effect = 2)

df <- data.frame(W = W, A = A, Y = Y)

spec <- causal_spec(df, "A", "Y", "W")
#> ✔ Created causal specification: n=500, 1 covariate(s)

def_results <- estimate_deficiency(
    spec,
    methods = c("unadjusted", "iptw"),
    n_boot = 100
)
#> ℹ Estimating deficiency: unadjusted
#> ℹ Estimating deficiency: iptw

print(def_results)
#> 
#> -- Deficiency Proxy Estimates (PS-TV) ------
#> 
#>      Method  Delta     SE               CI            Quality
#>  unadjusted 0.1115 0.0283 [0.0585, 0.1772] Insufficient (Red)
#>        iptw 0.0162 0.0091 [0.0055, 0.0364]  Excellent (Green)
#> Note: delta is a propensity-score TV proxy (overlap/balance diagnostic).
#> 
#> Best method: iptw (delta = 0.0162 )

frontier <- confounding_frontier(
    spec,
    alpha_range = c(-3, 3),
    gamma_range = c(-3, 3),
    grid_size = 40
)
#> ℹ Computing benchmarks for observed covariates...
#> ✔ Computed confounding frontier: 40x40 grid

plot(frontier)
#> Warning: The following aesthetics were dropped during statistical transformation: fill.
#> ℹ This can happen when ggplot fails to infer the correct grouping structure in
#>   the data.
#> ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
#>   variable into a factor?

bounds <- policy_regret_bound(def_results, utility_range = c(0, 10), method = "iptw")
#> ℹ Transfer penalty: 0.1619 (delta = 0.0162)
print(bounds)
#> 
#> -- Policy Regret Bounds -------------------------------------------------
#> 
#> * Deficiency delta: 0.0162 
#> * Delta mode: point 
#> * Delta method: iptw 
#> * Delta selection: pre-specified method 
#> * Utility range: [0, 10]
#> * Transfer penalty: 0.1619 (additive regret upper bound)
#> * Minimax floor: 0.0809 (worst-case lower bound)
#> 
#> Note: this is a plug-in bound using a deficiency proxy rather than an identified exact deficiency.
#> 
#> Interpretation: Transfer penalty is 1.6 % of utility range given delta

# Effect estimate
effect <- estimate_effect(def_results, target_method = "iptw")
print(effect)
#> 
#> -- Causal Effect Estimate ----------------------
#> Method:    iptw 
#> Type:      ATE 
#> Contrast:  1 vs 0 
#> Estimate:  2.1256

# For E-value calculation, we need to convert to risk ratio scale
# This is an approximation; exact E-values require binary outcomes
# Here we use the standardized effect size

# Assuming effect is on continuous scale, we can compute
# a pseudo-risk ratio via effect size transformation
effect_se <- 1 # Approximate SE (would be from bootstrap in practice)
effect_est <- effect$estimate
t_stat <- effect_est / effect_se

# Approximate conversion to OR (for conceptual illustration)
# Using Chinn's (2000) formula for approximate OR from mean difference
approx_or <- exp(effect_est / 1.81)

# E-value formula
if (approx_or > 1) {
    e_value <- approx_or + sqrt(approx_or * (approx_or - 1))
} else {
    e_value <- 1 / approx_or + sqrt(1 / approx_or * (1 / approx_or - 1))
}

cat(sprintf("
Approximate E-value: %.2f

Interpretation: To explain away the observed effect, an unmeasured
confounder would need a risk ratio of at least %.2f with both
treatment and outcome.
", e_value, e_value))
#> 
#> Approximate E-value: 5.93
#> 
#> Interpretation: To explain away the observed effect, an unmeasured
#> confounder would need a risk ratio of at least 5.93 with both
#> treatment and outcome.

# Add more covariates for benchmarking
df$W2 <- 0.3 * U + rnorm(n, sd = 0.8)
df$W3 <- 0.9 * U + rnorm(n, sd = 0.3)

spec_multi <- causal_spec(df, "A", "Y", c("W", "W2", "W3"))
#> ✔ Created causal specification: n=500, 3 covariate(s)

frontier_bench <- confounding_frontier(
    spec_multi,
    grid_size = 40
)
#> ℹ Computing benchmarks for observed covariates...
#> ✔ Computed confounding frontier: 40x40 grid

# Access benchmarks
if (!is.null(frontier_bench$benchmarks)) {
    print(frontier_bench$benchmarks)
}
#>        covariate       alpha     gamma        delta
#> W_std          W 0.082061386 1.2208028 0.0311942215
#> W_std1        W2 0.001412356 0.5199305 0.0002617089
#> W_std2        W3 0.109257973 1.4261294 0.0456469462

# Add negative control
df$Y_nc <- U + rnorm(n, sd = 0.5) # Affected by U, not by A

spec_full <- causal_spec(
    df, "A", "Y", c("W", "W2", "W3"),
    negative_control = "Y_nc"
)
#> ✔ Created causal specification: n=500, 3 covariate(s)

# Complete analysis
def_full <- estimate_deficiency(
    spec_full,
    methods = c("unadjusted", "iptw"),
    n_boot = 100
)
#> ℹ Estimating deficiency: unadjusted
#> ℹ Estimating deficiency: iptw

nc_full <- nc_diagnostic(spec_full, method = "iptw", n_boot = 100)
#> ℹ Using kappa = 1 (conservative). Consider domain-specific estimation or sensitivity analysis via kappa_range.
#> ✔ No evidence against causal assumptions (p = 0.74257 )

print(def_full)
#> 
#> -- Deficiency Proxy Estimates (PS-TV) ------
#> 
#>      Method  Delta     SE               CI            Quality
#>  unadjusted 0.1033 0.0233 [0.1016, 0.1825] Insufficient (Red)
#>        iptw 0.0204 0.0089  [0.016, 0.0482]  Excellent (Green)
#> Note: delta is a propensity-score TV proxy (overlap/balance diagnostic).
#> 
#> Best method: iptw (delta = 0.0204 )
print(nc_full)
#> 
#> -- Negative Control Diagnostic ----------------------------------------
#> 
#> * screening statistic (weighted corr): 0.0173 
#> * delta_NC (association proxy): 0.0173 
#> * delta bound (under kappa alignment): 0.0173 (kappa = 1 )
#> * screening p-value: 0.74257 
#> * screening method: weighted_permutation_correlation 
#> 
#> RESULT: NOT REJECTED. This is a screening result, not proof that confounding is absent.
#> NOTE: Your effect estimate must exceed the Noise Floor (delta_bound) to be meaningful.