diff --git a/src/importance.rs b/src/importance.rs
new file mode 100644
index 0000000..8590302
--- /dev/null
+++ b/src/importance.rs
@@ -0,0 +1,93 @@
+//! Parameter importance via Spearman rank correlation.
+
+/// Assign average ranks to a slice of `f64` values (handles ties).
+#[allow(clippy::cast_precision_loss, clippy::float_cmp)]
+pub(crate) fn rank(values: &[f64]) -> Vec<f64> {
+    let n = values.len();
+    let mut indexed: Vec<(usize, f64)> = values.iter().copied().enumerate().collect();
+    indexed.sort_by(|a, b| a.1.partial_cmp(&b.1).unwrap_or(core::cmp::Ordering::Equal));
+
+    let mut ranks = vec![0.0; n];
+    let mut i = 0;
+    while i < n {
+        // Find the run of tied values.
+        let mut j = i + 1;
+        while j < n && indexed[j].1 == indexed[i].1 {
+            j += 1;
+        }
+        // Average rank for the tie group (1-based ranks).
+        let avg = (i + 1..=j).sum::<usize>() as f64 / (j - i) as f64;
+        for item in &indexed[i..j] {
+            ranks[item.0] = avg;
+        }
+        i = j;
+    }
+    ranks
+}
+
+/// Pearson correlation coefficient on two equal-length slices.
+#[allow(clippy::cast_precision_loss)]
+fn pearson(x: &[f64], y: &[f64]) -> f64 {
+    let n = x.len() as f64;
+    let mean_x = x.iter().sum::<f64>() / n;
+    let mean_y = y.iter().sum::<f64>() / n;
+
+    let mut cov = 0.0;
+    let mut var_x = 0.0;
+    let mut var_y = 0.0;
+    for (xi, yi) in x.iter().zip(y.iter()) {
+        let dx = xi - mean_x;
+        let dy = yi - mean_y;
+        cov += dx * dy;
+        var_x += dx * dx;
+        var_y += dy * dy;
+    }
+
+    let denom = (var_x * var_y).sqrt();
+    if denom == 0.0 { 0.0 } else { cov / denom }
+}
+
+/// Spearman rank correlation (Pearson on ranks).
+pub(crate) fn spearman(x: &[f64], y: &[f64]) -> f64 {
+    pearson(&rank(x), &rank(y))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn rank_no_ties() {
+        let ranks = rank(&[30.0, 10.0, 20.0]);
+        assert_eq!(ranks, vec![3.0, 1.0, 2.0]);
+    }
+
+    #[test]
+    fn rank_with_ties() {
+        let ranks = rank(&[10.0, 20.0, 20.0, 30.0]);
+        assert_eq!(ranks, vec![1.0, 2.5, 2.5, 4.0]);
+    }
+
+    #[test]
+    fn perfect_positive_correlation() {
+        let x = vec![1.0, 2.0, 3.0, 4.0, 5.0];
+        let y = vec![2.0, 4.0, 6.0, 8.0, 10.0];
+        let r = spearman(&x, &y);
+        assert!((r - 1.0).abs() < 1e-10);
+    }
+
+    #[test]
+    fn perfect_negative_correlation() {
+        let x = vec![1.0, 2.0, 3.0, 4.0, 5.0];
+        let y = vec![10.0, 8.0, 6.0, 4.0, 2.0];
+        let r = spearman(&x, &y);
+        assert!((r + 1.0).abs() < 1e-10);
+    }
+
+    #[test]
+    fn zero_variance_returns_zero() {
+        let x = vec![5.0, 5.0, 5.0];
+        let y = vec![1.0, 2.0, 3.0];
+        assert!(spearman(&x, &y).abs() < f64::EPSILON);
+    }
+}
diff --git a/src/lib.rs b/src/lib.rs
index 2283d5d..4079fff 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -216,6 +216,7 @@ macro_rules! trace_debug {
 
 mod distribution;
 mod error;
+mod importance;
 mod kde;
 mod param;
 pub mod parameter;
diff --git a/src/study.rs b/src/study.rs
index a5d2dba..0875b94 100644
--- a/src/study.rs
+++ b/src/study.rs
@@ -1812,6 +1812,110 @@ where
     }
 }
 
+impl<V> Study<V>
+where
+    V: PartialOrd + Clone + Into<f64>,
+{
+    /// Computes parameter importance scores using Spearman rank correlation.
+    ///
+    /// For each parameter, the absolute Spearman correlation between its values
+    /// and the objective values is computed across all completed trials. Scores
+    /// are normalized so they sum to 1.0 and sorted in descending order.
+    ///
+    /// Parameters that appear in fewer than 2 trials are omitted.
+    /// Returns an empty `Vec` if the study has fewer than 2 completed trials.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// use optimizer::parameter::{FloatParam, Parameter};
+    /// use optimizer::{Direction, Study};
+    ///
+    /// let study: Study<f64> = Study::new(Direction::Minimize);
+    /// let x = FloatParam::new(0.0, 10.0).name("x");
+    ///
+    /// study
+    ///     .optimize(20, |trial| {
+    ///         let xv = x.suggest(trial)?;
+    ///         Ok::<_, optimizer::Error>(xv * xv)
+    ///     })
+    ///     .unwrap();
+    ///
+    /// let importance = study.param_importance();
+    /// assert_eq!(importance.len(), 1);
+    /// assert_eq!(importance[0].0, "x");
+    /// ```
+    #[must_use]
+    #[allow(clippy::cast_precision_loss)]
+    pub fn param_importance(&self) -> Vec<(String, f64)> {
+        use std::collections::BTreeSet;
+
+        use crate::importance::spearman;
+        use crate::param::ParamValue;
+        use crate::types::TrialState;
+
+        let trials = self.completed_trials.read();
+        let complete: Vec<_> = trials
+            .iter()
+            .filter(|t| t.state == TrialState::Complete)
+            .collect();
+
+        if complete.len() < 2 {
+            return Vec::new();
+        }
+
+        // Collect all parameter IDs across trials.
+        let all_param_ids: BTreeSet<_> = complete.iter().flat_map(|t| t.params.keys()).collect();
+
+        let mut scores: Vec<(String, f64)> = Vec::new();
+
+        for &param_id in &all_param_ids {
+            // Collect (param_value_f64, objective_f64) for trials that have this param.
+            let mut param_vals = Vec::new();
+            let mut obj_vals = Vec::new();
+
+            for trial in &complete {
+                if let Some(pv) = trial.params.get(param_id) {
+                    let f = match *pv {
+                        ParamValue::Float(v) => v,
+                        ParamValue::Int(v) => v as f64,
+                        ParamValue::Categorical(v) => v as f64,
+                    };
+                    param_vals.push(f);
+                    obj_vals.push(trial.value.clone().into());
+                }
+            }
+
+            if param_vals.len() < 2 {
+                continue;
+            }
+
+            let corr = spearman(&param_vals, &obj_vals).abs();
+
+            // Determine label: use param_labels if available, else "param_{id}".
+            let label = complete
+                .iter()
+                .find_map(|t| t.param_labels.get(param_id))
+                .map_or_else(|| param_id.to_string(), Clone::clone);
+
+            scores.push((label, corr));
+        }
+
+        // Normalize so scores sum to 1.0.
+        let sum: f64 = scores.iter().map(|(_, s)| *s).sum();
+        if sum > 0.0 {
+            for entry in &mut scores {
+                entry.1 /= sum;
+            }
+        }
+
+        // Sort descending by score.
+        scores.sort_by(|a, b| b.1.partial_cmp(&a.1).unwrap_or(core::cmp::Ordering::Equal));
+
+        scores
+    }
+}
+
 impl<V> IntoIterator for &Study<V>
 where
     V: PartialOrd + Clone,
diff --git a/tests/importance_tests.rs b/tests/importance_tests.rs
new file mode 100644
index 0000000..58c1648
--- /dev/null
+++ b/tests/importance_tests.rs
@@ -0,0 +1,166 @@
+use optimizer::parameter::{CategoricalParam, FloatParam, IntParam, Parameter};
+use optimizer::{Direction, Study};
+
+#[test]
+fn known_perfect_correlation() {
+    let study: Study<f64> = Study::new(Direction::Minimize);
+    let x = FloatParam::new(0.0, 100.0).name("x");
+
+    // Objective = x, so perfect correlation.
+    for _ in 0..30 {
+        let mut trial = study.ask();
+        let xv = x.suggest(&mut trial).unwrap();
+        study.tell(trial, Ok::<_, &str>(xv));
+    }
+
+    let importance = study.param_importance();
+    assert_eq!(importance.len(), 1);
+    assert_eq!(importance[0].0, "x");
+    assert!(
+        (importance[0].1 - 1.0).abs() < 1e-10,
+        "single param should be 1.0"
+    );
+}
+
+#[test]
+fn no_effect_parameter() {
+    let study: Study<f64> = Study::new(Direction::Minimize);
+    let x = FloatParam::new(0.0, 100.0).name("x");
+    let noise = FloatParam::new(0.0, 100.0).name("noise");
+
+    // Objective depends only on x; noise is unused in objective.
+    for _ in 0..50 {
+        let mut trial = study.ask();
+        let xv = x.suggest(&mut trial).unwrap();
+        let _nv = noise.suggest(&mut trial).unwrap();
+        study.tell(trial, Ok::<_, &str>(xv));
+    }
+
+    let importance = study.param_importance();
+    assert_eq!(importance.len(), 2);
+    // x should have much higher importance than noise.
+    let x_score = importance.iter().find(|(l, _)| l == "x").unwrap().1;
+    let noise_score = importance.iter().find(|(l, _)| l == "noise").unwrap().1;
+    assert!(
+        x_score > noise_score,
+        "x ({x_score}) should outrank noise ({noise_score})"
+    );
+    // x should dominate
+    assert!(x_score > 0.7, "x importance {x_score} should be dominant");
+}
+
+#[test]
+fn multiple_parameters_varying_importance() {
+    let study: Study<f64> = Study::new(Direction::Minimize);
+    let x = FloatParam::new(0.0, 10.0).name("x");
+    let y = FloatParam::new(0.0, 10.0).name("y");
+
+    // Objective = 10*x + 0.01*y → x should be far more important.
+    for _ in 0..50 {
+        let mut trial = study.ask();
+        let xv = x.suggest(&mut trial).unwrap();
+        let yv = y.suggest(&mut trial).unwrap();
+        study.tell(trial, Ok::<_, &str>(10.0 * xv + 0.01 * yv));
+    }
+
+    let importance = study.param_importance();
+    assert_eq!(importance.len(), 2);
+    assert_eq!(importance[0].0, "x", "x should rank first");
+    assert!(importance[0].1 > importance[1].1);
+}
+
+#[test]
+fn fewer_than_two_trials_returns_empty() {
+    let study: Study<f64> = Study::new(Direction::Minimize);
+
+    // 0 trials
+    assert!(study.param_importance().is_empty());
+
+    // 1 trial
+    let x = FloatParam::new(0.0, 1.0).name("x");
+    let mut trial = study.ask();
+    let xv = x.suggest(&mut trial).unwrap();
+    study.tell(trial, Ok::<_, &str>(xv));
+    assert!(study.param_importance().is_empty());
+}
+
+#[test]
+fn int_parameter() {
+    let study: Study<f64> = Study::new(Direction::Minimize);
+    let n = IntParam::new(1, 100).name("n");
+
+    for _ in 0..30 {
+        let mut trial = study.ask();
+        let nv = n.suggest(&mut trial).unwrap();
+        study.tell(trial, Ok::<_, &str>(nv as f64));
+    }
+
+    let importance = study.param_importance();
+    assert_eq!(importance.len(), 1);
+    assert_eq!(importance[0].0, "n");
+    assert!(importance[0].1 > 0.9);
+}
+
+#[test]
+fn categorical_parameter() {
+    let study: Study<f64> = Study::new(Direction::Minimize);
+    let cat = CategoricalParam::new(vec!["a", "b", "c"]).name("cat");
+    let x = FloatParam::new(0.0, 100.0).name("x");
+
+    // Objective depends only on x; categorical is random noise.
+    for _ in 0..50 {
+        let mut trial = study.ask();
+        let _c = cat.suggest(&mut trial).unwrap();
+        let xv = x.suggest(&mut trial).unwrap();
+        study.tell(trial, Ok::<_, &str>(xv));
+    }
+
+    let importance = study.param_importance();
+    assert_eq!(importance.len(), 2);
+    let x_score = importance.iter().find(|(l, _)| l == "x").unwrap().1;
+    assert!(x_score > 0.5, "x should dominate over categorical noise");
+}
+
+#[test]
+fn normalization_sums_to_one() {
+    let study: Study<f64> = Study::new(Direction::Minimize);
+    let x = FloatParam::new(0.0, 10.0).name("x");
+    let y = FloatParam::new(0.0, 10.0).name("y");
+    let z = FloatParam::new(0.0, 10.0).name("z");
+
+    for _ in 0..50 {
+        let mut trial = study.ask();
+        let xv = x.suggest(&mut trial).unwrap();
+        let yv = y.suggest(&mut trial).unwrap();
+        let zv = z.suggest(&mut trial).unwrap();
+        study.tell(trial, Ok::<_, &str>(xv + 0.5 * yv + 0.1 * zv));
+    }
+
+    let importance = study.param_importance();
+    let sum: f64 = importance.iter().map(|(_, s)| *s).sum();
+    assert!(
+        (sum - 1.0).abs() < 1e-10,
+        "scores should sum to 1.0, got {sum}"
+    );
+}
+
+#[test]
+fn label_when_unnamed_uses_debug() {
+    let study: Study<f64> = Study::new(Direction::Minimize);
+    // No .name() call → label defaults to Debug representation.
+    let x = FloatParam::new(0.0, 10.0);
+
+    for _ in 0..10 {
+        let mut trial = study.ask();
+        let xv = x.suggest(&mut trial).unwrap();
+        study.tell(trial, Ok::<_, &str>(xv));
+    }
+
+    let importance = study.param_importance();
+    assert_eq!(importance.len(), 1);
+    assert!(
+        importance[0].0.starts_with("FloatParam"),
+        "expected Debug label, got {:?}",
+        importance[0].0
+    );
+}