diff --git a/src/collocatordb.cc b/src/collocatordb.cc
index 6eda410..63029c4 100644
--- a/src/collocatordb.cc
+++ b/src/collocatordb.cc
@@ -179,12 +179,21 @@
 // Collocations. PhD dissertation, IMS, University of Stuttgart. Published in
 // 2005, URN urn:nbn:de:bsz:93-opus-23714. Free PDF available from
 // http://purl.org/stefan.evert/PUB/Evert2004phd.pdf
+// The table classifies co-occurrence tokens, not corpus tokens: with a window of
+// window_size positions, every occurrence of either word takes part in that many
+// pairs, so the sample size and both marginals scale with it. Scaling only the
+// row, as this did before, leaves cells that do not add up to one sample and lets
+// n - window_size * w1 turn negative for a frequent node in a wide window. The
+// expected co-occurrence frequency is window_size * w1 * w2 / n either way, which
+// is why the other measures do not depend on this.
 static double ca_ll(uint64_t w1, uint64_t w2, uint64_t w12, uint64_t n,
                            uint64_t window_size) {
-  double r1 = (double)w1 * window_size, r2 = (double)n - r1, c1 = w2,
-         c2 = n - c1, o11 = w12, o12 = r1 - o11, o21 = c1 - w12, o22 = r2 - o21,
-         e11 = r1 * c1 / n, e12 = r1 * c2 / n, e21 = r2 * c1 / n,
-         e22 = r2 * c2 / n;
+  double total = (double)n * window_size,
+         r1 = (double)w1 * window_size, r2 = total - r1,
+         c1 = (double)w2 * window_size, c2 = total - c1,
+         o11 = w12, o12 = r1 - o11, o21 = c1 - o11, o22 = r2 - o21,
+         e11 = r1 * c1 / total, e12 = r1 * c2 / total, e21 = r2 * c1 / total,
+         e22 = r2 * c2 / total;
   return (2 * ((o11 > 0 ? o11 * log(o11 / e11) : 0) +
                (o12 > 0 ? o12 * log(o12 / e12) : 0) +
                (o21 > 0 ? o21 * log(o21 / e21) : 0) +