Chemistry and Pollution: Cause and Effect

The statistical studies that evaluation of chemical hazards rely on run into limitations when small numbers are involved.  Consider the famous case of chromium pollution uncovered by Erin Brockovich.  Statistical analysis reveals no excess cancers in the area of Hinckley, CA.  The area population was 3644 during the period studied (1996-2008), and suffered 196 cases of cancer when 224 would be expected statistically.  Can we conclude that the elevated levels of hexavalent chromium observed caused no cancers?  Of course not, hexavalent chromium is a known carcinogen, but it shows that it may be very difficult to sort out cause and effect, particularly in small populations.