Evans (1997 Sep, 1997 Jun) and Rees (1997 Sep) have emphasized that great c
are is needed to obtain good data because, otherwise, Garbage In leads to G
arbage Out. This tutorial demonstrates that, even when one has good data, t
he results still are incorrect if data analysis is performed incorrectly. A
central issue in correct statistical analysis is determining the context w
ithin which the data arose; and resolving the inherent ambiguities in inter
preting failure-data makes it essential to incorporate such context into re
liability data analyses. When this is ignored, as is usually the case (a se
t-of-numbers is treated as if it were an entire data-set, thus ignoring oth
er essential information) even Good Data In results in Garbage Out.