2.6.2.2. Internal validity. Internal validity is the
extent to which we can establish a causal relationship,
whereby certain conditions are shown to lead
to other conditions, as distinguished from spurious
relationships (Cook and Campbell, 1979; Yin, 1989).
To enhance internal validity, Yin suggests the researcher
do “pattern matching”. That is, if for a single
case, it can be shown that actual data patterns match
proposed patterns, then there is good evidence for a
given proposition. If these patterns can be replicated
in similar cases (literal replication), the confirmation
becomes stronger. And, if patterns can be shown not
to hold for understandable reasons for dissimilar cases
(theoretical replication), the confirmation becomes
stronger yet.