Against external validity

Weighting for External Validity∗

External validity is a challenge in treatment effect estimation. Even in randomized trials, the experimental sample often differs from the population of interest. If participation decisions are explained by observed variables such differences can be overcome by reweighting. However, participation may depend on unobserved variables. Even in such cases, under a common support assumption there exi...

Theory and External Validity

Winer (1999 [this issue]) proposes that external validity concerns require more attention in theoretical research. The author argues that one cannot “enhance” external validity by choosing one method over another. External validity can only be “assessed” by better understanding how the focal variables in one’s theory interact with moderator variables that are seen as irrelevant early in a resea...

External, Internal and Construct Validity

Introduction In research, validity refers to the degree to which findings are applicable in real-life situations. Essentially, if the findings are strongly valid, it implies that they have an excellent degree of applicability. In contrast, low validity implies that the survey is not applicable in real-life situations. The specific approach used during research has strong influence on validity. ...

Do pragmatic trials trade-off internal validity for external validity?

Trials can be described as being on a design spectrum between highly explanatory (roughly, ‘Can the intervention work?’) to highly pragmatic (‘Does the intervention work in routine care?’). A criticism levelled at trials that take a pragmatic approach is that they sacrifice internal validity for external validity, i.e. there is a trade-off to be made. Proponents of pragmatic trials argue that t...

Why internal validity is not prior to external validity