Skip to main content icon/video/no-internet
icon backReturn to Entries

Replication

Replication, or repetition, typically refers to the ability of results and theoretical concepts to be recreated in subsequent investigations. This is an essential means of building the credibility or external validity of a theory or concept in the research world. Successful replication demonstrates that observed phenomena (often in regards to causal relationships) were not isolated instances, but fairly reliable patterns in a larger context. In an interdisciplinary field such as communication, this may be particularly important when using existing theories from other fields. Replication ensures robustness and generalizability of experimental observations. A communication scholar may find frequent need to reproduce the relationships demonstrated between common variables in other disciplines, but in a communication-specific context. Repetition of experiments is particularly important to confirming causal inferences. If the results of an experiment can be replicated under similar conditions, this reduces the danger of committing both type I and type II errors. This entry first reviews the history and method of replication and then discusses the importance of replication in the scientific method.

History

The value of building the external validity of theoretical concepts is equally, if not more, important in the social sciences and humanities as it is in the natural sciences. The need to draw connections between what was traditionally considered to be the natural world and the realm of theoretical deduction has been stressed by social scientists and philosophers since the early 20th century. Replication of experiments is a methodological legacy of such philosophical considerations and a desire to deduce epistemic patterns in the natural world, including the world of human behavior.

A significant source of historical inspiration for the concept of repetition may be traced to Karl Popper, a scientific philosopher known for popularizing the idea of falsifiability. Empirical falsifiability can be easily understood through the null hypothesis. Popper asserted that a hypothesis can never be proven to be absolutely correct, but it can be proven to be incorrect. The classic example of falsifiability is that the claim “all swans are white” cannot practically be demonstrated, but that the same claim can be proven false by the observation of a single black swan. Therefore, empiricism should demonstrate claims to be true only in contrast by what we can prove to be false. Replication might be compared to the search for the “black swan” of the hypothesis: the null hypothesis. An inability to produce the null hypothesis through subsequent, repeated observations builds the case for the hypothesis and, thus, supports the credibility of the theoretical concept in question.

Methods of Replication

There is no one way to repeat or replicate the results of an experiment. The simplest way to confirm an experimental relationship is, as the term suggests, by repeating the same experiment with a different sample population. For example, administering the same survey to a different group of respondents. In principle, for an experiment to be meaningfully replicated, it should be repeated with similar, if not identical methods to the original study. However, this will be dependent on the nature of the experiment and phenomenon being investigated.

...

  • Loading...
locked icon

Sign in to access this content

Get a 30 day FREE TRIAL

  • Watch videos from a variety of sources bringing classroom topics to life
  • Read modern, diverse business cases
  • Explore hundreds of books and reference titles

Read next

More like this

Sage Recommends

We found other relevant content for you on other Sage platforms.

close

Have you created a personal profile? Login or create a profile so that you can save clips, playlists and searches

close
close
close Signed In to profile You are signed in as:
close
Logged in Institution Institution