Failure to replicate earlier findings

A recent paper by Horton [1] attracted 1,576 views and 123 tweets within ten days of its publication.[2] A major scientific breakthrough? Hardly, the paper reported failure to replicate an earlier finding. Whose earlier finding? Horton’s! Horton suggests two reasons for his failure to replicate earlier results: lack of generalisability or type 1 error (false positive result arising through the play of chance). Both papers dealt with memory clues through associations – the idea that a clue, such as a place or a person that was present when the memory was stored in the brain, could prompt its recall.

The CLAHRC WM director thinks Type 1 error is the likely explanation. A positive value is much less impressive evidence against the null hypothesis than many suppose.[3] A Bayesian approach [4] would have forestalled such a volte-face.

— Richard Lilford, CLAHRC WM Director

References:

  1. Brown-Schmidt S, Horton WS. The Influence of Partner-Specific Memory Associations on Picture Naming: A Failure to Replicate Horton (2007). PLoS ONE. 2014; 9(10): e109035.
  2. Reas E. This Week’s Most Discussed PLOS Neuroscience Article: The Influence of Partner-Specific Memory Associations on Picture Naming: A Failure to Replicate. [Online]. 2014.
  3. Goodman S. A Dirty Dozen: Twelve P-Value Misconceptions. Semin Hematol. 2008; 45(3): 135-40.
  4. Goodman SN. Toward Evidence-Based Medical Statistics. 2: The Bayes Factor. Ann Intern Med. 1999; 130: 1005-13.
Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s