1 / 8

Significance testing the validity of idiographic methods: a little derangement goes a long way

Significance testing the validity of idiographic methods: a little derangement goes a long way. Chris Evans, John Hughes & Julia Houston http://www.psyctc.org/cgi-bin/mailto.pl?chris. The issue. How to validate idiographic data when you can’t use mismatched cases

bevan
Download Presentation

Significance testing the validity of idiographic methods: a little derangement goes a long way

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Significance testing the validity of idiographic methods: a little derangement goes a long way Chris Evans, John Hughes & Julia Houston http://www.psyctc.org/cgi-bin/mailto.pl?chris

  2. The issue • How to validate idiographic data when you can’t use mismatched cases • Some situations in which mismatched cases aren’t available or where they would generalise from reference data to the test data. (Fine if you have an underlying model, e.g. CCRT but not O.K. if you’re radically idiographic)

  3. The answer • Take the data you have (n  4) • Shuffle the data • Present them to judge • Ask judge to match data to people • Score is correct matches • Score  4, regardless of n, gives p<.05 against null model

  4. Advantages • No generalisation involved • Entirely logically coherent method • Entirely idiographic, no assumptions of any common dimensions of variation • Manipulation of information available to the judge could explore sources of judgement

  5. Disadvantages • n 4 • Need some judge with some information about respondents other than the idiographic data • Binary answer (strictly a p value with a limited number of possible values conditional on n)

  6. Method: stages 1 and 2 1 2 2 6 3 1 4 4 5 3 6 5 1: Get the data (n4) 2: Randomly rearrange the data

  7. Method: stage 3 3: See if judge can map data back to people ? 2 6 1 4 3 5

  8. Method: stages 4, (5) & 6 (5: Lookup p value if you want it) 2 6 4 or more 1 4 3 5 3 or fewer 4: Score correct mappings 6: respond accordingly

More Related