Study Learning, Study Learning

Phi Delta Kappan

Volumn 78, Issue 3, 1997, Pages 246-247

  Baker, Keith ^a  

^a NONE

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0345909593     PISSN: 00317217     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (5)

1. W. R. Robinson, "Ecological Correlations and the Behavior of Individuals," American Sociological Review, vol. 15, 1950, pp. 351-57.
2. The following example of how the ecological correlation fallacy works does not use educational variables because test scores would greatly complicate the mathematics and increase the time it would take me to create (and readers to understand) the example.
3. The infamous "Wall Chart" put out by the U.S. Department of Education for some years was a collection of state-level aggregate data. As such, it was fraught with the dangers of the ecological correlation fallacy. Policy makers, pundits, the media, and politicians drew a variety of conclusions about learning from each Wall Chart, and all of them were invalid.
4. Much classical economic and sociological theory and research works with the relationships between aggregate variables. This is okay. Explaining aggregate relationships from individual relationships is also okay. Drawing inferences about individual- level relationships from aggregate relationships is not okay.
5. See Keith Baker, "Yes, Throw Money at Schools," Phi Delta Kappan, April 1991, pp. 628-30.