Kathryn G. Sapnas

Minimizing sample size when using exploratory factor analysis for measurement.

Traditional protocol for the determination of an adequate sample size is power analysis. Such a protocol is not useful when the primary hypothesis focuses on psychometric measurement properties. Traditional psychometrics advises that there should be 10 respondents per item. Both hypothetical and real research examples illustrate the usefulness of sub-sample analysis in determining that a sample size of at least 50 and not more than 100 subjects is adequate to represent and evaluate the psychometric properties of measures of social constructs. The “10 respondents per item” advice builds a sample size disincentive into the research design; it also represents “sample size overkill.” Sample-size overkill occurs when the research design specifies a number of cases needed, which is in excess of the number actually needed for a desired inference.

HEART INJURIES AMONG RESTRAINED OCCUPANTS IN FRONTAL CRASHES

The William Lehman Injury Research Center has conducted multi-disciplinary investigations of one hundred seventy-eight crashes involving adult occupants protected by safety belts and air bags. When used in conjunction with National Accident Sampling System/Crashworthiness Data System (NASS/CDS) they provide insight into the most severe injuries suffered by restrained occupants in frontal crashes. Heart injuries are rare, but when they occur they are usually life threatening. NASS/CDS shows that heart injuries comprise about 0.2% of the injuries in frontal tow-away crashes, In the NHTSA file of Special Crash Investigations (SCI) of air bag cases, heart injuries are reported in 1% of the occupants over 15 years of age. Twenty-five percent of the fatally injured occupants had heart injuries and 83% of those with heart injury died. In the Lehman Center cases, heart injuries are present in 5.1% of the cases. Forty percent of the fatally injured had heart injury, and 78% of the victims with heart injury died. This paper suggests two additional triage criteria, based on observations from multi-disciplinary studies. These include: (1) passengers in 2-point belts and crashes of 25 mph or higher, with the lap belt unfastened or with the seat full forward; (2) drivers in crash conditions which delay the air bag deployment or permit the driver to be close to the air bag at deployment. (A) For the covering abstract see IRRD 893297.