CALIFORNIA STATE UNIVERSITY LONG BEACH
PPA 696--RESEARCH METHODS:
BINGHAM & FELBINGER CH. 12
  1. BIBLIOGRAPHIC INFORMATION
    1. Author: D. M. Maxwell
    1. Title: Impact Analysis of the Raised Legal Drinking Age in Illinois
    1. Source: National Highway Transportation Safety Administration, U.S. Dept. of Transportation, December, 1981, Technical Report DOT-HS-806-115

      2.  
  1. SUMMARY OF THE RESEARCH
    1. PROBLEM STATEMENT:
What is the effect on accident rates of raising the minimal legal drinking age?
    1. BACKGROUND:
The federal government was considering establishing a national minimum drinking age of 21
    1. HYPOTHESIS:
Raising the minimum legal drinking age will reduce the automobile accident rate
    1. MEASUREMENT OF VARIABLES
      1. Dependent variable: Accident rate for Single Vehicle Night Male Drivers
      1. Independent variable(s): Legal Minimum Drinking Age
      1. Control variable(s): n/a
    1. RESEARCH DESIGN:
A quasi-experimental, single interrupted time series design.
T1 T2 T3 T4 Policy 

Change

 T5
O1 O2 O3 O4 X O5
 
    1. SAMPLING:
Observations were taken for fours years prior to and one year after the policy change.
    1. INSTRUMENTATION:
SVNMD was used as a surrogate for alcohol-related automobile accidents
    1. DATA COLLECTION/ETHICS:
Data were collected from state records
    1. DATA ANALYSIS:
Box-Tiao intervention analysis was used to explore whether there were statistically significant differences in the accident rate by age group, before and after the policy change.
    1. CONCLUSIONS:
The policy change reduced the SVNMD accident rate among the affected age groups (19-20 year olds) by about 8.8%, but it did not reduce the SVNMD accident rate among other age groups.
 
 
  1. CRITIQUE
    1. Possible Threats to Internal Validity
      1. History:
No control for other things that could have influenced the accident rates
      1. Maturation:
n/a
      1. Testing:
n/a
      1. Instrumentation:
No indication that state records changed over time
      1. Regression Artifact:
Abnormally high rates could be expected to fall over time
      1. Selection bias:
n/a
      1. Experimental Mortality:
n/a
      1. Design contamination:
n/a
    1. Possible Threats to External Validity
      1. unique program features:
Assumption that measuring SVNMD accident rates captures the accident rate for teenage drivers is faulty
      1. experimental arrangements:
Illinois may be different than other states
      1. other threats:
very little reduction in accident rates