NCJ Number
57688
Journal
Sociological Methods and Research Volume: 7 Issue: 4 Dated: SPECIAL ISSUE (MAY 1979) Pages: COMPLETE ISSUE
Editor(s)
E F BORGATTA,
D J JACKSON
Date Published
1979
Length
125 pages
Annotation
THIS SPECIAL ISSUE OF THE JOURNAL SOCIOLOGICAL METHODS AND RESEARCH IS DEVOTED TO STUDIES ON THE ANALYSIS AND INTERPRETATION OF AGGREGATE DATA.
Abstract
AN OVERVIEW OF THE PROBLEMS SOCIAL SCIENTISTS AND SOCIOLOGISTS ENCOUNTER IN ANALYZING AGGREGATE DATA SHOWS THAT POTENTIAL HAZARDS LIE IN THE AREAS OF INTERPRETATION OF INDIVIDUAL LEVEL VARIABLES BASED ON ANALYSES OF DATA AGGREGATED BY GEOGRAPHICAL OR OTHER UNITS, CONVERTING AGGREGATE-LEVEL DATA INTO RATES, DEALING WITH THE 'REALITY OF GROUPS' FROM SPECULATIVE TERMS, AND INDEPENDENT MEASURING OF INDIVIDUAL'S CHARACTERISTICS APART FROM CHARACTERISTICS OF GROUPS. TWO REGRESSION METHODS MOST OFTEN RECOMMENDED FOR ASSESSING GROUP EFFECTS IN NONEXPERIMENTAL DATA--COVARIANCE ANALYSIS AND CONTEXTUAL ANALYSIS--ARE EXAMINED IN A COMPARATIVE STUDY. GUIDELINES ARE PRESENTED FOR RESEARCHERS WORKING WITH RATIO DATA, AND AN OVERVIEW IS PROVIDED OF ISSUES REGARDING THE USE OF RATIOS IN CORRELATION AND REGRESSION ANALYSES. ALSO DISCUSSED ARE THE PROBLEMS PRESENTED IN ANALYSIS PROCEDURES AND INFERENCES WHEN RATIOS ARE COMPUTED BY USING THE SAME OR HIGHLY CORRELATED DENOMINATORS, A PROBLEM PRESENT IN EITHER CROSS-SECTIONAL OR LONGITUDINAL RESEARCH. SEVERAL SOLUTIONS TO OVERCOME THOSE PROBLEMS ARE OUTLINED. SEE ALSO NCJ-57689, 57690, AND 57692. (MHP)