Link? Y/N

Enter Y (yes) if the link is significant at p equal to or less than .05; enter N (no) otherwise. For studies with statistical tests of more than one measure of the cause and/or effect or with statistical tests of various subgroups (e.g., boys and girls)—all for the same link—enter Y if any of the tests were significant and describe them all in the abstract. If none are significant, enter N.

Research Method

Enter one of the following six abbreviations (in parentheses). See the definitions that follow the terms.

  • Natural experiment (Exp-N)

  • Randomized trial (Exp)

  • Panel (L-Pnl)

  • Cohort (L-Coh)

  • Trend (L-Trnd)

  • Cross-sectional (CS)

Experimental Studies

  • Natural experiment (Exp-N): Treatment assigned serendipitously but randomly. For example, in the early 1990s in the Milwaukee School Voucher program, there were more students who applied for school vouchers than vouchers available. All applicants were entered in a lottery, with only the winners getting vouchers.

  • Randomized trial (Exp): Treatment assigned deliberately and randomly.

Nonexperimental (Observational) Studies

Longitudinal Studies:

  • Panel (L-Pnl): Measures the same sample of individuals at different points in time.

  • Cohort (L-Coh): Similar subjects (age, demographics, etc.) are followed over time and compared on outcome or descriptive measures (e.g., health). Cohort studies typically involve a sample in which some individuals have a property and some do not (e.g., smokers versus nonsmokers).

  • Trend (L-Trnd): Samples different groups of people at different points in time from the same population, using the same measures.

Cross-Sectional Studies:

  • Cross-sectional (CS): Nonexperimental study at a single point in time.

Cause Variable

Briefly describe the marketing variable considered the causal (initiating,



The National Academies | 500 Fifth St. N.W. | Washington, D.C. 20001
Copyright © National Academy of Sciences. All rights reserved.
Terms of Use and Privacy Statement