Click on the following links. Please note these will open in a new window.

Article 1: Slavin, R., & Smith, D. (2009). The relationship between sample sizes and effect sizes in systematic reviews in education. Educational Evaluation and Policy Analysis, 31(4), 500–506. doi:10.3102/0162373709352369.

Summary/Abstract: Research in fields other than education has found that studies with small sample sizes tend to have larger effect sizes than those with large samples. This article examines the relationship between sample size and effect size in education. It analyzes data from 185 studies of elementary and secondary mathematics programs that met the standards of the Best Evidence Encyclopedia. As predicted, there was a significant negative correlation between sample size and effect size. The differences in effect sizes between small and large experiments were much greater than those between randomized and matched experiments. Explanations for the effects of sample size on effect size are discussed.

Questions to Consider

1. How does effect size and sample size impact the likelihood of journal publications?

2. The authors discovered that effect sizes varied based on the type of randomization that was employed. From high to low, order the following designs based on their obtained effect sizes.

1. Randomized, randomized quasi-experiments, and then matched studies
2. Matched studies, randomized, and then randomized quasi-experiments
3. Randomized, matched studies, and then randomized quasi-experiments
4. Randomized quasi-experiments, matched studies, and then randomized

3. The authors suggest that the bias towards small sample sizes can be reduced. Which of the following is not a technique they discussed?

1. weight effect sizes by their sample sizes
2. weighting by inverse variances
3. winsorizing the data set
4. log transformations
    

Article 2: Li, W., & Zinbarg, R. E. (2007). Anxiety sensitivity and panic attacks: A 1-year longitudinal study. Behavior Modification, 31(2), 145–161. doi:10.1177/0145445506296969.

Summary/Abstract: The hypothesis that anxiety sensitivity (AS) is a risk factor for panic genesis has obtained compelling support, but the clinical/practical importance of AS in panic genesis has been questioned. In addition, the association between panic experience and AS increase has not been clearly demonstrated. Through this 1-year longitudinal study among college students, the authors replicated the vulnerability effect of AS on panic onset. By measuring AS according to its hierarchical structure, the authors found an AS subfactor—AS-Mental Incapacitation Concerns—to be a significant predictor of panic onset. The authors also demonstrate that AS is not only statistically significant but also clinically/pragmatically important for the onset of panic. The association between panic and increased AS was confirmed in this study, although it remains for future research to conclude whether this association should be attributed to a “scar effect” of panic. Theoretical and methodological issues regarding tests of the scar effect hypothesis are discussed.

Questions to Consider

1. How did the authors utilize effect sizes to answer their research questions?

2. What test statistic did the authors use to determine effect size?

1. Cohen transformation
2. Nagelkerke R²
3. Eta square
4. d prime

3. Based on effect size, how did anxiety sensitivity impact the likelihood of panic attacks?

1. AS as a risk factor for panic is more important than it was previously thought to be.
2. AS as a risk factor for panic is less important than it was previously thought to be.
3. AS as a risk factor for panic is equally as important as it was previously thought to be.
4. AS does not impact the likelihood of panic attacks at all.