Effect size

In empirical studies the notion statistically significant is often used. But, for a large sample, even a small effect may be statistically significant. But if we want to know how important the effect is, we need another measure: effect size.

Now, these effect sizes show that sexual abuse has only a small effect in the average.

Extracts from the meta-analysis of Rind et.al. 1998

One researcher, by the name of Jumper, in 1995 included student, community, and clinical samples in her meta-analysis of the relation between CSA and adjustment. She averaged the effect sizes separately for each sample-type. After correcting for some errors she made, her results were that CSA accounted for 0.8% of the adjustment variation in the student samples, 2.25% in the community samples, and 7.3% in the clinical samples. In other words, CSA was related to adjustment, but the relationship was small in the nonclinical samples and medium in the clinical samples.

In 1996, another group of researchers published a second meta-analysis. They computed average effect sizes separately for nonclinical and clinical samples. The amount of variability accounted for by CSA was 1.4% for the nonclinical samples and 3.6% for the clinical samples. []

These two quantitative reviews improved over the qualitative reviews in several ways. First, they avoided subjective interpretations. Second, they included large numbers of nonclinical samples. Third, they analyzed them separately. The overall picture is this. Clinical samples are clearly different from nonclinical samples. This empirically demonstrates that it is not appropriate to generalize from clinical reports of CSA to the general population. Additionally, although CSA is related to poorer adjustment in nonclinical samples, the association is small. This means that claims that CSA pervasively produces lasting, severe psychological injury are vastly overstated.

We next examined the relationship between CSA and adjustment by meta-analyzing results across the 54 samples that provided usable statistics. Based on 15,912 subjects, the average amount of variability in adjustment scores accounted for by CSA was 0.81%, meaning that CSA failed to account for 99.19% of the adjustment variability. Nevertheless, this small difference in adjustment was statistically significant, with CSA subjects showing somewhat poorer adjustment. We next meta-analyzed the relations between CSA and adjustment separately for males and females. As you can see in Table 6, CSA accounted for 0.49% of the adjustment variability for males and 1.00% for females - exactly the same values as in the national samples. It is worth emphasizing at this point that the comparability of the college samples and the national samples is quite good in various respects: prevalence rates of CSA, types of CSA, and the magnitude of the CSA-adjustment relations. These findings indicate that college data are substantially more valuable than clinical data for attempting to understand the nature of CSA in the general population.

Other research results

In Scott 1992 it is "estimated that 74% [probably 7.4%?] of the exposed psychiatric cases (i.e., those with a history of CSA), and 3.9% of all psychiatric cases within the population can be attributed to childhood sexual abuse."