## **Core Concept**
The design effect, also known as the "design effect size," is a statistical measure used in survey research and epidemiology to quantify the impact of a study's design on the variance of estimates. It is particularly relevant in the context of cluster sampling or other complex sampling designs.

## **Why the Correct Answer is Right**
The design effect is most closely associated with **Cluster Sampling**. In cluster sampling, the population is divided into clusters (or groups), and a random sample of these clusters is selected. All (or a random sample) of the elements within the selected clusters are then studied. The design effect arises because the variation within clusters can be different from the variation between clusters, affecting the overall variance of the estimates. This technique is used to account for the increased variability (or reduced precision) that can occur when observations within clusters are more similar than those across different clusters.

## **Why Each Wrong Option is Incorrect**
- **Option A:** Simple Random Sampling does not involve a design effect in the same way cluster sampling does, as it assumes that each unit in the population has an equal chance of being selected, and the observations are considered independent.
- **Option B:** Stratified Sampling involves dividing the population into distinct subgroups (strata) and then sampling from each subgroup. While it does involve a form of sampling design, the primary goal here is to ensure that each subgroup is adequately represented, rather than to specifically account for a design effect related to cluster-level variability.
- **Option C:** Systematic Sampling involves selecting samples based on a fixed interval or system (e.g., every 10th item), which does not inherently involve the kind of clustering that would necessitate a design effect adjustment.

## **Clinical Pearl / High-Yield Fact**
A key point to remember is that the design effect is quantitatively expressed as a ratio of the variance of the estimator under the actual sampling design to the variance under simple random sampling. A design effect of 1 indicates no difference from simple random sampling, while a design effect greater than 1 suggests that the sampling design results in a larger variance (less efficient) than simple random sampling.

## **Correct Answer:** C. Cluster Sampling