Which sampling method may lead to bias due to reliance on contact networks?

Snowball sampling is the method that may lead to bias due to reliance on contact networks. This technique is commonly used in situations where the population is hard to access or identify, such as with marginalized groups or specific communities.

In snowball sampling, existing study subjects recruit future subjects from among their acquaintances. This reliance on social networks can introduce bias because the sample may not be representative of the overall population. The participants are likely to share similar characteristics or experiences, thus skewing the results and limiting the diversity of the sample. This kind of sampling can create a homogenous group, which doesn't accurately reflect the broader population's perspectives or behaviors.

Other sampling methods, such as stratified random sampling, systematic random sampling, and quota sampling, have structures intended to minimize bias by ensuring a more representative selection of the population. Stratified random sampling divides the population into strata and samples from each one, systematic random sampling selects every nth individual, and quota sampling sets specific quotas to ensure representation of certain subgroups. Thus, they do not have the same inherent reliance on social networks as snowball sampling does.