手法を比較

	フィールドベース最大多様性サンプリング	フィールドベース層化抽出法
分野	調査方法論	調査方法論
系統	Process / pipeline	Process / pipeline
提唱年	1990 (Patton); field application established through ecological and ethnographic practice in the 1990s–2000s	1934 (Neyman's stratified sampling theory); field applications throughout 20th century
提唱者	Michael Quinn Patton (maximum variation sampling); adapted for field research contexts	Jerzy Neyman (stratified sampling theory); applied broadly in field survey practice
種類	Purposive qualitative/mixed-methods sampling strategy	Probability sampling design
原典	Patton, M. Q. (2002). Qualitative Research and Evaluation Methods (3rd ed.). Sage. [Maximum variation sampling discussed in Chapter 5] ISBN: 978-0761919711	Cochran, W. G. (1977). Sampling Techniques (3rd ed.). John Wiley & Sons. ISBN: 978-0471162407
別名	field MVS, field-based purposeful maximum variation, maximum heterogeneity field sampling, diverse case field sampling	field stratified sampling, stratified field survey sampling, in-field stratified sampling, field survey stratification
関連	6	6
概要	Field-based maximum variation sampling is a purposive strategy in which a researcher deliberately selects field sites, ecological plots, communities, or observational units that span the widest possible range of relevant characteristics. By maximising heterogeneity among selected units, the approach ensures that both common patterns shared across diverse conditions and unique features specific to particular contexts are documented, making findings robust across a broad spectrum of real-world variation.	Field-based stratified sampling divides a geographically dispersed or heterogeneous target population into internally homogeneous subgroups (strata) defined by features observable in the field — such as land use type, habitat zone, administrative district, or community category — and then independently draws random samples from each stratum during on-site data collection. The approach combines the precision gains of stratification with the logistical realities of fieldwork, ensuring that every identifiable subgroup of the landscape or community is represented in the final data set.