Think about Your Methods, Then Think Again SASci - Augustin

Think about Your Methods, Then Think Again SASci

 

CHAIR: WELLER, Susan C. (UTMB)

 

WELLER, Susan C. and VICKERS, Ben (UTMB), BERNARD, H. Russell (ASU/UF) Sample Size: Saturation, Domain Size, & Salience TURNLEY, Jessica Glicken (Galisteo Consulting) When Data Isn’t Data: Unpacking the Term across the Sciences AUGUSTIN, Caitlin (U Miami/DataKind), CHENG, Samantha (NCEAS), MINNICH, Robert (Columbia U/DataKind), and ANZAROOT, Sam (DataKind) Efficient Systematic Mapping: New Methods for Analysis and Effective Communication of Results to Community Partners for Conservation Policy Decision-Making 

 

WELLER, Susan C. and VICKERS, Ben (UTMB), BERNARD, H. Russell (ASU/UF) Sample Size: Saturation, Domain Size, & Salience. Sample size estimation for open-ended interviewing relies primarily on custom. In an analysis of 28 examples of free-lists (total n=1147) the median sample size for reaching saturation was 75 (range n=15-194) and salience indices, including the proportion of people in a sample that mentioned an item, were highly correlated. Because sample proportions estimate population proportions, sample size for qualitative studies can be guided by the desired level of salience one hopes to observe. Since many domains are large and unbounded, item salience is a more useful concept than saturation in guiding sample size decisions for qualitative studies.

 

Session took place in Santa Fe, NM at the 77th Annual Meeting of the Society for Applied Anthropology in March 2017.