巢狀分子變方分析的取樣數與效能

文章來源：Fitzpatrick BM. 2009. Power and sample size for nested analysis of molecular variance. Molecular Ecology 18(19): [全文下載]

分子變方分析（AMOVA）是個在量化不同階層的族群結構對於遺傳變異的貢獻程度時被廣為使用的工具，利用排列測試的運算方式去檢定是否接受或拒絕沒有族群結構的虛無假說。若資料分為若干組，每組內各有數個族群時，每組內的族群數愈少，組間的族群結構會因為組內可取樣供排列測試的族群數過少，而難以偵測得到。事實上，當總族群數少於6群，分析較高階族群結構時排列測試的P值絕不會小於0.05，作者於文中還提供了一套可估算在不同樣本數時最小P值的多項式係數與R指令。一個擁有大量個體數的樣本在階層式結構的分析是不具意義的，偵測組間差異的效能決定於各組內的族群數，因此研究者取應適當取樣。

Abstract
Analysis of molecular variance (AMOVA) is a widely used tool for quantifying the contribution of various levels of population structure to patterns of genetic variation. Implementations of AMOVA use permutation tests to evaluate null hypotheses of no population structure within groups and between groups. With few populations per group, between-group structure might be impossible to detect because only a few permutations of the sampled populations are possible. In fact, with fewer than six total populations, permutation tests will never result in P-values < 0.05 for higher-level population structure. I present minimum numbers of replicates calculated from multinomial coefficients and an R script that can be used to evaluate the minimum P-value for any sampling scheme. While it might seem counterintuitive that a large sample of individuals is uninformative about hierarchical structure, the power to detect between-group differences depends on the number of populations per group and investigators should sample appropriately.

相關連結 R project: http://www.r-project.org