对于如何为以下模型设置多个预测变量的先验,我有点困惑:
require(rstanarm)
wi_prior <- normal(0, sd(train$attendance))
SEED <- 101
fmla <- attendance ~ (1 + W + W1 + W2 + W3 + DivWin1 + DivWin2 + DivWin3 +
WSWin1 | franchID)
baylm <- stan_glmer(fmla,
data = train,
family = "gaussian",
algorithm = "sampling",
adapt_delta = .95,
prior_intercept = wi_prior, seed = SEED)
根据要求,这是火车上的第一次观察。
train <- structure(list(franchID = structure(25L, .Label = c("ANA", "ARI",
"ATL", "BAL", "BOS", "CHC", "CHW", "CIN", "CLE", "COL", "DET",
"FLA", "HOU", "KCR", "LAD", "MIL", "MIN", "NYM", "NYY", "OAK",
"PHI", "PIT", "SDP", "SEA", "SFG", "STL", "TBD", "TEX", "TOR",
"WSN"), class = "factor"), yearID = 1999L, name = "San Francisco Giants",
park = "3Com Park", attendance = 2078399L, W = 86L, W1 = 89L,
W2 = 90L, W3 = 68L, WCWin1 = FALSE, WCWin2 = FALSE, WCWin3 = FALSE,
DivWin1 = FALSE, DivWin2 = TRUE, DivWin3 = FALSE, LgWin1 = FALSE,
LgWin2 = FALSE, LgWin3 = FALSE, WSWin1 = FALSE, WSWin2 = FALSE,
WSWin3 = FALSE), .Names = c("franchID", "yearID", "name",
"park", "attendance", "W", "W1", "W2", "W3", "WCWin1", "WCWin2",
"WCWin3", "DivWin1", "DivWin2", "DivWin3", "LgWin1", "LgWin2",
"LgWin3", "WSWin1", "WSWin2", "WSWin3"), row.names = c(NA, -1L
), class = "data.frame")
答案 0 :(得分:2)
您可以通过将长度为K的向量传递给先验支持的分布之一来为K个预测变量指定系数的先验。例如,如果K = 4,则可以
wi_prior2 <- normal(location = c(0, 1, -2, 5))
您还可以传递比例矢量和/或与normal
不同的系列。然后,您可以使用stan_glmer
致电prior = wi_prior2
。如果你这样做
wi_prior2 <- normal(location = 0)
然后相同的先验将用于所有K个公共系数。
但是,在您的情况下,我怀疑fmla
是错误的。您通常还希望在lme4样式的括号表达式之外包含大多数(如果不是全部)预测变量,以允许franchID
的所有级别的共同效果。因此,fmla
将成为
fmla <- attendance ~ W + W1 + W2 + W3 + DivWin1 + DivWin2 + DivWin3 +
WSWin1 + (1 + W + W1 + W2 + W3 + DivWin1 + DivWin2 + DivWin3 +
WSWin1 | franchID)
如果您只在括号中包含该部分,那么您假设这些变量的系数在总体中恰好为零,并且仅在由franchID
的级别定义的子群中偏离零。因此,没有机会将先前的分布放在它们的系数上。
与公共系数的分组偏差之前的条件是条件多变量法线,其中平均向量为零,并且有些复杂但未知的协方差结构。这在help(priors, package = "rstanarm")
中有更详细的解释。