将函数应用于因子（参和者）的每一级，根据与R中标准偏差平均值的距离去除异常值
我在R中有一个data.frame，其中一列表示实验中的参与者将函数应用于因子（参和者）的每一级，根据与R中标准偏差平均值的距离去除异常值,r,dataframe,outliers,R,Dataframe,Outliers,我在R中有一个data.frame，其中一列表示实验中的参与者受试者，另一列表示条件，试验类型，最后一列表示我的数值因变量rt 以下是使用dput（）函数为我的data.frame的前64行生成的数据的可复制示例： structure(list(subject = structure(c(21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 24L, 24L, 24L, 24L, 24
受试者条件试验类型rtdput（） structure(list(subject = structure(c(21L, 21L, 21L, 21L, 21L,
21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 24L, 24L,
24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L, 24L,
24L, 27L, 27L, 27L, 27L, 27L, 27L, 27L, 27L, 27L, 27L, 27L, 27L,
27L, 27L, 27L, 27L, 47L, 47L, 47L, 47L, 47L, 47L, 47L, 47L, 47L,
47L, 47L, 47L, 47L, 47L, 47L, 47L), .Label = c("1p12", "1p13",
"1p15", "1p30", "1p36", "1p39", "1p43", "1p46", "1p49", "1p59",
"1p60", "1p67", "1p69", "1p79", "1p80", "1p81", "1p84", "1p85",
"1p88", "1p9", "2p1", "2p11", "2p18", "2p2", "2p22", "2p25",
"2p3", "2p31", "2p33", "2p42", "2p44", "2p5", "2p50", "2p58",
"2p63", "2p72", "2p76", "2p78", "2p8", "2p83", "3p10", "3p16",
"3p20", "3p28", "3p32", "3p34", "3p4", "3p41", "3p47", "3p54",
"3p55", "3p56", "3p61", "3p64", "3p66", "3p7", "3p77", "3p82",
"3p86", "3p87", "4p14", "4p17", "4p19", "4p21", "4p24", "4p26",
"4p27", "4p29", "4p35", "4p37", "4p38", "4p48", "4p51", "4p57",
"4p6", "4p62", "4p68", "4p70", "4p74", "4p75"), class = "factor"),
rt = c(4303L, 5616L, 1317L, 1663L, 1353L, 645L, 648L, 457L,
2359L, 2497L, 832L, 523L, 1427L, 511L, 483L, 1300L, 873L,
1185L, 1752L, 2037L, 4849L, 2975L, 1621L, 1235L, 3008L, 1560L,
1075L, 4596L, 1129L, 1093L, 1302L, 1414L, 5542L, 2369L, 4944L,
2338L, 1274L, 1837L, 3384L, 1338L, 2002L, 1756L, 2516L, 1868L,
2017L, 1337L, 1106L, 1388L, 6812L, 5579L, 1695L, 1976L, 1897L,
4484L, 3095L, 1865L, 2283L, 1659L, 1328L, 1882L, 1483L, 1993L,
1776L, 2256L), condition = structure(c(1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("reliable",
"unreliable"), class = "factor"), trial_type = structure(c(2L,
2L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L,
2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 1L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L,
1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L,
1L, 2L, 2L), .Label = c("same", "switch"), class = "factor"),
accuracy = c(0L, 0L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 0L, 1L,
1L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 0L, 0L, 1L, 0L, 1L,
0L, 1L, 1L, 0L, 1L, 0L, 0L, 1L, 0L, 0L, 1L, 1L, 0L, 1L, 1L,
1L, 0L, 0L, 1L, 0L, 1L, 0L, 0L, 0L, 1L, 1L, 1L, 0L, 0L, 1L,
1L, 0L, 1L, 1L, 0L, 1L, 0L, 1L)), row.names = c(NA, -64L), class = c("tbl_df",
"tbl", "data.frame"))
rt受试者试验类型rt# Calculate mean and `sd` for each level of `trial_type`
# For 'same':
MeanSame <- mean(RTs$rt[RTs$trial_type == "same"])
SDSame <- sd(RTs$rt[RTs$trial_type == "same"])
# For 'switch':
MeanSwitch <- mean(RTs$rt[RTs$trial_type == "switch"])
SDSwitch <- sd(RTs$rt[RTs$trial_type == "switch"])
# Create upper and lower cut for level 'same' of 'trial_type':
UpperSame <- MeanSame + 2.5*SDSame
LowerSame <- MeanSame - 2.5*SDSame
# Create upper and lower cut for level 'switch' of 'trial_type':
UpperSwitch <-2.5*SDSwitch + MeanSwitch
LowerSwitch <- MeanSwitch - 2.5*SDSwitch
#Identify Outliers in Same
OutliersSameUpper <- which(RTs$rt > UpperSame & RTs$trial_type == "same")
OutliersSameLower <- which(RTs$rt < LowerSame & RTs$trial_type == "same")
# Identify Outliers in Switch
OutliersSwitchUpper <- which(RTs$rt > UpperSwitch & RTs$trial_type == "switch")
OutliersSwitchLower <- which(RTs$rt < LowerSwitch & RTs$trial_type == "switch")
# Create new data.frame without the identified outliers:
RTsClean <- RTs[-c(OutliersSameUpper,OutliersSameLower,OutliersSwitchUpper,OutliersSwitchLower),]
#计算每个“试验”类型水平的平均值和“sd”`
#对于“相同”：
根据OP的要求，平均值相同
如果有人能帮助我找到最好的方法来应用我在上面指定的异常值移除方法，我将不胜感激，但这种方法可以单独应用于主题向量的每个级别。这意味着需要为每个受试者级别指定平均值和sd变量
它删除三行作为异常值
图书馆（dplyr）
RTs%%>%分组依据（受试者）%%>%
过滤器（rt=平均值（rt）-（2.5*sd（rt）））
#>#A tibble:61 x 5
#>#分组：受试者[4]
#>受试者rt条件试验类型精度
#>
#>1 2p1 4303可靠开关0
#>2 2p1 1317可靠开关0
#>3 2p1 1663可靠性相同1
#>4 2p1 1353可靠开关1
#>5 2p1 645可靠的相同1
#>6 2p1 648可靠性相同1
#>7 2p1 457可靠相同1
#>8 2p1 2359可靠开关0
#>9 2p1 2497可靠开关0
#>10 2p1 832可靠相同的1
#> # ... 还有51行
基于OP的进一步要求
如果可能，最好在data.frame中创建一个新列，指定rt中的每一行，不管该行是否被视为异常值。但我不知道如何才能做到这一点
基于OP的这一要求
如果有人能帮助我找到最好的方法来应用我在上面指定的异常值移除方法，我将不胜感激，但这种方法可以单独应用于主题向量的每个级别。这意味着需要为每个受试者级别指定平均值和sd变量
它删除三行作为异常值
图书馆（dplyr）
RTs%%>%分组依据（受试者）%%>%
过滤器（rt=平均值（rt）-（2.5*sd（rt）））
#>#A tibble:61 x 5
#>#分组：受试者[4]
#>受试者rt条件试验类型精度
#>
#>1 2p1 4303可靠开关0
#>2 2p1 1317可靠开关0
#>3 2p1 1663可靠性相同1
#>4 2p1 1353可靠开关1
#>5 2p1 645可靠的相同1
#>6 2p1 648可靠性相同1
#>7 2p1 457可靠相同1
#>8 2p1 2359可靠开关0
#>9 2p1 2497可靠开关0
#>10 2p1 832可靠相同的1
#> # ... 还有51行
基于OP的进一步要求
如果可能，最好在data.frame中创建一个新列，指定rt中的每一行，不管该行是否被视为异常值。但我不知道如何才能做到这一点
在这里，您可以通过groupby
和summary
获得结果。
您可以根据需要调整->任何内容：
library(dplyr)
RTs %>%
group_by(subject, trial_type) %>%
summarise(mean= mean(rt), sd = sd(rt), Upper = 2.5*sd + mean, Lower = mean - 2.5*sd,
OutliersUpper <- rt > Upper, OutliersLower <- rt < Lower)
库（dplyr）
RTs%>%
分组依据（受试者、试验类型）%>%
总结（平均值=平均值（rt），标准差=标准差（rt），上限值=2.5*sd+平均值，下限值=平均值-2.5*sd，
异常值上限，异常值下限%
总结（平均值=平均值（rt），标准差=标准差（rt），上限值=2.5*sd+平均值，下限值=平均值-2.5*sd，
离群值越高，离群值越低在这里，您可以通过groupby
和summary
获得结果。
您可以根据需要调整->任何内容：
library(dplyr)
RTs %>%
group_by(subject, trial_type) %>%
summarise(mean= mean(rt), sd = sd(rt), Upper = 2.5*sd + mean, Lower = mean - 2.5*sd,
OutliersUpper <- rt > Upper, OutliersLower <- rt < Lower)
库（dplyr）
RTs%>%
分组依据（受试者、试验类型）%>%
总结（平均值=平均值（rt），标准差=标准差（rt），上限值=2.5*sd+平均值，下限值=平均值-2.5*sd，
异常值上限，异常值下限%
总结（平均值=平均值（rt），标准差=标准差（rt），上限值=2.5*sd+平均值，下限值=平均值-2.5*sd，
离群值越高，离群值越低其他答案的概括版本
首先，将现有筛选转换为函数：
dropOutliers <- function(.x, .y, multiplier=2.5) {
limits <- .x %>%
group_by(trial_type) %>%
summarise(
SD=sd(rt),
Mean=mean(rt),
Lower=Mean - multiplier * SD,
Upper=Mean + multiplier * SD
)
.x %>%
left_join(
limits,
by="trial_type"
) %>%
filter(rt >= Lower && rt <= Upper) %>%
select(-SD, -Mean, -Upper, -Lower)
}
这似乎不会删除任何行，因此应用更深入的筛选来检查：
d %>% group_by(subject) %>% group_map(dropOutliers, multiplier=1) %>% bind_rows()
# A tibble: 16 x 4
rt condition trial_type accuracy
<int> <fct> <fct> <int>
1 873 reliable switch 1
2 1185 reliable same 1
3 1752 reliable same 1
4 2037 reliable same 1
5 4849 reliable switch 1
6 2975 reliable switch 0
7 1621 reliable switch 0
8 1235 reliable same 1
9 3008 reliable switch 0
10 1560 reliable same 1
11 1075 reliable switch 0
12 4596 reliable same 1
13 1129 reliable same 1
14 1093 reliable switch 0
15 1302 reliable same 1
16 1414 reliable switch 0
d%%>%groupby（subject）%%>%groupmap（dropOutliers，乘数=1）%%>%bind\u行（）
#一个tibble:16 x 4
rt条件试验类型精度
1873可靠开关1
2 1185可靠相同的1
3 1752可靠相同的1
4 2037可靠相同1
5 4849可靠开关1
6 2975可靠开关0
7 1621可靠开关0
8 1235可靠相同1
9 3008可靠开关0
10 1560可靠相同的1
11 1075可靠开关0
12 4596可靠相同1
13 1129可靠的相同1
14 1093可靠开关0
15 1302可靠的相同1
16 1414可靠开关0
其他答案的概括版本
首先，将现有筛选转换为
RTs %>%
group_by(subject, trial_type, condition, accuracy) %>%
summarise(mean= mean(rt), sd = sd(rt), Upper = 2.5*sd + mean, Lower = mean - 2.5*sd,
OutliersUpper <- rt > Upper, OutliersLower <- rt < Lower)
dropOutliers <- function(.x, .y, multiplier=2.5) {
limits <- .x %>%
group_by(trial_type) %>%
summarise(
SD=sd(rt),
Mean=mean(rt),
Lower=Mean - multiplier * SD,
Upper=Mean + multiplier * SD
)
.x %>%
left_join(
limits,
by="trial_type"
) %>%
filter(rt >= Lower && rt <= Upper) %>%
select(-SD, -Mean, -Upper, -Lower)
}
d %>% group_by(subject) %>% group_map(dropOutliers) %>% bind_rows()
d %>% group_by(subject) %>% group_map(dropOutliers, multiplier=1) %>% bind_rows()
# A tibble: 16 x 4
rt condition trial_type accuracy
<int> <fct> <fct> <int>
1 873 reliable switch 1
2 1185 reliable same 1
3 1752 reliable same 1
4 2037 reliable same 1
5 4849 reliable switch 1
6 2975 reliable switch 0
7 1621 reliable switch 0
8 1235 reliable same 1
9 3008 reliable switch 0
10 1560 reliable same 1
11 1075 reliable switch 0
12 4596 reliable same 1
13 1129 reliable same 1
14 1093 reliable switch 0
15 1302 reliable same 1
16 1414 reliable switch 0