如何两两比较多次测量的增减？

我有一个数据，我想通过取差值来两两比较测量值，如果差值大于 0.2，则添加另一列为“是”，否则为“否”。就像图像中的示例数据一样。并且，在每个人的最后，如果至少有一个“是”，则最终结果为“是”。我已手动填写第一行，但我想对我的所有个人（1000 个人）执行相同的操作。在此输入图像描述 https://i.stack.imgur.com/2Ee83.png

library(readxl)
dd <- read_excel("dd.xlsx")
dd <- dput(dd)
structure(list(ID = c(1, 2, 3, 4, 5, 6), m1 = c("2.1", "1.4","NA", "4.0", "2.5", "NA"), 
               m2 = c("2.8", "1.5", "NA", "4.0", "3.8", "1.1"),
               m3 = c("3.5", "1.5", "NA", "4.0", "NA", "1.3"), 
               m4 = c("NA", "1.8", "1.8", "4.0", "NA", "1.3"), 
               m5 = c("NA","1.5", "2.9", "NA", "NA", "1.5"), 
               m6 = c("NA", "NA", "3.5", "NA", "NA", "1.2")), 
          class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, -6L))

这种方法使用更长的枢轴来估计您的列，然后通过重命名更宽的枢轴将为您提供您想要的内容（请参阅第二个解决方案）。但是，如果您只是想要Final列，按 ID，只需执行以下操作：

1. 获取的简单方法Final by ID

dd %>% 
  pivot_longer(cols = !ID) %>%
  mutate(value=as.numeric(value)) %>% 
  group_by(ID) %>% 
  summarize(Final = any(value-lag(value)>0.2))

2. 如果您确实想要所有这些中间变量，请使用扩展方法

dd %>% 
  pivot_longer(cols = !ID) %>%
  mutate(value=as.numeric(value)) %>% 
  group_by(ID) %>% 
  mutate(diff=value-lag(value),
         gt=if_else(diff>0.2, "Yes", "No")) %>% 
  pivot_wider(id_cols = ID,names_from = name,values_from = value:gt) %>% 
  rowwise() %>% 
  mutate(Final = any(c_across(starts_with("gt"))=="Yes")) %>% 
  select(!c(diff_m1,gt_m1)) %>% 
  rename_with(~c("ID", "m1","m2","m3","m4","m5","m6",
                 "m2-m1", "m3-m2", "m4-m3", "m5-m4", "m6-m5",
                 "r(m2-m1)", "r(m3-m2)", "r(m4-m3)", "r(m5-m4)", "r(m6-m5)",
                 "Final"), .cols = everything()
  )

Output:

     ID    m1    m2    m3    m4    m5    m6 `m2-m1` `m3-m2` `m4-m3` `m5-m4` `m6-m5` `r(m2-m1)` `r(m3-m2)` `r(m4-m3)`
  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl> <chr>      <chr>      <chr>     
1     1   2.1   2.8   3.5  NA    NA    NA     0.7       0.7    NA      NA      NA   Yes        Yes        NA        
2     2   1.4   1.5   1.5   1.8   1.5  NA     0.100     0       0.3    -0.3    NA   No         No         Yes       
3     3  NA    NA    NA     1.8   2.9   3.5  NA        NA      NA       1.1     0.6 NA         NA         NA        
4     4   4     4     4     4    NA    NA     0         0       0      NA      NA   No         No         No        
5     5   2.5   3.8  NA    NA    NA    NA     1.3      NA      NA      NA      NA   Yes        NA         NA        
6     6  NA     1.1   1.3   1.3   1.5   1.2  NA         0.2     0       0.2    -0.3 NA         No         No        
# … with 3 more variables: `r(m5-m4)` <chr>, `r(m6-m5)` <chr>, Final <lgl>