1

这是我拥有的数据，我使用 proc tabulate 来呈现它在 excel 中的呈现方式，并使可视化更容易。目标是确保组严格低于对角线（我知道它是一个矩形，（1,1）（2,2）...（7,7）“对角线”）卷起列直到它碰到对角线或使组大小至少为 75。

      1   2   3    4    5    6   7  (month variable)
(age)
  1  80  90  100  110  122  141 88
  2  80  90  100  110   56   14 88
  3  80  90   87   45   12   41 88
  4  24  90  100  110   22  141 88
  5  0   1    0    0    0    0   2
  6  0   1    0    0    0    0   6
  7  0   1    0    0    0    0   2
  8  0   1    0    0    0    0  11

我已经使用 if/thens 重新组合某些数据值，但我需要一种通用方法来为其他集合执行此操作。提前致谢

期望的结果

   1  2   3    4    5    6   7  (month variable)
(age)
  1  80  90  100  110  122  141 88
  2  80  90  100  110   56   14 88
  3  104 90   87   45   12   41 88
  4  0   94  100  110   22  141 88
  5  0   0    0    0    0    0   2
  6  0   0    0    0    0    0   6
  7  0   0    0    0    0    0   13
  8  0   0    0    0    0    0   0
4

1 回答 1

0

为一些必须统计的患者模拟一些分类数据

data mock;
  do patient_id = 1 to 2500;
    month = ceil(7*ranuni(123));
    age = ceil(8*ranuni(123));
    output;
  end;
  stop;
run;

创建一个与问题中所示相似的计数 (N) 列表：

options missing='0';

proc tabulate data=mock;
  class month age;
  table age,month*n=''/nocellmerge;
run;

每个月获取次对角线患者数量

proc sql;
/*  create table subdiagonal_column as */
  select month, count(*) as subdiag_col_freq
  from mock
  where age > month
  group by month;

对于每一行，获取对角线前的患者人数

/*  create table prediagonal_row as */
  select age, count(*) as prediag_row_freq
  from mock
  where age > month
  group by age;

如果分类值不是 +1 单调的，则其他集合可能会很棘手。要对非单调分类值执行类似的过程，您需要创建 +1 单调的代理变量。例如：

data mock;
  do item_id = 1 to 2500;
    pet = scan ('cat dog snake rabbit hamster', ceil(5*ranuni(123)));
    place = scan ('farm home condo apt tower wild', ceil(6*ranuni(123)));
    output;
  end;
run;

proc tabulate data=mock;
  class pet place;
  table pet,place*n=''/nocellmerge;
run;

proc sql;
  create table unq_pets as select distinct pet from mock;
  create table unq_places as select distinct place from mock;

data pets;
  set unq_pets;
  pet_num = _n_;
run;

data places;
  set unq_places;
  place_num = _n_;
run;

proc sql;
  select distinct place_num, mock.place, count(*) as subdiag_col_freq
  from mock 
  join pets on pets.pet = mock.pet
  join places on places.place = mock.place
  where pet_num > place_num
  group by place_num
  order by place_num
  ;
于 2017-12-06T10:16:59.003 回答