在面板中生成引导变量

Question

我想通过 CMA、Province 和 Year 生成潜在客户收入变量 V1，如下所示：

CMA  Province  Year  Income  V1
TO      A      1990        
TO      A      1991        .
TO      A      1991        .
MT      A      1990       
MT      A      1991        .
MT      A      1991        .
AB      B      1990        
AB      B      1991       .
AB      B      1991       .

我正在使用以下代码，但我只得到缺失值：

gsort CMA Province -Year Income
gen ld_inc = Income[_n-1] if Year == Year[_n-1] + 1
replace ld_inc = ld_inc[_n-1] if Year == Year[_n-1] & missing(ld_inc)

我的代码有问题吗？我哪里出错了？

Answer 1

以下适用于您的示例：

clear

input str2 CMA str2 Province Year Income V1
"TO"  "A" 1990  5  8
"."   "." 1991  8  .
"MT"  "A" 1990 12  7
"."   "." 1991  7  .
"AB"  "B" 1990  5 15
"."   "." 1990 15  .
end

generate V2 = Income[_n+1] if CMA != "."

list, separator(0)

     +------------------------------------------+
     | CMA   Province   Year   Income   V1   V2 |
     |------------------------------------------|
  1. |  TO          A   1990        5    8    8 |
  2. |   .          .   1991        8    .    . |
  3. |  MT          A   1990       12    7    7 |
  4. |   .          .   1991        7    .    . |
  5. |  AB          B   1990        5   15   15 |
  6. |   .          .   1991       15    .    . |
     +------------------------------------------+

但是，通常应该使用如下标识符来完成：

egen id = seq(), block(2)
bysort id (Year Province): generate V3 = Income[_n+1]

order id
list, separator(0)

     +----------------------------------------------------+
     | id   CMA   Province   Year   Income   V1   V2   V3 |
     |----------------------------------------------------|
  1. |  1    TO          A   1990        5    8    8    8 |
  2. |  1     .          .   1991        8    .    .    . |
  3. |  2    MT          A   1990       12    7    7    7 |
  4. |  2     .          .   1991        7    .    .    . |
  5. |  3    AB          B   1990        5   15   15   15 |
  6. |  3     .          .   1991       15    .    .    . |
     +----------------------------------------------------+

编辑：

使用你的新例子，事情就更简单了：

clear

input str2 CMA  str1 Province  Year  Income  V1
TO      A      1990   5     8
TO      A      1991   8     .
TO      A      1991   8     .
MT      A      1990   12    7
MT      A      1991   7     .
MT      A      1991   7     .
AB      B      1990   5     15
AB      B      1991   15    .
AB      B      1991   15    .
end

bysort CMA (Year Province): generate V2 = Income[_n+1] if _n == 1

list, sepby(CMA)

     +------------------------------------------+
     | CMA   Province   Year   Income   V1   V2 |
     |------------------------------------------|
  1. |  AB          B   1990        5   15   15 |
  2. |  AB          B   1991       15    .    . |
  3. |  AB          B   1991       15    .    . |
     |------------------------------------------|
  4. |  MT          A   1990       12    7    7 |
  5. |  MT          A   1991        7    .    . |
  6. |  MT          A   1991        7    .    . |
     |------------------------------------------|
  7. |  TO          A   1990        5    8    8 |
  8. |  TO          A   1991        8    .    . |
  9. |  TO          A   1991        8    .    . |
     +------------------------------------------+

在面板中生成引导变量

Generate a lead variable in a panel

panel

stata