Unequal number of observations in percentile groups

[Stephen Okiya]

Hi Stata users,

I am trying to come up with percentile groups using the code below

_pctile asset_index, nquantiles(100)
return list
forval i=1/99 {
local p`i' = (r(r`i'))
}

gen percent = .
replace percent = 1 if asset_index < `p1'
replace percent = 100 if asset_index > `p99' & asset_index < .
forval i=1/98 {
di "``i''"
local j = `i' + 1
di "lower `p`i''"
di "upper `p`j''"
replace percent = `i' + 1 if inrange(asset_index, `p`i'', `p`j'')
}
ta percent

I am noticing that there are groups with extremely few number of observations such as 3 or 5. I am not sure whether the syntax is wrong or my understanding of how percentiles are calculated is misinformed.

Am attaching the dataset since

dataex

may not be the most effective way of sharing 9097 observations

Any advice is welcome.

Thanks in advance!

[Fei Wang]

One line of code is sufficient. It seems one group has 5 obs while others are reasonably large.

xtile percent = asset_index, n(100)

. tab percent, sort

        100 |
  quantiles |
         of |
asset_index |      Freq.     Percent        Cum.
------------+-----------------------------------
         33 |        281        3.10        3.10
         27 |        258        2.84        5.94
         38 |        255        2.81        8.75
         21 |        236        2.60       11.35
         16 |        221        2.44       13.79
         12 |        207        2.28       16.07
         50 |        200        2.20       18.27
         46 |        199        2.19       20.46
         24 |        185        2.04       22.50
         18 |        180        1.98       24.48
         53 |        168        1.85       26.34
         40 |        162        1.79       28.12
         31 |        158        1.74       29.86
         43 |        148        1.63       31.49
          5 |        145        1.60       33.09
         26 |        139        1.53       34.62
         66 |        138        1.52       36.14
          9 |        136        1.50       37.64
         14 |        130        1.43       39.07
         10 |        126        1.39       40.46
         84 |        120        1.32       41.79
         82 |        113        1.25       43.03
          3 |        112        1.23       44.26
         58 |        112        1.23       45.50
         64 |        112        1.23       46.73
         67 |        110        1.21       47.94
         70 |        109        1.20       49.15
         49 |        107        1.18       50.33
         55 |        106        1.17       51.49
         20 |        103        1.13       52.63
          2 |        102        1.12       53.75
         68 |        102        1.12       54.88
          1 |         98        1.08       55.96
         36 |         98        1.08       57.04
         81 |         98        1.08       58.12
         63 |         97        1.07       59.18
         88 |         97        1.07       60.25
         61 |         96        1.06       61.31
         90 |         96        1.06       62.37
         74 |         95        1.05       63.42
         80 |         95        1.05       64.46
         97 |         94        1.04       65.50
         56 |         93        1.02       66.52
         76 |         93        1.02       67.55
         85 |         93        1.02       68.57
         94 |         93        1.02       69.60
          7 |         92        1.01       70.61
         71 |         91        1.00       71.61
         92 |         91        1.00       72.62
         99 |         91        1.00       73.62
         45 |         90        0.99       74.61
         78 |         90        0.99       75.60
         96 |         90        0.99       76.60
        100 |         90        0.99       77.59
         72 |         89        0.98       78.57
         79 |         89        0.98       79.55
         93 |         89        0.98       80.53
          6 |         88        0.97       81.50
         91 |         88        0.97       82.47
         95 |         88        0.97       83.44
         98 |         88        0.97       84.41
         59 |         86        0.95       85.36
         62 |         84        0.93       86.28
         89 |         84        0.93       87.21
         77 |         83        0.91       88.12
         73 |         80        0.88       89.00
         75 |         79        0.87       89.87
         87 |         78        0.86       90.73
         60 |         76        0.84       91.57
         37 |         72        0.79       92.36
         86 |         72        0.79       93.16
          8 |         70        0.77       93.93
         57 |         65        0.72       94.64
         65 |         63        0.69       95.34
         48 |         61        0.67       96.01
         52 |         58        0.64       96.65
         83 |         57        0.63       97.28
          4 |         53        0.58       97.86
         44 |         46        0.51       98.37
         30 |         37        0.41       98.78
         42 |         37        0.41       99.18
         32 |         26        0.29       99.47
         69 |         22        0.24       99.71
         54 |         21        0.23       99.94
         15 |          5        0.06      100.00
------------+-----------------------------------
      Total |      9,075      100.00

[Stephen Okiya]

Thanks so much Fei Wang for your help. This is great!!

[Nick Cox]

This overlaps with your earlier thread https://www.statalist.org/forums/for...centile-groups

Please don't run two or more threads on the same topic.

[Stephen Okiya]

Nick Cox Well noted!