Too many ties in Y. Cant use quantile regression.

[ajay pasi]

It's crucial for my analysis to estimate how the independent variable (X) affects the dependent variable (Y) across various levels of Y. I've come to realize that quantile regression isn't the appropriate approach. As I have too many ties in Y. What alternative method should I pursue?

nblind75_bl |
   ind_diff |      Freq.     Percent        Cum.
------------+-----------------------------------
        -60 |          2        0.02        0.02
        -59 |          1        0.01        0.03
        -57 |          1        0.01        0.04
        -54 |          1        0.01        0.04
      -53.5 |          1        0.01        0.05
        -53 |          1        0.01        0.06
        -52 |          3        0.03        0.09
      -51.5 |          2        0.02        0.11
        -51 |          1        0.01        0.12
      -50.5 |          1        0.01        0.13
        -50 |          3        0.03        0.15
      -49.5 |          1        0.01        0.16
        -49 |          3        0.03        0.19
      -48.5 |          2        0.02        0.21
     -48.25 |          1        0.01        0.21
        -48 |          4        0.04        0.25
      -47.5 |          1        0.01        0.26
        -47 |          3        0.03        0.29
      -46.5 |          1        0.01        0.30
        -46 |          3        0.03        0.32
      -45.5 |          1        0.01        0.33
        -45 |          3        0.03        0.36
        -44 |          3        0.03        0.38
      -43.5 |          1        0.01        0.39
        -43 |          5        0.04        0.44
      -42.5 |          4        0.04        0.47
        -42 |          3        0.03        0.50
     -41.75 |          1        0.01        0.51
      -41.5 |          4        0.04        0.55
        -41 |          9        0.08        0.63
      -40.5 |          5        0.04        0.67
        -40 |          8        0.07        0.74
      -39.5 |          2        0.02        0.76
     -39.25 |          1        0.01        0.77
        -39 |          8        0.07        0.84
      -38.5 |          1        0.01        0.85
     -38.25 |          1        0.01        0.86
        -38 |         13        0.12        0.97
      -37.5 |          3        0.03        1.00
     -37.25 |          1        0.01        1.01
        -37 |         14        0.13        1.14
      -36.5 |          2        0.02        1.15
        -36 |         15        0.13        1.29
     -35.86 |          1        0.01        1.30
      -35.5 |          6        0.05        1.35
        -35 |         19        0.17        1.52
      -34.5 |          5        0.04        1.56
        -34 |         14        0.13        1.69
      -33.5 |          2        0.02        1.71
        -33 |         18        0.16        1.87
      -32.5 |          4        0.04        1.90
        -32 |         19        0.17        2.07
     -31.75 |          1        0.01        2.08
      -31.5 |          6        0.05        2.14
        -31 |         22        0.20        2.33
     -30.75 |          1        0.01        2.34
      -30.5 |          4        0.04        2.38
     -30.25 |          2        0.02        2.40
        -30 |         41        0.37        2.76
      -29.5 |          5        0.04        2.81
        -29 |         34        0.30        3.11
      -28.5 |         15        0.13        3.25
     -28.36 |          1        0.01        3.25
        -28 |         41        0.37        3.62
      -27.5 |          7        0.06        3.68
     -27.25 |          1        0.01        3.69
        -27 |         52        0.46        4.16
     -26.75 |          2        0.02        4.17
      -26.5 |          9        0.08        4.26
     -26.25 |          1        0.01        4.26
        -26 |         50        0.45        4.71
     -25.75 |          1        0.01        4.72
      -25.5 |         15        0.13        4.85
     -25.25 |          3        0.03        4.88
        -25 |         38        0.34        5.22
      -24.5 |          9        0.08        5.30
     -24.11 |          1        0.01        5.31
        -24 |         57        0.51        5.82
      -23.5 |          8        0.07        5.89
     -23.25 |          1        0.01        5.90
     -23.11 |          1        0.01        5.91
        -23 |         57        0.51        6.42
     -22.75 |          1        0.01        6.43
      -22.5 |         19        0.17        6.60
     -22.25 |          1        0.01        6.61
        -22 |         55        0.49        7.10
     -21.75 |          1        0.01        7.11
      -21.5 |          8        0.07        7.18
        -21 |         84        0.75        7.93
      -20.5 |         16        0.14        8.07
        -20 |         67        0.60        8.67
     -19.75 |          1        0.01        8.68
      -19.5 |         18        0.16        8.84
     -19.25 |          1        0.01        8.85
        -19 |         78        0.70        9.55
      -18.5 |         14        0.13        9.67
        -18 |         85        0.76       10.43
      -17.5 |         21        0.19       10.62
     -17.25 |          1        0.01       10.63
        -17 |         96        0.86       11.49
     -16.75 |          1        0.01       11.50
      -16.5 |         21        0.19       11.68
        -16 |        108        0.97       12.65
     -15.75 |          1        0.01       12.66
      -15.5 |         23        0.21       12

[Nick Cox]

Show us a scatter plot of the data.

[John Mullahy]

You might take a look at this paper by Machado and Joao Santos Silva

https://www.tandfonline.com/doi/abs/...14505000000330

Since your outcome variable appears to be measured on an evenly spaced grid (with increments of 0.25) then it has a "count-like" character and the Machado-Santos Silva results may be useful.