Problem with lpolyci graph using Stata 15 vs 17

[Gaia Gaudenzi]

Hi everybody!


I am using Stata 17. While running the code below:

sysuse auto, clear
    
reghdfe price headroom weight , absorb(i.trunk)  resid
predict y_hat, res
    
twoway (lpolyci price headroom,  n(100) ciplot(rline) pstyle(ci2) lcolor(lavender) lwidth(medthick)  blpattern(dash)   )

I obtain a graph, while my colleague, who runs exactly the same code from another laptop (which has Stata 15) gets a different graph.

I tried to solve the issue by putting "version 15:" in front of the graph, but it did not work. I could not find a workaround for this problem on Google. Does anybody know what I can try?

Thank you very much in advance!

[Leonardo Guizzetti]

In Stata 16, there was this update:

------ update 15dec2020 ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

     4. lpoly, in the default case of kernel epanechnikov with the rule-of-thumb bandwidth estimator, produced an incorrect value for the bandwidth estimate.  This also affected the default pilot bandwidth
        used for the standard-error computation with kernel epanechnikov.  The estimated bandwidth value was larger than it should have been, which led to oversmoothing.  The constant in the rule-of-thumb
        estimator incorrectly integrated over the interval [-1, 1] instead of the correct interval [-sqrt(5), sqrt(5)].  This has been fixed.