0

I am performing the quantile regression in R on a non linear model. I am getting the coefficients for the desired quantiles (tau = 0.05, 0.50, 0.95). All very nice, but running the code without reasoning is not good enough. As we determine quantiles at the extremes, i.e. 0.05, 0.95 but also smaller/larger, the regression results will be dependent on the number of points in the data sample. My questions are:

  • Are there any rules for determining the minimum number of samples (sample size) needed to perform such quantile regressions?
  • How do we determine the confidence LEVEL of the quantile regression, e.g. at 0.05? (Level, not interval... I mean, if I get a regression line for tau = 0.05 how much is its confidence level? Or am I thinking wrong?.. I used as tag "confidence-interval" because "confidence-Level" was not allowed)

If there is literature with indications, I will gladly read it... if possible with practical rules without complicated theorems.

Thank you all very much!

M B
  • 3
  • 1
  • 1
    This is not really a specific programming question that's appropriate for Stack Overflow. If you need help choosing statistically appropriate models for your data, you should ask for help at [stats.se] instead. You are likely to get better help there. – MrFlick Aug 01 '23 at 15:13
  • Ah, okay, all right, thanks for the suggestion, I will try that community as well. The thing is that thinking about a practical problem, i.e. the 0.05 quantile regression where initial values can be used to determine the coefficients, these coefficients will be more or less sensitive to the initial values depending on the sample size. So I thought there were some practical rules that could be used. – M B Aug 02 '23 at 09:04

0 Answers0