Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: How do I summarize and report predicted medians after qreg command?


From   I M <[email protected]>
To   <[email protected]>
Subject   st: How do I summarize and report predicted medians after qreg command?
Date   Tue, 20 Jan 2009 09:26:57 -0800

Hello,

Thank you in advance.

If I want to report the adjusted (predicted) median price (see example below), adjusted for weight and mpg, which summary statistic should I use?

Also, I know that I can easily do this using the 'adjust' command as well, but my question is: If I wanted to report the adjusted median, do I want to report the median (50%ile) or the mean "of the predicted median"?




See example:


---begin---

sysuse auto, clear
qreg price weight mpg
predict adjustedprice, xb
sum adjustedprice, d

---end---






. sum adjustedprice, d

                      Linear prediction
-------------------------------------------------------------
      Percentiles      Smallest
 1%     3364.087       3364.087
 5%     3754.391       3673.913
10%     4097.478       3737.043       Obs                  74
25%     4592.348       3754.391       Sum of Wgt.          74

50%     5311.543                      Mean           5193.156
                        Largest       Std. Dev.      780.0377
75%     5792.217           6303
90%     6129.522       6418.652       Variance       608458.9
95%         6303       6772.348       Skewness      -.2198667
99%     6841.739       6841.739       Kurtosis       2.374105





1. Note that I run my quantile regression model, which essentially generates my predicted median price (adjusting for weight and mpg) (the qreg command).

2. I then generate the predicted values using linear prediction (the predict command).

3. I then summarize the data.

4. Now, if I want to report predicted medians, do I want to use the 50% (median) of the adjusted price, or the mean of the adjusted price (noting that the qreg command provides predicted medians already)?

Thank you


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index