Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: =?utf-8?B?UkU6IFJFOiBSRTogUkU6IFJFOiBSRTogUkU6IHN0OiA=?==?utf-8?B?wrTDsMK4wrQ6IHN0OiBIb3cgdG8gY2hvb3NlIGEgcHJvcGVy?==?utf-8?B?IG1vZGVsIGlmIHRoZSBkZXBlbmRlbnQgdmFyaWFibGU=?==?utf-8?B?IGlzIHdpdGhpbiBib3VuZHM/?=

From   "Cheng, Xiaoqiang" <>
To   <>
Subject   st: =?utf-8?B?UkU6IFJFOiBSRTogUkU6IFJFOiBSRTogUkU6IHN0OiA=?==?utf-8?B?wrTDsMK4wrQ6IHN0OiBIb3cgdG8gY2hvb3NlIGEgcHJvcGVy?==?utf-8?B?IG1vZGVsIGlmIHRoZSBkZXBlbmRlbnQgdmFyaWFibGU=?==?utf-8?B?IGlzIHdpdGhpbiBib3VuZHM/?=
Date   Mon, 2 Oct 2006 15:54:20 +0200

Thank you very much.

To make it clear, let's forget what I have said.

What I want to know is, since dy/dx is the approximate slope and it should be explained as how much y will change respect to one unit change of x. In this case, I guess it will be right if we devide the value of the slope by 100 in order to know how much y will change respect to 1/100 unit change of x.


Xiaoqiang Cheng

University of Leuven
Tel  +32 16 326853
Fax  +32 16 326796
Mail  Xiaoqiang Cheng
      Center for Economic Studies
      University of Leuven
      Naamsestraat 69
      Leuven,  Belgium

-----Original Message-----
From: [] On Behalf Of Nick Cox
Sent: 2006年10月2日 15:44
Subject: st: RE: RE: RE: RE: RE: RE: st: ´ð¸´: st: How to choose a proper model if the dependent variable is within bounds?

Stata does not know anything about your variables
that you have not told it. Thus, if you use certain 
units in your dataset, but wish to change to other 
units, the translation is your responsibility. 

I don't know if this answers the question, which 
doesn't seem at all clear to me: for example, what 
is reality, independent of choice of units? 


Cheng, Xiaoqiang
> Can we think an alternative of your previous suggestion about 
> the prediction of dy/dx when it exceeds unit? 
> One example will be: if the prediction exceeds unit and x is 
> counted in 100s (one unit of x in sample data means 100 in 
> reality. For instance, x stands for kilometres. In reality, 
> the distance from Brussels to Leuven is 20 km, but in our 
> sample we count the distance as 0.2), can we interpret the 
> dy/dx by, lets say, one unit of x increase in reality, the y 
> will increase (dy/dx)/100?

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2022 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index