Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

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

Re: st: test of significant between coefficients

From   Andrea Rispoli <[email protected]>
To   [email protected]
Subject   Re: st: test of significant between coefficients
Date   Tue, 27 Sep 2011 16:30:08 +0100

Richard, Nick, thank you very much

On Tue, Sep 27, 2011 at 4:12 PM, Nick Cox <[email protected]> wrote:
> I think it makes about as much sense as any other significance test.
> But what it means and how useful it is depend on the problem. For
> example, two predictors may both be non-significant at conventional
> levels because they are fighting for the same predictive share. The
> way forward is likely to be not to quantify the problem by yet another
>  significance test, but to try to identify the better predictor to
> use.
> Also, watch out. If what you are doing is looking at some significance
> test results and wondering about doing more tests, then this divides
> the world. Some deride this as data snooping and want to underline how
> bad a strategy this is for scientific inference. Others regard this as
> among the allowed tricks of intelligent data analysis in which you are
> alive to all the things the data can tell you about their structure.
> In many fields there is a sanctioned hypocrisy whereby you write up
> the last model as if it flows automatically from the hypotheses you
> now claim you had at the outset.
> On Tue, Sep 27, 2011 at 3:35 PM, Andrea Rispoli <[email protected]> wrote:
>> I am running a test of significance between two coefficients of the
>> same OLS regression.
>> My question is : if the two coefficients are not significant, does it
>> still make sense to conduct the test? I am asking because sometimes
>> while the individual coefficients are not significant the difference
>> between them is significant, so I was trying to understand the meaning
>> of this result.
> *
> *   For searches and help try:
> *
> *
> *

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index