Statalist


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

Re: st: clarification on interpreting Stock&Yogo- maximal IV "size"


From   "Nirina F" <[email protected]>
To   [email protected]
Subject   Re: st: clarification on interpreting Stock&Yogo- maximal IV "size"
Date   Wed, 26 Sep 2007 10:58:32 -0400

Great!!! I understand it much better now. Many thanks Austin.

On 9/25/07, Austin Nichols <[email protected]> wrote:
> Nirina F <[email protected]>:
> Looks your bias is relatively small (less than 5% of OLS) but the size
> distortion is potentially large (more than 15% rejection rate with a
> 5% alpha). -findit condivreg- or -net install st0033_2.pkg- to get a
> program due to Mikusheva and Poi (2006) to conduct hypothesis tests
> robust to weak instruments, for the case of a single endog regressor
> and i.i.d. errors.  With more than one endog regressor or non-iid
> errors, you may want to use the Anderson and Rubin (1949)
> approach--see
> http://www.stata.com/meeting/5nasug/wiv.pdf
> for full references and some discussion (esp. slide titled "AR
> Confidence Sets").
>
> On 9/25/07, Nirina F <[email protected]> wrote:
> > ------------------------------------------------------------------------------
> > Weak identification test (Cragg-Donald Wald F statistic):               58.734
> > Stock-Yogo weak ID test critical values:  5% maximal IV relative bias    21.30
> >                                         10% maximal IV relative bias    11.10
> >                                         20% maximal IV relative bias     5.86
> >                                         30% maximal IV relative bias     4.07
> >                                         10% maximal IV size            141.08
> >                                         15% maximal IV size             72.44
> >                                         20% maximal IV size             49.26
> >                                         25% maximal IV size             37.65
> > Source: Stock-Yogo (2005).  Reproduced by permission.
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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