R help - May 2006 - factor analysis - discrepancy in results from R vs. Stata

Hi,

I found a discrepancy between results in R and Stata for a factor analysis
with a promax rotation.  For Stata:

. *rotate, factor(2) promax*



            (promax rotation)

               Rotated Factor Loadings

    Variable |      1          2    Uniqueness

-------------+--------------------------------

pfq_amanag~y |  -0.17802    0.64161    0.70698

pfq_bwalk_~ø |   0.72569    0.05570    0.41706

pfq_cwalk_~s |   0.78938   -0.03497    0.41200

pfq_dkneel~g |   0.80165   -0.04188    0.39979

pfq_elifting |   0.58700    0.19396    0.46795

pfq_fhouse~e |   0.50086    0.38770    0.34323

  pfq_gmeals |   0.03516    0.75884    0.38781

pfq_hwalki~s |   0.15942    0.52766    0.58543

pfq_istand~r |   0.46516    0.29058    0.52127

pfq_jget_i~d |   0.31819    0.43345    0.52934

   pfq_kfork |   0.02458    0.48797    0.74549

pfq_ldress~g |   0.11193    0.63987    0.48377

pfq_mstand~s |   0.73177    0.07817    0.38311

pfq_nsitti~g |   0.49535    0.16943    0.61545

pfq_oreach~d |   0.34980    0.27156    0.67887

pfq_pgrasp~l |   0.26975    0.21778    0.80248

pfq_qgo_mo~s |   0.25753    0.65296    0.28598

pfq_rsocia~t |   0.14482    0.72348    0.31770

pfq_sleisu~e |  -0.06316    0.69822    0.56654

For R:

*factanal(x = matrix, factors = 2, rotation = "promax")*



Loadings:

                     Factor1 Factor2

pfq_amanage_money     0.769

pfq_bwalk_mileø               0.925

pfq_cwalk_steps               0.977

pfq_dkneeling         0.802   0.152

pfq_elifting          0.812   0.114

pfq_fhouse_chore      0.884

pfq_gmeals            0.920

pfq_hwalking_rooms    0.963

pfq_istand_chair      0.927

pfq_jget_in_out_bed   0.951

pfq_kfork             0.846

pfq_ldressing         0.947

pfq_mstanding_hours   0.844

pfq_nsitting_long     0.795

pfq_oreach_over_head  0.856

pfq_pgrasp_small      0.814

pfq_qgo_movies        0.971

pfq_rsocial_event     0.930

pfq_sleisure_home     0.811

This is just one example -- all other comparisons with a different number of
factors, with and without rotation, generated different numbers.  Any
thoughts from the list members on the reasons for the discrepancy?

thanks,


Ricardo Pietrobon, MD, PhD
Duke University Health System

	[[alternative HTML version deleted]]

I don't believe promax is uniquely defined.  Not only are there 
differences in the criterion (R allows a choice), it is an optimization 
problem with multiple local optima.

In fact the same is true of factanal, and the first thing to check would 
be to see if the same FA solution has been found.

On Fri, 19 May 2006, Ricardo Pietrobon wrote:
> Hi,
>
> I found a discrepancy between results in R and Stata for a factor analysis
> with a promax rotation.  For Stata:
[...]
> This is just one example -- all other comparisons with a different number
of
> factors, with and without rotation, generated different numbers.  Any
> thoughts from the list members on the reasons for the discrepancy?
>
> thanks,
>
>
> Ricardo Pietrobon, MD, PhD
> Duke University Health System
>
> 	[[alternative HTML version deleted]]
PLEASE don't send HTML code but properly formatted ASCII text.

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595