Prev: Observed rate ratio VS model rate ratio
Next: Fw: extracting numbers from a string
From: Vivian Pun on 28 Dec 2009 17:28
Hi SAS users,

When I analyze the rate of injury by hospital teaching status. I
calculate the average injury rates by teaching status:
Rate Rate ratio
Teaching 26/1000 FTEs 26/18 = 1.44
Non-teaching 18/1000 FTEs reference

I have tried two ways (there could be more ways) to import the
injury count data into SAS.
OPTION 1: use SAS datalines option such as:
data data1;
input teaching count total_fte;
l_fte=log(total_fte);
datalines;
No 6041 332967.7441
Yes 12778 490319.0468
;
run;
*This option is simple, but doesn't allow a more complicated
model multivariate testing.

OPTION 2: use count dataset that include breakdown of all
variables, such as:
year quarter count total_fte teaching bedcat ....
2002 3 23 2345 No
1 .....
2004 1 100 100322 Yes
2 .....
*This option does allow a more complicated model multivariate
testing.

When I fit the data from either OPTION into a Poisson model, an
crude univariate poisson regression model for the association between
injury rate and teaching status shows that the model rate ratio from
OPTION 1 is 1.44, model rate ratio from OPTION 2 is 1.33. I don't
understand why the crude model rate ratio for OPTION 2 isn't 1.44 like
the observed rate ratio or OPTION 1??? Any thoughts on this? Thank
you.


Vivian
From: Vivian Pun on 29 Dec 2009 08:27
On Dec 28, 5:28 pm, Vivian Pun <vivianpu...(a)gmail.com> wrote:
> Hi SAS users,
>
>    When I analyze the rate of injury by hospital teaching status. I
> calculate the average injury rates by teaching status:
>                              Rate                        Rate ratio
>      Teaching           26/1000 FTEs           26/18 = 1.44
>      Non-teaching     18/1000 FTEs           reference
>
>    I have tried two ways (there could be more ways) to import the
> injury count data into SAS.
>    OPTION 1: use SAS datalines option such as:
>                     data data1;
>                     input teaching count total_fte;
>                     l_fte=log(total_fte);
>                    datalines;
>                    No 6041 332967.7441
>                    Yes 12778 490319.0468
>                    ;
>                    run;
>        *This option is simple, but doesn't allow a more complicated
> model multivariate testing.
>
>    OPTION 2: use count dataset that include breakdown of all
> variables, such as:
>                    year quarter count total_fte teaching bedcat ....
>                    2002   3         23     2345       No
> 1   .....
>                    2004   1        100  100322     Yes
> 2   .....
>        *This option does allow a more complicated model multivariate
> testing.
>
>     When I fit the data from either OPTION into a Poisson model, an
> crude univariate poisson regression model for the association between
> injury rate and teaching status shows that the model rate ratio from
> OPTION 1 is 1.44, model rate ratio from OPTION 2 is 1.33. I don't
> understand why the crude model rate ratio for OPTION 2 isn't 1.44 like
> the observed rate ratio or  OPTION 1??? Any thoughts on this? Thank
> you.

For OPTION 1, my procedure code is

proc genmod data=data1;
class teaching (ref='No') / param=ref;
model count = teaching /dist=poisson link=log offset=l_fte ;
estimate 'Teaching' teaching 1/ exp;
run;

for OPTION 2,
proc genmod data=data;
class hosid teaching (ref='No') / param=ref;
model count = teaching /dist=poisson link=log offset=l_fte ;
repeated subject = hosid;
estimate 'Teaching' teaching 1/ exp;
run;

(for option 2, because my surveillance data spans for 7 years and same
99 hospitals (hosid) each year, I use repeated measurement for
hospitals.)
Does it make sense?? Any thoughts on why the results from both OPTIONS
using the same data differ?? Thank you.



Vivian
 | 
Pages: 1
Prev: Observed rate ratio VS model rate ratio
Next: Fw: extracting numbers from a string