From: rangoonraja123 on
Hi ALL,

how are you doing. I want to calculate average annual percent change
for cancer mortality.

see the below description.

Annual Percent Change (APC)
The Annual Percent Change (APC) is calculated by fitting a least
squares regression line to the natural logarithm of the rates, using
the calendar year as a regressor variable.
n = number of years
r = rates
y = Ln(r)
x = calendar year
y = mx + b
APC = 100 * (em - 1) ---- what does this really mean.

Can you guys tell me how i can do in SAS

Regards,
Raju

From: frazster on
(((y2/y1)**(1/(y2-y1)))-1)*100

where y1 & y2 are you calculated mortality rates for y1=year 1 &
y2=year 2.

From: Arthur Tabachneck on
Raju,

If changes in mortality rates are calculated the same as other changes
in rates, then I would presume you would only need a formula like
(assuming you are calculating the change from rate1 to rate2):

APC=rate2/rate1-1

If you are asking what the above formula represents, it can also be
expressed as:

(rate2-rate1)/rate1

Art
---------
On Feb 21, 2:56 pm, rangoonraja...(a)gmail.com wrote:
> Hi ALL,
>
> how are you doing. I want to calculate average annual percent change
> for cancer mortality.
>
> see the below description.
>
> Annual Percent Change (APC)
> The Annual Percent Change (APC) is calculated by fitting a least
> squares regression line to the natural logarithm of the rates, using
> the calendar year as a regressor variable.
> n = number of years
> r = rates
> y = Ln(r)
> x = calendar year
> y = mx + b
> APC = 100 * (em - 1) ---- what does this really mean.
>
> Can you guys tell me how i can do in SAS
>
> Regards,
> Raju