You need to tell us what you eman by:
"- the total number of people in each of these three
groups that died broken down by calender year, gender and age group"
I suppose it the the population size in each group at a given date in the year?
So the same person will contribute to this every year he is alive?
The it's an easy thing to compute the person-years - the brutal way is to multiply thes nubers by 1 year (which is what you would do if it is mid-year population size) or you could take successicve means if you have popuation size at 1 January, or you could some more fancy tabulations taking birth cohorts into account, see:
Carstensen B: Age-period-cohort models for the Lexis diagram.
Stat Med. 2007 Jul 10;26(15):3018-45.
Best regards,
Bendix Carstensen
> -----Original Message-----
> From: A UK-based worldwide e-mail broadcast system mailing
> list [mailto:[log in to unmask]] On Behalf Of Tiffany Lay
> Sent: 17. juli 2008 15:06
> To: [log in to unmask]
> Subject: Calculating direct and indirect standardised rates in STATA
>
> Can anyone help me?
>
> At present I am using tables in Excel in order to calculate
> direct and indirect standardised rates. However, I am trying
> to start doing this analysis in STATA. The problem that I
> have is that the data that I have does not enable me to use
> person time at risk in the calculation.
>
> The data that I have is as follows:
>
> Direct standardisation
> - the total number of people that belonged to one of
> three groups broken down by calender year, gender and age group
> - the total number of people in each of these three
> groups that died broken down by calender year, gender and age group
> - the standard population is the total number of people
> in the three groups combined for a specific year, broken down
> by gender and age group from this I need to produce a direct
> rate for the three groups and overall, standardised for gender and age
>
> Indirect standardisation
> - the total number of people in the UK broken down by
> calender year, gender and age
> - the total number of people in the UK that died, broken
> down by calender year, gender and age
> - the total number of people that belonged to one of
> three groups broken down by calender year, gender and age group
> - the total number of people in each of these three
> groups that died broken down by calender year, gender and age group
> - the standard population is the UK population from this
> I need to produce an indirect rate for the three groups and
> overall, standardised for gender, age and calender year
>
> All of this is analysis is being done for specific causes of
> mortality.
>
> Any help would be very much appreciated!
>
> Thanks,
>
> Tiffany Lay
> e-mail: [log in to unmask] <mailto:[log in to unmask]>
> P Please consider the environment before printing
>
> This e-mail and any files transmitted with it are
> confidential and intended solely for the use of the
> individual or entity to whom it is addressed. If you are not
> the intended recipient or there are problems please notify
> the sender and then delete the e-mail (and file(s) if
> attached) from your system.
> Recipients should note that e-mail traffic on MOD systems is
> subject to monitoring, recording and auditing to secure the
> effective operation of the system and for other lawful purposes.
> The MOD has taken steps to keep this e-mail and any
> attachments free from viruses. However it accepts no
> liability for any loss or damage howsoever caused as a result
> of any virus being passed on. It is the responsibility of the
> recipient to perform all necessary checks.
> The statements expressed in this e-mail are personal and do
> not necessarily reflect the opinions or policies of the department.
>
>
>
|