# Re: st: incidence rate and confidence intervals

 From Tim Wade <[email protected]> To [email protected] Subject Re: st: incidence rate and confidence intervals Date Mon, 18 Jan 2010 14:10:59 -0500

```Maybe something like this too?

xi: poisson cases i.year, exposure(population)
predict logn, xb
predict se, stdp
gen ratehat=exp(logn-log(population))*100000
gen rateup=exp(logn+(1.96*se)-log(population))*100000
gen ratelo=exp(logn-(1.96*se)-log(population))*100000
twoway line ratehat rateup ratelo year, sort

slightly different CIs than those obtained from ci, maybe because ci
produces exact intervals.

I think you can then test for differences in years of interest using
-test-, e.g.

test  _Iyear_1955== _Iyear_1956

overlapping confidence intervals do not always indicate no difference
at p=0.05, see:
http://www.stata.com/statalist/archive/2008-01/msg00900.html , and
other discussions.

you can also compare to a linear trend using model without year as a
categorical variable, e.g.

xi: poisson cases year, exposure(population)

Hope this helps, Tim

On Sun, Jan 17, 2010 at 2:11 PM, moleps <[email protected]> wrote:
> Dear listers,
> I扉e got the incidence of a disease in a population in the following data format -year,population,cases-
> I扉e created the incidence rate by dividing cases by population and multiplying by 100000.
>
> gen ins=(cases/population)*100000
> poisson cases year population
>
> **no tendency for increasing incidense after correcting for population.
> **however
>
> line ins ye
>
> **shows an increasing trend. But I悲 like to add 95% CI lines to corroborate this. Is this at all possible given my dataset??
>
> Regards,
> //M
>
>
>
>
>
>
>     |  year   population   cases|
>         |----------------------------|
>  1. | 1953    2285542         49 |
>  2. | 1954    3075055         44 |
>  3. | 1955    3015476         50 |
>  4. | 1956    3073404         52 |
>  5. | 1957    3407827         94 |
>     |----------------------------|
>  6. | 1958    3404373         78 |
>  7. | 1959    3343568         79 |
>  8. | 1960    3196884         59 |
>  9. | 1961    3372724         80 |
>  10. | 1962    3508295         67 |
>     |----------------------------|
>  11. | 1963    3348748         84 |
>  12. | 1964    3680068         72 |
>  13. | 1965    3594444         85 |
>  14. | 1966    3270933         67 |
>  15. | 1967    3668785         66 |
>     |----------------------------|
>  16. | 1968    3802479        140 |
>  17. | 1969    3758948        115 |
>  18. | 1970    3765404         75 |
>  19. | 1971    3811994        103 |
>  20. | 1972    3595579         86 |
>     |----------------------------|
>  21. | 1973    3846154         98 |
>  22. | 1974    3972990        122 |
>  23. | 1975    3736829        111 |
>  24. | 1976    4017101        109 |
>  25. | 1977    4035202         96 |
>     |----------------------------|
>  26. | 1978    3972186        100 |
>  27. | 1979    4066134        110 |
>  28. | 1980    3813510        111 |
>  29. | 1981    3908085        121 |
>  30. | 1982    4029101        126 |
>     |----------------------------|
>  31. | 1983    4045128        112 |
>  32. | 1984    4134353        126 |
>  33. | 1985    3998700        136 |
>  34. | 1986    3936817         99 |
>  35. | 1987    4100854        126 |
>     |----------------------------|
>  36. | 1988    4198289        111 |
>  37. | 1989    4124119        114 |
>  38. | 1990    4233116        114 |
>  39. | 1991    4175240         97 |
>  40. | 1992    4198459        112 |
>     |----------------------------|
>  41. | 1993    4124798        113 |
>  42. | 1994    3986070         95 |
>  43. | 1995    4348410        109 |
>  44. | 1996    4369957        135 |
>  45. | 1997    4392714        135 |
>     |----------------------------|
>  46. | 1998    4342720        142 |
>  47. | 1999    4445329        157 |
>  48. | 2000    4478497        135 |
>  49. | 2001    4503436        128 |
>  50. | 2002    4450334        144 |
>     |----------------------------|
>  51. | 2003    4552252        144 |
>  52. | 2004    4577457        150 |
>  53. | 2005    4606363        164 |
>  54. | 2006    4567282        152 |
>  55. | 2007    4681134        153 |
>     |----------------------------|
>  56. | 2008    4571227        150 |
>     +----------------------------+
>
>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
```