[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
ssamuels@albany.edu |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: How to treat variables where all outcomes happens in one interval Roland- When categories with events are compared to categories with no events in a Cox model, the partial likelihood is maximized by a HR of infinity, giving you the "very large HR" you observed. The same phenomenon occurs if you estimate the odds ratio in a 2 x 2 table with no observations in either of the off-diagonal cells. If you wish to use Cox, you cannot compare age >45 to age <=45. Your definition of stages is not very clear, but you cannot make any comparison of stages where membership in one requires age<=45. You may have to exclude all people <=45 and take what stage definitions remain remains. You may still analyze or adjust for differences among other stages, confined to those >45. If you can obtain from the literature information about the distribution of deaths by age, a sample size calculation (-stpower-) should show why you observed none in the <=45 group. -Steve On Mar 31, 2009, at 4:56 AM, roland andersson wrote: I am analysing survival in two methods of syrgery for thyroid cancer. The international classification of stage of disease includes tumorsize (<2, 2-4, >4 cm within the thyroid and growth outside the thyroid, presence of distant metastases, metastases to lymphglands and age>45 years. In my patients all deaths have occured in patients >age 45 years. When the dichotomised agevariable is analysed in Coxregression the HR is very large with very large SE. There is no problem with collinearity. How should I treat this situation? One solution would be to only analyse according to the stage classification (which includes age >45 years for stage 3 and 4), but I would like to analyse the importance of each element of the stageclassification. I may dichotomise with cutoff point >50 years, but that is not correct according to the international definition of tumour stage. |

Date |
Thu, 2 Apr 2009 14:55:33 -0400 (EDT) |

Roland- When categories with events are compared to categories with no events in a Cox model, the partial likelihood is maximized by a beta coefficient of plus or minus of infinity, giving you the "very large HR" you observed or to HR = 0. The same phenomenon would occur if you had a continuous covariate whose rank correlation with failure time was 1.0. A similar problem arises in estimating an oods ratio in a 2 x 2 table when one of the off-diagonal cells has no observations. If you wish to use Cox, you cannot compare age >45 to age <=45. You cannot make a comparison involving any stage defined, in part, by having age<=45. You may have to exclude all people <=45 and take whatever stages remain. Try to obtain from the literature information about the distribution of deaths by age. A sample size calculation (-stpower-) should show why you observed none in the <=45 group. -Steve On Mar 31, 2009, at 4:56 AM, roland andersson wrote: | |I am analysing survival in two methods of syrgery for thyroid cancer. |The international classification of stage of disease includes |tumorsize (<2, 2-4, >4 cm within the thyroid and growth outside the |thyroid, presence of distant metastases, metastases to lymphglands and |age>45 years. |In my patients all deaths have occured in patients >age 45 years. When |the dichotomised agevariable is analysed in Coxregression the HR is |very large with very large SE. There is no problem with collinearity. |How should I treat this situation? One solution would be to only |analyse according to the stage classification (which includes age >45 |years for stage 3 and 4), but I would like to analyse the importance |of each element of the stageclassification. I may dichotomise with |cutoff point >50 years, but that is not correct according to the |international definition of tumour stage. | * * 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/

- Prev by Date:
**st: Opinions on fractional logit versus tobit - prediction and model fit** - Next by Date:
**st: RE: Panel data - XTGEE with 2 levels of clustering** - Previous by thread:
**st: Opinions on fractional logit versus tobit - prediction and model fit** - Next by thread:
**Re: st: How to treat variables where all outcomes happens in one interval-apology** - Index(es):

© Copyright 1996–2014 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |