Öz
Sağkalım analizi çalışmalarında kullanılan veri tipleri genelde sağdan sansürlü verilerdir. Bu tür çalışmalarda amaç, hastalığın sağkalım süresine etki eden prognostik faktörleri (açıklayıcı değişkenler) belirlemektir. Bunun için Cox regresyon modeli (Cox oransal hazard modeli) kullanılmaktadır. Ancak sağkalım süreleri bazen parametrik bir dağılım gösterebilir. Bu durumda parametrik regresyon modelleri kullanılır. Bu çalışmada kemik iliği naklinde kullanılan interferon-α tedavisinde elde edilen sağdan sansürlü veriler incelendi. Bu veriler kullanılarak Cox regresyon modeli kuruldu ve interferon-α tedavisine etki yapan önemli prognostik faktörler belirlendi. Önemli olduğu düşünülen değişkenler tabakalı alınarak, tabakalı Cox regresyon modeli kuruldu ve tabakalı Cox regresyon modeli ile tabakasız Cox regresyon modeli sonuçları karşılaştırıldı. Ayrıca sağkalım sürelerine uygun parametrik dağılımlar, çeşitli yöntemlerle (AIC, logL, artıklar ve grafik yöntemi) incelendi ve en uygun dağılımın log-normal dağılım olduğu görüldü. Log-normal regresyon modeli ile tabakalı ve tabakasız Cox regresyon modeli sonuçları karşılaştırıldı.
Anahtar Kelimeler
Sağdan Sansürlü Veri Sağkalım Analizi Cox Regresyon Modeli Interferon-Α Tedavisi
Kaynakça
- COX, D.R. (1972), Regression models and life tables, Journal of the Royal Statistical Society, 34, 187-220.
- COX, D.R. and Snell, E.J. (1968), a general definition of residuals (with discussion), Journal of the Royal Statistical Society, B, 30, 248-275.
- HOSMER, D.W. and Lemeshow, S. (1999), Applied Survival Analysis: Regression Modeling of Time to Event Data, Wiley, John and Sons, Erişim: [ http://www.ats.ucla.edu/stat/sas/examples/asa/default.html ]. Erişim Tarihi: 25.09.2003
- KARDAUN, O., (1983), Statistical Analysis of Male Larynx-Cancer Patients-A Case Study, Statistical Nederlandica, 37, 103-126.
- KIM. S.W. and İBRAHİM, J.G., (2000), On Bayesian Inference for Proportional Hazards Models Using Noninformative Priors, Lifetime Data Analysis. 6, 331-341.
- KLEIN, J.P. and MOESCHBERGER. M. L., (1997), Survival Analysis-Techniques for Censored and Truncated Data, Springer.
- KLEINBAUM, D.G. (1996), Survival Analysis, a Self Learning Text, Springer, New York.
- NAHMAN. N.S . MIDDENDORF. D.F BAY, W.H., MCELLIGOTT. R . POWELL, S. and ANDERSON. J. (1992), Modification of the Percutaneous Approach to Peritoneal Dialysis Catheter Placement Under Peritoneoscopic Visualization: Clinical Results in 78 Patients, Journal of the American Society of Nephrology 3, 103-107.
- Sickle-Santanello, B.J., Farrar. W.B.. Keyhani-Rofagha. S.. Klein.J.P., Pearl. D.. Laufman, H..Dobson. J. and O'Toole. R.V. (1988), a Reproducible System of Flow Cytometric DNA Analysis of Paraffin Embedded Solid Tumors: Technical Improvements and Statistical Analysis, Cytometry 9, 594-599.
Öz
The data type used in survival analysis is generally right censored data. The aim in this kind of studies is to determine prognostic factors which have effects on survival time. For the above reason Cox regression model is used. Nevertheless survival times sometimes may have parametric distribution. In this case parametric regression models are used. In this study, the right censored data obtained from interferon-α treatment used in bone marrow transplant were investigated. Using this data, Cox regression model was constructed and prognostic factors, which have effects on interferon-α treatment, were determined. Taking variables which are thought important, as stratified, stratified Cox regression model was constructed. Stratified Cox regression model and Cox regression model was compared. Also parametric distributions, which a suitable for survival times, were examined using various methods such as AIC, LogL, residuals and graphic method. Log-normal regression model was selected as the most appropriate model. Latter model and the other models examined in this study are compared.
Anahtar Kelimeler
Right Censored Data Survival Analysis Cox Regression Model Interferon-α Treatment
Kaynakça
- COX, D.R. (1972), Regression models and life tables, Journal of the Royal Statistical Society, 34, 187-220.
- COX, D.R. and Snell, E.J. (1968), a general definition of residuals (with discussion), Journal of the Royal Statistical Society, B, 30, 248-275.
- HOSMER, D.W. and Lemeshow, S. (1999), Applied Survival Analysis: Regression Modeling of Time to Event Data, Wiley, John and Sons, Erişim: [ http://www.ats.ucla.edu/stat/sas/examples/asa/default.html ]. Erişim Tarihi: 25.09.2003
- KARDAUN, O., (1983), Statistical Analysis of Male Larynx-Cancer Patients-A Case Study, Statistical Nederlandica, 37, 103-126.
- KIM. S.W. and İBRAHİM, J.G., (2000), On Bayesian Inference for Proportional Hazards Models Using Noninformative Priors, Lifetime Data Analysis. 6, 331-341.
- KLEIN, J.P. and MOESCHBERGER. M. L., (1997), Survival Analysis-Techniques for Censored and Truncated Data, Springer.
- KLEINBAUM, D.G. (1996), Survival Analysis, a Self Learning Text, Springer, New York.
- NAHMAN. N.S . MIDDENDORF. D.F BAY, W.H., MCELLIGOTT. R . POWELL, S. and ANDERSON. J. (1992), Modification of the Percutaneous Approach to Peritoneal Dialysis Catheter Placement Under Peritoneoscopic Visualization: Clinical Results in 78 Patients, Journal of the American Society of Nephrology 3, 103-107.
- Sickle-Santanello, B.J., Farrar. W.B.. Keyhani-Rofagha. S.. Klein.J.P., Pearl. D.. Laufman, H..Dobson. J. and O'Toole. R.V. (1988), a Reproducible System of Flow Cytometric DNA Analysis of Paraffin Embedded Solid Tumors: Technical Improvements and Statistical Analysis, Cytometry 9, 594-599.
Ayrıntılar
| Birincil Dil | Türkçe |
|---|---|
| Konular | İstatistik |
| Bölüm | Araştırma Makaleleri |
| Yazarlar | |
| Yayımlanma Tarihi | 15 Nisan 2004 |
| Yayımlandığı Sayı | Yıl 2004 Cilt: 3 Sayı: 1 |
