PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 761455

A computer program for life table regression analysis with time dependent covariates.

P Peduzzi·T Holford·R Hardy
View original source ↗Export metadata ↓

Abstract

This paper presents a computer program for analyzing time-dependent covariables in survival studies by the life table regression model described by Holford [3]. Basically, life table regression incorporates the elements of regression and the life table into a single model. Regression parameters are estimated by the method of maximum likelihood using the Newton-Raphson iterative procedure. The program provides two methods for testing hypotheses concerning regression coefficients, namely the standard normal deviate test and a Wald statistic based on the first and second derivatives of the log likelihood. Residual plots are provided to assess the fit of the model to the data.

Explore related subjects

Actuarial AnalysisComputersHumansLongevityModels, BiologicalMortalityRegression AnalysisStatistics as TopicTime FactorsJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

P Peduzzi, T Holford, R Hardy. 1979. A computer program for life table regression analysis with time dependent covariates.. https://doi.org/10.1016/0010-468x(79)90024-2

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed1992

Potential impact on tumor control and organ preservation with cisplatin and 5-fluorouracil for patients with advanced tumors of the paranasal sinuses and nasal fossa. A prospective pilot study.

METHODS: Twelve patients with advanced epithelial nonadenocarcinoma of the paranasal sinuses and nasal fossa were treated with three cycles of cisplatin (100 mg/m2, day 1) and 5-fluorouracil (1000 mg/m2/24 hours on days 1-5 by continuous infusion), followed by preoperative external radiation therapy of 48 Gy and limited surgery, clearing the paranasal sinuses and nasal fossa. RESULTS: After chemotherapy, 11 of 12 patients were free of the previous symptoms of disease. Clinical response rates were different, however, with an overall response rate of approximately 70% with no complete responses. Histopathologic analysis of resected specimens showed no vital tumor in eight patients, minimal microscopic disease in three patients, and infiltrating tumor in one patient. Local control was achieved in 11 of 12 patients. Ten patients are alive with no evidence of disease (mean follow-up, 27 months). Surgical mutilation was avoided, with no functional or cosmetic loss. CONCLUSIONS: The results of this small pilot study seem to indicate a high chemosensitivity of carcinomas of the paranasal sinuses and nasal fossa, which, in this study, has meant significant relief of symptoms and an unusually high rate of local control (90%) without mutilation.

Actuarial Analysis↗
PubMed1992

Urokinase combination chemotherapy in small cell lung cancer. A phase II study.

BACKGROUND AND METHODS: Fifty-one patients with small cell lung cancer (SCLC) were treated with alternating urokinase (UK)-cyclophosphamide-doxorubicin (Adriamycin, Adria Laboratories, Columbus, OH)-vincristine and cisplatin-etoposide-vincristine. UK was given as a loading dose of 3000 micrograms/kg body weight, followed by 3000 micrograms/kg/h for 6 hours. Thoracic irradiation with split technique (46 Gy) and prophylactic cranial irradiation (25 Gy) were administered to responding patients. A second staging was performed in patients exhibiting a clinical complete response (CR) after 1 year. RESULTS: In 27 patients with limited disease, there were 23 CR and 8 partial responses (PR) (CR, 85.1%; 66.2-95.8% at 95% confidence intervals); in 24 patients with extensive disease, there were 17 CR, 4 PR, and 3 cases with progression. Pathologically proven CR were observed in 59.2% patients with limited disease and 33.3% patients with extensive disease. Survival rates were as follows: in patients with limited disease, 1 year, 85.1%; 2 years, 55.5%; and 3 years, 25.9%; in patients with extensive disease, 1 year, 54.1; and 2 years, 16.9%. Median survival times were 26.3 months (patients with limited disease) and 13.3 months (patients with extensive disease). UK-related toxic effects included four episodes of mild to moderate bleeding, one allergic reaction, and one cerebrovascular accident. Myelotoxicity was severe, with a median of two episodes of Grade III-IV (World Health Organization classification) aplasia per patient. CONCLUSIONS: These results are consistent with a potential benefit of fibrinolytic therapy in combination with chemotherapy in patients with SCLC with limited disease. Additional trials are indicated.

Actuarial Analysis↗