In order to compare several outcomes of different therapies, a comparative evaluation of the empirical approach vs the non-empirical one, has been conducted within an epidemiological survey on nosocomial infections carried out in 79 hospitals from different Italian regions. This paper presents a methodological approach to apply statistical techniques for hypotheses testing particularly idoneous in the context of observational studies. The methods proposed consists in a joint use of stratification techniques to control for confounding factors and statistical tests for coherent alternatives based on the nonparametric combination of dependent permutation tests.
Il progetto SETIG e la valutazione comparativa delle strategie terapeutiche adottate: metodologia statistica e applicazione.
ARBORETTI GIANCRISTOFARO, Rosa;
2000
Abstract
In order to compare several outcomes of different therapies, a comparative evaluation of the empirical approach vs the non-empirical one, has been conducted within an epidemiological survey on nosocomial infections carried out in 79 hospitals from different Italian regions. This paper presents a methodological approach to apply statistical techniques for hypotheses testing particularly idoneous in the context of observational studies. The methods proposed consists in a joint use of stratification techniques to control for confounding factors and statistical tests for coherent alternatives based on the nonparametric combination of dependent permutation tests.I documenti in SFERA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
