Statistical inference is the basis for data processing and interpretation. When planning a clinical trial, the calculation of the sample size is essential to avoid erroneous results and must be determined before starting the study. Statistical tests must follow the logic of data. In case of continuous variables, verification of normality is the first step to determine the choice between parametric and nonparametric tests (t-test rather than Mann–Whitney or ANOVA instead of Kruskal–Wallis, etc.), while categorical variables do not need to respect this hypothesis. When we need to check the association between continuous variables, we may use correlation analysis, while linear regression analysis will be useful to check if there is a linear relationship between a (continuous) response variable and one or more independent variables. Logistic regression is applied when the dependent variable is dichotomous, while when it has more than three levels, the multinomial analysis must be used.

Basic statistics for nuclear medicine and radiology / Campagna, Giuseppe; Signore, Alberto. - (2022), pp. 622-630. [10.1016/B978-0-12-822960-6.00133-2].

### Basic statistics for nuclear medicine and radiology

#### Abstract

Statistical inference is the basis for data processing and interpretation. When planning a clinical trial, the calculation of the sample size is essential to avoid erroneous results and must be determined before starting the study. Statistical tests must follow the logic of data. In case of continuous variables, verification of normality is the first step to determine the choice between parametric and nonparametric tests (t-test rather than Mann–Whitney or ANOVA instead of Kruskal–Wallis, etc.), while categorical variables do not need to respect this hypothesis. When we need to check the association between continuous variables, we may use correlation analysis, while linear regression analysis will be useful to check if there is a linear relationship between a (continuous) response variable and one or more independent variables. Logistic regression is applied when the dependent variable is dichotomous, while when it has more than three levels, the multinomial analysis must be used.
##### Scheda breve Scheda completa
2022
Nuclear Medicine and Molecular Imaging
9780128229606
9780323997492
parametric e non parametric test; linear and logistic regression
02 Pubblicazione su volume::02a Capitolo o Articolo
Basic statistics for nuclear medicine and radiology / Campagna, Giuseppe; Signore, Alberto. - (2022), pp. 622-630. [10.1016/B978-0-12-822960-6.00133-2].
File allegati a questo prodotto
File
Campagna_Basic-statistics-for nuclear_2022.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Dimensione 1.58 MB
Campagna_Copertina_Basic-statistics-for nuclear_2022.pdf

solo gestori archivio

Tipologia: Altro materiale allegato
Dimensione 1.38 MB
Campagna_Frontespizio_Basic-statistics-for nuclear_2022.pdf

solo gestori archivio

Tipologia: Altro materiale allegato
Dimensione 323.38 kB
Campagna_Indice_Basic-statistics-for nuclear_2022.pdf

solo gestori archivio

Tipologia: Altro materiale allegato
Dimensione 2.92 MB
Campagna_Quarta_Basic-statistics-for nuclear_2022.pdf

solo gestori archivio

Tipologia: Altro materiale allegato
Dimensione 1.64 MB

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: `https://hdl.handle.net/11573/1648154`
• ND
• 1
• ND