Skip to main content

Table 1 Summary table of the characteristics of the imputation methods used to handle missing data

From: Imputation by the mean score should be avoided when validating a Patient Reported Outcomes questionnaire by a Rasch model in presence of informative missing data

Method

Ability of the individual

Difficulty of the item

Addition of a random process

Likelihood based approach

NOIMP

    

LD

    

WORST

    

PMS

X

 

X

 

IMS

 

X

X

 

CIM

X

X

X

 

ICS

X

X

  

LOG

X

X

X

X

MOK

X

X

  

RAS

X

X

X

X

RAI

X

X

 

X