Skip to main content

Table 5 HADS – Rating Scale Model Error rates by sample size (collapsing across items)

From: Rasch fit statistics and sample size considerations for polytomous data

HADS A

Infit t

Infit t

Infit MNSQ

Infit MNSQ

Infit MNSQ

Outfit t

Outfit t

Outfit MNSQ

Outfit MNSQ

Outfit MNSQ

 

<-2

>2

<0.7

>1.2

>1.3

<-2

>2

<0.7

>1.2

>1.3

25

0

0

1

1

1

0

0

1

1

1

50

0

1

0

1

1

0

1

0

1

1

100

0

1

0

1

1

0

1

0

1

1

200

0

1

0

1

1

0

1

0

1

1

400

1

1

0

1

1

1

1

0

1

1

800

1

1

0

1

1

1

1

0

1

1

1600

5

1

0

1

1

4

1

0

1

1

3200

5

1

0

1

1

4

1

0

1

1

HADS D

Infit t

Infit t

Infit MNSQ

Infit MNSQ

Infit MNSQ

Outfit t

Outfit t

Outfit MNSQ

Outfit MNSQ

Outfit MNSQ

 

<-2

>2

<0.7

>1.2

>1.3

<-2

>2

<0.7

>1.2

>1.3

25

0

0

0

2

2

0

0

1

2

1

50

0

0

0

2

2

0

0

1

1

1

100

0

0

0

2

2

1

0

1

2

2

200

0

2

0

2

2

1

0

0

2

0

400

1

2

0

2

1

1

1

0

1

1

800

1

2

0

2

2

2

1

1

1

1

1600

2

3

0

2

2

3

3

0

1

1

3200

2

3

0

2

2

3

3

0

1

1

  1. The number of items exceeding the fit criteria are shown in each column