Skip to main content

Table 1 Data structure for the breast cancer dataset and associated means and standard deviations (SDs) after suitable transformation

From: Comparison of techniques for handling missing covariate data within prognostic modelling studies: a simulation study

Covariate

Variable Type

Groupings/Measurement

Label

X

Mean(SD)

Age

Continuous

Years

Age

X 1

53.05(10.12)

Lymph nodes

Continuous

Number of

LN

X 2

1.16(0.94)

Progesterone receptor

Continuous

fmol

PGR

X 3

3.35(1.93)

Oestrogen receptor

Continuous

fmol

ER

X 4

3.35(1.84)

Hormonal treatment

Binary

1 = Yes,

0 = No

TRT

X 5

0.36(0.48)

Menopausal status

Binary

0 = Pre,

1 = Post

MENO

X 6

0.58(0.49)

Tumour group

Binary

0 = Grade I,

1 = Grade II/III

TG

X 7

0.88(0.32)

Tumour size

Continuous variable categorised

1 = ≤20 mm,

2 = 21-30 mm,

3 = >30 mm

TS

X 8

3.27(0.46)

  1. Note: Data from the breast cancer dataset for X2 and X8 were log transformed; X3 and X4 were transformed using log(X+1).