Validity and reliability - What's it all about?

Research update

Validity and reliability - What's it all about? Part 1 Validity in quantitative studies

This is one of a series of short papers on aspects of research by Alison Twycross and Linda Shields

Just because a research study has been published in a

design. Internal validity relates to the extent to which the

journal does not mean that it is good research or that

design of a research study is a good test of the hypothesis

the results are applicable to your area of clinical practice.

or is appropriate for the research question (Carter and

When reading a paper, it is necessary to consider the

Porter 2000). External validity, meanwhile, relates to

validity and reliability of the study being described. This

whether or not research findings can be generalised

and the next artide in this series will define validity and

beyond the immediate study sample and setting.

reliability, and will explain how you can ascertain whether

Measures that are used to assess the validity of data

a quantitative research study is both valid and reliable.

collection tools are summarised in the box below (tliese

Validity means that a tool measures what it sets out

are adapted from Knapp (1998}, Carter and Porter

to measure - for example, that a pain assessment tool

Alison Twycross RGN, RMN, RSCN,MSc,CertEci(HE),DMS,

(2000), Peat (2002)).

measures pain intensity rather than anxiety. There are

When reading a research paper, you need to look for

several measures of validity that provide evidence of the

evidence that the researcher has addressed the validity

quality of a study.

and reliability of the data collection tools. This is usually

hitemal and external validity relate to the overall study

discussedinthemethodology section of the paper ISlfil

Senior Lecturer in Children's Nnrsing/Senior Nurse (Research Development), Glasgow

Box 1: Measures to assess the validity of data collection tools Content validity

Whether a tool appears to others to be measuring what it says it does. Face

Caledonian University/Yoridiill

validity is a simple fornn of content validity - the researcher asks a few people to

NHS Trust

check the tool covers all areas. A more rigorous way to assess content validity is to ask recognised experts in the area to give their opinion on the validity of the tool

Linda Shields PhD, FRCNA. Professor of Nursing, Universit)'

Criterion validity

Concurrent or predictive validity are both measures of criterion validity. Concurrent validity uses an already existing and well-accepted measure against

of Limerick, Ireland

which the new measure can be compared - for example, if you were developing a new pain assessment tool you would compare ttie ratings obtained from the new tools with those obtained using a previously validated tool. Predictive validity measures the extent to which a tool can predict a future event of interest - for example, does a tool developed to measure the risk of pressure sores in children in hospital in fact identify the children at risk"^ Criterion validity is usually measured using a correlation coefficient - when the correlation is high, the tool can be considered valid

REFERENCES Carter DE and Porter S (2000) Validity and reliability. !n Connack D (ed.) TTit Resmrck Process in Nursing. Fourth edition. Oxford. Blackwell Science. 29-42. Kjiapp TR (1998) Quantitative Nursing Research. Thousand Oaks, Sage. Peat J (2002) Health Services Research: A Handbook of Quantitative Methods. Londoti, Sage.

28

Construct validity

This tests the link between a measure and the underlying theory If a test has construct validity, you would expect to see a reasonable correlation with tests measuring related areas. Evidence of construct validity can be provided by comparing the results obtained withi the results obtained using other tests, other (related) characteristics of the individual or factors in the individual's environment which would be expected to affect test performance. Construct validity is usually measured using a correlation coefficient - when the correlation is high, the tool can be considered valid

Paediatric Nursing

vol 16 no 9 November 2004