You are on page 1of 2

Clinical Simulation in Nursing (2016) 12, 530-531

www.elsevier.com/locate/ecsn

Departments

Making Sense of Methods and


Measurement: Lawshe’s Content
Validity Index
Gregory E. Gilbert, EdD, MSPHa,b, Susan Prion, EdD, RN, CNEc,*
a
DMI’s-IRCS, Iselin, NJ 08830, USA
b
Center for Teaching and Learning, Ross University School of Medicine, Roseau, Dominica, West Indies
c
School of Nursing and Health Professions, University of San Francisco, San Francisco, CA 94117, USA

Calculating Lawshe’s Content Validity Index practitioners, and physician assistants. These are experts
representing practitioners who regularly insert urinary
Simulation performance evaluation is a complex and catheters.
complicated process. To produce valid and reliable assess- Each member of the panel is supplied the list of
ment data, the instruments used to gather the data must be evidence-based items chosen by the researcher to represent
empirically grounded. In previous columns, we have the construct or skill (Figure 1). Independent of the other
discussed reliability (Adamson & Prion, 2012a) and validity panelists, each panelist is asked to rate each of the items
(Adamson & Prion, 2012b, 2012c). In this column, we as ‘‘essential,’’ ‘‘useful,’’ or ‘‘not necessary.’’ A weighted
extend our understanding of validity by introducing Law- value is assigned to each rating.
she’s Content Validity Ratio (CVR) and Content Validity In- Responses from all panelists are pooled, and the number
dex (CVI) used to quantify validity of an assessment indicating ‘‘essential’’ for each item is determined.
instrument or tool as evaluated by review of clinical experts.
A validity study begins with gathering evidence-based
items for potential inclusion in the instrument or tool. If a Calculating the Content Validity Ratio
skill is being assessed, locate the best practices for perform-
ing the skill and include all the steps for conducting that The CVR is an item statistic useful in rejection or
skill listed by all sources. Once the items to be evaluated retention of individual items and is internationally
have been collected, a Content Evaluation Panel is formed. recognized as the method for establishing content
The Content Evaluation Panel should be composed of per- validity (Wilson, Pan, & Schumsky, 2012). The CVI is
sons who are experts about the domain being studied. the mean CVR for all the items included in the final in-
Ideally, there should be a range of experts (also known as strument (DeVon et al., 2007). When all panelists say
subject matter experts) on this panel at various professional that the tested knowledge or skill is ‘‘essential,’’ or
levels. In content areas where it is difficult to find experts, when none say that it is ‘‘essential,’’ we are confident
the use of three experts is acceptable; normally, a panel of to include or delete the item. It is when there is not
5-10 experts is preferred. The use of >10 experts is prob- consensus that item issues arise. Two assumptions are
ably unnecessary (Lynn, 1986). For example, if assessing made, each of which is consistent with established psy-
the validity of a task trainer used for urinary catheterization, chophysical principles:
an investigator could assemble a group of nurses, nurse
 Any item, performance on which is perceived to be
‘‘essential’’ by more than half of the panelists, has
* Corresponding author: prions@usfca.edu (S. Prion). some degree of content validity.

1876-1399/$ - see front matter Ó 2016 International Nursing Association for Clinical Simulation and Learning. Published by Elsevier Inc. All rights reserved.
http://dx.doi.org/10.1016/j.ecns.2016.08.002
Making Sense of Methods and Measurement: Lawshe’s Content Validity Index 531

Is the skill (or knowledge) measured by this item or tool, we can calculate a CVI. The CVI is simply the mean
o Essential? of the CVR values for all items meeting the CVR threshold
o Useful but not essential? Why? of 0.78 and retained for the final instrument. Tilden, Nelson,
o Not necessary? Why? and May (1990) suggest CVI values exceed 0.70; however,
Davis (1992) suggests a CVI exceeding 0.80 is preferred. In
Figure 1 Lawshe’s method for assessing content validity. many situations, it is more efficient to report the overall CVI
score than each individual item CVR.
The CVR is a useful statistical technique to determine
 The more panelists (beyond 50%), perceiving an item the validity of individual instrument items, as rated by a
as ‘‘essential’’, the greater the extent or degree of its panel of content experts. The CVI provides a numeric value
content validity. for the overall mean CVRs of all items included in the
instrument. Both the CVR and CVI can provide researchers
The CVR is calculated using the shown in Figure 2: and consumers with a quantitative measure of the validity
of a simulation evaluation instrument.

where: References
ne is the number of panelists identifying an item as “essential” and
N is the total number of panelists (N/2 is half the total number of panelists).
Adamson, K., & Prion, S. K. (2012a). Making sense of methods and mea-
Figure 2 Equation to calculate Lawshe’s Content Validity Ratio surement: Reliability. Clinical Simulation in Nursing, 8(6), e259-e260.
Adamson, K., & Prion, S. K. (2012b). Making sense of methods and mea-
(CVR).
surement: Validity Part II. Clinical Simulation in Nursing, 8(8), e383-
e384.
When all panelists agree an item is ‘‘essential,’’ the CVR Adamson, K., & Prion, S. K. (2012c). Making sense of methods and mea-
is 1.00 (adjusted to 0.99 for ease of manipulation according surement: Validity Part I. Clinical Simulation in Nursing, 8(7), e319-e320.
to Lawshe [1975]). When the number of panelists rating an Ayre, C., & Scally, A. (2014). Critical values for Lawshe’s content validity
item ‘‘essential’’ is more than half, but less than all, the ratio: Revisiting the original methods of calculation. Measurement and
CVR is somewhere between 0 and 0.99. If none of the Evaluation in Counseling and Development, 47(1), 79-86. http:
//dx.doi.org/10.1177/0748175613513808.
raters marks the item as ‘‘essential,’’ the CVR would be 0. Davis, L. (1992). Instrument review: Getting the most from a panel of ex-
perts. Applied Nursing Research, 5(4), 194-197.
Item Selection DeVon, H., Block, M. E., Moyle-Wright, P., Ernst, D. M., Hayden, S. J.,
Lazzara, D. J., ., & Kostas-Polston, E. (2007). A Psychometric toolbox
for testing validity and reliability. Journal of Nursing Scholarship,
A CVR is calculated for each item. Items are eliminated
39(2), 155-164.
possibly occurring due to chance using a table of critical Lawshe, C. (1975). A quantitative approach to content validity. Personnel
values found in Ayre and Scally (2014). Alternatively, Polit, Psychology, 28(4), 563-575. http://dx.doi.org/10.1111/j.1744-6570.
Beck, and Owen (2007) suggest items with a CVR of 0.78 1975.tb01393.x.
or higher with three or more experts could be considered Lynn, M. (1986). Determination and quantification of content validity.
Nursing Research, 35(6), 382-385.
evidence of good content validity. If an item does not reach
Polit, D., Beck, C., & Owen, S. (2007). Is the CVI an acceptable indicator
this threshold, it would normally be deleted from the final of content validity? Appraisal and recommendations. Research in
instrument. Nursing and Health, 30(4), 459-467. http://dx.doi.org/10.1002/nur.20199.
Tilden, V., Nelson, C., & May, B. (1990). Use of qualitative methods to
Content Validity Index enhance content validity. Nursing Research, 39(3), 172-175.
Wilson, F., Pan, W., & Schumsky, D. (2012). Recalculation of the critical
values for Lawshe’s content validity ratio. Measurement and Evaluation
The CVR tells us about the validity of individual items. If in Counseling and Development, 45(3), 197-210. http://dx.doi.org/10.
we want to know the content validity of the entire instrument 1177/0748175612440286.

pp 530-531  Clinical Simulation in Nursing  Volume 12  Issue 12

You might also like