2009
DOI: 10.22237/jmasm/1241137140
|View full text |Cite
|
Sign up to set email alerts
|

Which Is the Best Parametric Statistical Method For Analyzing Delphi Data?

Abstract: This study compares the three parametric statistical methods: coefficient of variation, Pearson correlation coefficient, and F-test to obtain reliability in a Delphi study that involved more than 100 participants. The results of this study indicated that coefficient of variation was the best procedure to obtain reliability in such a study.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

1
18
0
1

Year Published

2014
2014
2023
2023

Publication Types

Select...
4
4

Relationship

0
8

Authors

Journals

citations
Cited by 40 publications
(20 citation statements)
references
References 4 publications
1
18
0
1
Order By: Relevance
“…Table 6 summarizes the absolute difference between results of Delphi Round 1 and Round 2. Whilst [66] marked that values of [CV R1 -CV R2] below 0.2 are considered as minor, [65] added that henceforth the stopping rule is applied for the Delphi study. Noting such highlights, it is deduced that stability of each Severe DIF was reached at Round 2 and no further Delphi rounds were required.…”
Section: Results Stage 3 -Delphi Roundmentioning
confidence: 99%
See 1 more Smart Citation
“…Table 6 summarizes the absolute difference between results of Delphi Round 1 and Round 2. Whilst [66] marked that values of [CV R1 -CV R2] below 0.2 are considered as minor, [65] added that henceforth the stopping rule is applied for the Delphi study. Noting such highlights, it is deduced that stability of each Severe DIF was reached at Round 2 and no further Delphi rounds were required.…”
Section: Results Stage 3 -Delphi Roundmentioning
confidence: 99%
“…Further computation to compare results from Delphi Round 2 and previous results from Delphi Round 1 was performed by exploiting a coefficient of variation [CV]. Parametric statistical methods such as the CV and F-test have been used in Delphi studies with samples below 50 as stated in [65] . The CV which defines ratio of standard deviation [SD] of a competency area to its corresponding means [AVG] among the Expert members was formulated as: [1] Accordingly, an absolute difference was calculated by subtracting the CV of the current and previous stage.…”
Section: Stage 2 -Delphi Roundmentioning
confidence: 99%
“…Although there is no universal referent, consensus can be understood as "the degree of convergence of individual estimates to a minimum of 80 per cent" (Pozo, Gutiérrez & Rodríguez, 2007). The coefficient of variation provided by the experts' answers (S (x)=0.18) also indicates a high degree of consensus concerning the issues raised in the tool, since for (Shah & Kalaian, 2009) this coefficient is the most adequate test for this type of studies. Once the questionnaire structure was established, after the second consultation with the experts, the final design of the instrument was elaborated in telematic version, being its link: http://bit.ly/1EGNx4Y.…”
Section: Discussionmentioning
confidence: 98%
“…There is no a single way of estimating consensus (Arregui Ayatuy, Vallejo Alonso, & Villarreal Larrianaga, 1996, E. Martínez, 2003, Shah & Kalaian, 2009, Von der Gracht, Heiko A., 2012. Across the different possibilities, they can be the median or coefficient of variation because they are the most used in practice.…”
Section: Discussionmentioning
confidence: 99%
“…Delphi surveys are typically analyzed with descriptive statistics (Hasson et al, 2000). However, inferential statistics in survey analysis provides more insights into the relationships between responses and rounds in surveys, including Delphi surveys (Hasson et al, 2000;Shah and Kalaian, 2009). Therefore, inferential statistics was used to analyze the data of this survey.…”
Section: Methodsmentioning
confidence: 99%