Title: | Measuring Stakeholder Influence |
---|---|
Description: | Proposes an original instrument for measuring stakeholder influence on the development of an infrastructure project that is carried through by a municipality, drawing on stakeholder classifications (Mitchell, Agle, & Wood, 1997) and input-output modelling (Hester & Adams, 2013). Mitchell R., Agle B.R., & Wood D.J. <doi:10.2307/259247> Hester, P.T., & Adams, K.M. (2013) <doi:10.1016/j.procs.2013.09.282>. |
Authors: | Anna Zamojska [aut], Piotr Zientara [aut], Sebastian Susmarski [aut], Lech Kujawski [aut, cre] |
Maintainer: | Lech Kujawski <[email protected]> |
License: | GPL (>= 2) |
Version: | 1.2 |
Built: | 2024-12-01 08:31:21 UTC |
Source: | CRAN |
This project was financed by The National Center of Reaserch and Development (grant number IS-2/88/NCBR/2015). This software is an original instrument for measuring stakeholder influence on the development of a publicly-funded infrastructure project and for estimating its cost and benefits, as preceived by different stakeholder groups. Its originality lies in application of Leontief's input-output analysis to estimating both stakeholder influence on a infrastructure project and its cost and benefits, as perceived by different stakeholder groups. Admittedly, in the literature there are studies that draw on Leontief's model to estimate stakeholder influence or, separately, to measure a project's perceived costs and benefits. That said, none of this research work - unlike our package - combines the two focuses. It follows that our software, uniquely, links together Leontief's input-output analysis, stakeholder influence measurement and estimation of a project's costs and benefits. Therefore, it constitutes a useful instrument that might be of particular interest to managers and municipality official responsible for implementation of a large-scale infrastructure projects. Proposes an original instrument for measuring stakeholder influence on the development of an infrastructure project that is carried through by a municipality, drawing on stakeholder classifications (Mitchell, Agle, & Wood, 1997) and input-output modelling (Hester & Adams, 2013). Mitchell R., Agle B.R., & Wood D.J. <doi:10.2307/259247> Hester, P.T., & Adams, K.M. (2013) <doi:10.1016/j.procs.2013.09.282>. Proposes an original instrument for measuring stakeholder influence on the development of an infrastructure project that is carried through by a municipality, drawing on stakeholder classifications (Mitchell, Agle, & Wood, 1997) and input-output modelling (Hester & Adams, 2013). Mitchell R., Agle B.R., & Wood D.J. <doi:10.2307/259247> Hester, P.T., & Adams, K.M. (2013) <doi:10.1016/j.procs.2013.09.282>.
The DESCRIPTION file:
Package: | StakeholderAnalysis |
Version: | 1.2 |
Date: | 2017-10-24 |
Title: | Measuring Stakeholder Influence |
Authors@R: | c(person("Anna", "Zamojska", role="aut", email="[email protected]"), person("Piotr", "Zientara", role="aut", email="[email protected]"), person("Sebastian", "Susmarski", role="aut", email="[email protected]"), person("Lech", "Kujawski", role=c("aut", "cre"), email = "[email protected]")) |
Author: | Anna Zamojska [aut], Piotr Zientara [aut], Sebastian Susmarski [aut], Lech Kujawski [aut, cre] |
Maintainer: | Lech Kujawski <[email protected]> |
Depends: | R (>= 3.2.3) |
Description: | Proposes an original instrument for measuring stakeholder influence on the development of an infrastructure project that is carried through by a municipality, drawing on stakeholder classifications (Mitchell, Agle, & Wood, 1997) and input-output modelling (Hester & Adams, 2013). Mitchell R., Agle B.R., & Wood D.J. <doi:10.2307/259247> Hester, P.T., & Adams, K.M. (2013) <doi:10.1016/j.procs.2013.09.282>. |
License: | GPL (>= 2) |
URL: | https://www.r-project.org |
NeedsCompilation: | no |
Packaged: | 2017-11-13 19:32:59 UTC; Marcin |
Repository: | CRAN |
Date/Publication: | 2017-11-13 21:18:07 UTC |
Index of help topics:
AttribIdent AttribIdent AttribPict AttribPict BenefCost BenefCost CollabPotential CollabPotential DataExp DataExp Histograms Histograms ImpactAnalysis ImpactAnalysis PrelCalc PrelCalc RelationPict RelationPict RespVerif RespVefif StakeholdClassif StakeholdClassif StakeholderAnalysis-package Measuring Stakeholder Influence
Lech Kujawski Anna Zamojska [aut], Piotr Zientara [aut], Sebastian Susmarski [aut], Lech Kujawski [aut, cre]
Maintainer: Lech Kujawski <[email protected]>
Hester, P.T., & Adams, K.M. (2013) <doi:10.1016/j.procs.2013.09.282> Hester, P.T., Bradley, J.M., MacGregor K.A. (2012) <doi:10.1504/IJSSE.2012.052687>
Identifies stakeholder attributes as well as benefits and costs
AttribIdent(TestedResponses, NoAttrib, NoStakeholders, NameStakeholders)
AttribIdent(TestedResponses, NoAttrib, NoStakeholders, NameStakeholders)
TestedResponses |
the result of the RespVerif function |
NoAttrib |
col numbers in the raw data set related to particular constructs. The $NoAttrib from the PreCalc function should be used |
NoStakeholders |
the number of stakeholder groups. The $NoStakeholders from the PreCalc function should be used |
NameStakeholders |
the names of stakeholder groups. The $NameStakeholders from the PreCalc function should be used |
Based on previously performed tests of means and fractions (see the RespVerif function), the function determines whether a particular attribute is statistically significant or not (.<05)
Mean |
(the number of stakeholder groups) x 6 matrix. In each row, the "+" sign indicates that an attribute is statistically significant, while the "-" sign indicates that an attribute is not statistically significant (based on the mean test). The "0" sign shows that the response is neutral, meaning that respondents do not know whether they possess a particular attribute or not |
Fra |
(the number of stakeholder groups) x 6 matrix. In each row, the "+" sign indicates that an attribute is statistically significant, while the "-" sign indicates that an attribute is not statistically significant (based on the fraction test). The "0" sign shows that the response is neutral, meaning that respondents do not know whether they possess a particular attribute or not |
Sebastian Susmarski, Lech Kujawski, Anna Zamojska, Piotr Zientara
# first import DataExp data(DataExp) # then execute PrelCalc(), RespVerif() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) RespVerifExp=RespVerif(CountResponses=PrelCalcExp$CountResponses, NoStakeholders=PrelCalcExp$NoStakeholders) # AttribIdent() AttribIdentExp=AttribIdent(TestedResponses=RespVerifExp, NoAttrib=PrelCalcExp$NoAttrib, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) AttribIdentExp
# first import DataExp data(DataExp) # then execute PrelCalc(), RespVerif() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) RespVerifExp=RespVerif(CountResponses=PrelCalcExp$CountResponses, NoStakeholders=PrelCalcExp$NoStakeholders) # AttribIdent() AttribIdentExp=AttribIdent(TestedResponses=RespVerifExp, NoAttrib=PrelCalcExp$NoAttrib, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) AttribIdentExp
Draws a picture of stakeholder attributes in the form of three overlapping circles
AttribPict(path, tofile, AttribIdent, CollabPotential)
AttribPict(path, tofile, AttribIdent, CollabPotential)
path |
a path of a particular catalogue in which pictures are saved, set path="" when tofile=0 |
tofile |
logical. 1=save-to-file. 0=show-on-screen |
AttribIdent |
stakeholder attributes. The $Mean or the $Fra from the AttribIdent function should be used |
CollabPotential |
potential for collaboration. The $Mean or the $Fra from the CollabPotential function should be used |
The function draws a picture of stakeholder attributes in the form of three overlapping circles in different colours
drow |
A drow of stakeholder attributes |
Sebastian Susmarski, Lech Kujawski, Anna Zamojska, Piotr Zientara
# first import DataExp data(DataExp) # then execute PrelCalc(), RespVerif(), AttibIdent(), CollabPotential() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) RespVerifExp=RespVerif(CountResponses=PrelCalcExp$CountResponses, NoStakeholders=PrelCalcExp$NoStakeholders) AttribIdentExp=AttribIdent(TestedResponses=RespVerifExp, NoAttrib=PrelCalcExp$NoAttrib, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) CollabPotentialExp=CollabPotential(AttribIdent=AttribIdentExp) # AttribPict() AttribPict(path="",tofile=0,AttribIdent=AttribIdentExp$Mean,CollabPotential=CollabPotentialExp$Mean)
# first import DataExp data(DataExp) # then execute PrelCalc(), RespVerif(), AttibIdent(), CollabPotential() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) RespVerifExp=RespVerif(CountResponses=PrelCalcExp$CountResponses, NoStakeholders=PrelCalcExp$NoStakeholders) AttribIdentExp=AttribIdent(TestedResponses=RespVerifExp, NoAttrib=PrelCalcExp$NoAttrib, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) CollabPotentialExp=CollabPotential(AttribIdent=AttribIdentExp) # AttribPict() AttribPict(path="",tofile=0,AttribIdent=AttribIdentExp$Mean,CollabPotential=CollabPotentialExp$Mean)
Calculates the benefit indicator (normalized on the 0-1 scale) and the cost indicator (normalized on the 0-1 scale), and performs a Student's t-test (with H0 stating that the mean of benefits and the mean of costs are equal)
BenefCost(CountResponses)
BenefCost(CountResponses)
CountResponses |
the number of stakeholder groups x 30 matrix comprising counted responses to particular items. The $CountResponses from the PreCalc function should be used |
Based on responses to relevant items, the function calculates the benefit indicator (normalized on the 0-1 scale) and the cost indicator (normalized on the 0-1 scale). Subsequently, it performs a Student's t-test (with H0 stating that the mean of benefits and the mean of costs are equal) with a view to ascertaining whether benefits are greater than costs (which is indicated by the "+" sign) or vice versa (which is indicated by the "-" sign)
BenefCostInd |
the benefit indicator and the cost indicator |
BenefCostTest |
the results of Student's t-tests |
Sebastian Susmarski, Lech Kujawski, Anna Zamojska, Piotr Zientara
# first import DataExp data(DataExp) # then execute PrelCalc() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) # BenefCost() BenefCostExp=BenefCost(CountResponses=PrelCalcExp$CountResponses) BenefCostExp
# first import DataExp data(DataExp) # then execute PrelCalc() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) # BenefCost() BenefCostExp=BenefCost(CountResponses=PrelCalcExp$CountResponses) BenefCostExp
Determines the potential of particular stakeholder groups for collaboration
CollabPotential(AttribIdent)
CollabPotential(AttribIdent)
AttribIdent |
Identifies stakeholder attributes. The $Mean or $Fra from the AttribIdent function should be used |
Based on responses to items measuring Power, Legitimacy and Urgency, the function determines the potential of particular stakeholder groups for collaboration ("high" and "low")
Mean |
the potential for collaboration determined on the basis of the mean value |
Fra |
the potential for collaboration determined on the basis of the fractions of responses |
Sebastian Susmarski, Lech Kujawski, Anna Zamojska, Piotr Zientara
# first import DataExp data(DataExp) # then execute PrelCalc(), RespVerif(), AttibIdent() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) RespVerifExp=RespVerif(CountResponses=PrelCalcExp$CountResponses, NoStakeholders=PrelCalcExp$NoStakeholders) AttribIdentExp=AttribIdent(TestedResponses=RespVerifExp, NoAttrib=PrelCalcExp$NoAttrib, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) # CollabPotential CollabPotentialExp=CollabPotential(AttribIdent=AttribIdentExp) CollabPotentialExp
# first import DataExp data(DataExp) # then execute PrelCalc(), RespVerif(), AttibIdent() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) RespVerifExp=RespVerif(CountResponses=PrelCalcExp$CountResponses, NoStakeholders=PrelCalcExp$NoStakeholders) AttribIdentExp=AttribIdent(TestedResponses=RespVerifExp, NoAttrib=PrelCalcExp$NoAttrib, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) # CollabPotential CollabPotentialExp=CollabPotential(AttribIdent=AttribIdentExp) CollabPotentialExp
Example of data collected via servey reserch
data(DataExp)
data(DataExp)
A data frame with 112 observations on the following 39 variables.
ID
a factor with levels Consulting Agencies
Firms
Local Residents
Project Implementers
Research Units
Local Authorities
pyt1
a numeric vector on a five-point Likert scale. I have a positive view on the implementation of the project (Attitude).
pyt2
a numeric vector on a five-point Likert scale. I have effective power over the implementation of the project (Power).
pyt3
a numeric vector on a five-point Likert scale. I think that the implementation of the project is urgent (Urgency).
pyt4
a numeric vector on a five-point Likert scale. I am entitled to be consulted about the implementation of the project (Legitimacy).
pyt5
a numeric vector on a five-point Likert scale. The project should be implemented as soon as possible (Urgency).
pyt6
a numeric vector on a five-point Likert scale. It is justified to consult me about the implementation of the project (Legitimacy).
pyt7
a numeric vector on a five-point Likert scale. Changes to the implementation of the project depends on me (Power).
pyt8
a numeric vector on a five-point Likert scale. Given my role in the project, I should bo consulted abouts its implementation (Legitimacy).
pyt9
a numeric vector on a five-point Likert scale. In my opinion, the implementaton of the project is a matter of urgency (Urgency).
pyt10
a numeric vector on a five-point Likert scale. My attitude to the implementation of the project is unambiguously positive (Attitude).
pyt11
a numeric vector on a five-point Likert scale. The implementation of the project is very important to me (Urgency).
pyt12
a numeric vector on a five-point Likert scale. Implementers of the project can count on me for support (Attitude).
pyt13
a numeric vector on a five-point Likert scale. My power over the implantation of the project is considerable (Power).
pyt14
a numeric vector on a five-point Likert scale. I support the implantation of the project (Attitude).
pyt15
a numeric vector on a five-point Likert scale. I am in a position to influence the implantation of the project (Power).
pyt16
a numeric vector on a five-point Likert scale. My role in the project justifies consulting me about its implementation (Legitimacy).
prof1
a numeric vector on a five-point Likert scale. The implementation of the project will generate new jobs.
prof2
a numeric vector on a five-point Likert scale. The implementation of the project will enhance the technological potential of the region.
prof3
a numeric vector on a five-point Likert scale. Thanks to the implementation of the project, more results of scientific research will be put into practice.
prof4
a numeric vector on a five-point Likert scale. The implementation of the project will translate into a greater number of patents and inventions.
prof5
a numeric vector on a five-point Likert scale. Thanks to the implementation of the project, local infrastructure will be modernized.
cost1
a numeric vector on a five-point Likert scale. The implementation of the project will increase road traffic in the area.
cost2
a numeric vector on a five-point Likert scale. The implementation of the project will negatively affect the environment.
cost3
a numeric vector on a five-point Likert scale. The implementation of the project will increase air pollution.
cost4
a numeric vector on a five-point Likert scale. The implementation of the project will increase noise.
cost5
a numeric vector on a five-point Likert scale. The implementation of the project will make it harder to park a car.
my1
a numeric vector on a five-point Likert scale. I have influence over Consulting Agencies.
my2
a numeric vector on a five-point Likert scale. I have influence over Firms.
my3
a numeric vector on a five-point Likert scale. I have influence over Local Residents.
my4
a numeric vector on a five-point Likert scale. I have influence over Project Implementers.
my5
a numeric vector on a five-point Likert scale. I have influence over Research Units.
my6
a numeric vector on a five-point Likert scale. I have influence over Local Authorities.
me1
a numeric vector on a five-point Likert scale. Consulting Agencies have influence over me.
me2
a numeric vector on a five-point Likert scale. Firms have influence over me.
me3
a numeric vector on a five-point Likert scale. Local Residents have influence over me.
me4
a numeric vector on a five-point Likert scale. Project Implementers have influence over me.
me5
a numeric vector on a five-point Likert scale. Research Units have influence over me.
me6
a numeric vector on a five-point Likert scale. Local Authorities have influence over me.
data(DataExp)
data(DataExp)
Draws histograms of responses
Histograms(path, tofile, CountResponses)
Histograms(path, tofile, CountResponses)
path |
a path of a particular catalogue in which pictures are saved, set path="" when tofile=0 |
tofile |
logical. 1=save-to-file. 0=show-on-screen |
CountResponses |
the result of the PrelCalc function |
The function draws histograms of responses
Histograms |
Histograms of responses |
Sebastian Susmarski, Lech Kujawski, Anna Zamojska, Piort Zientar
# first import DataExp data(DataExp) # then execute PrelCalc() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) # Histograms() Histograms(path="",tofile=0,CountResponses=PrelCalcExp$CountResponses)
# first import DataExp data(DataExp) # then execute PrelCalc() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) # Histograms() Histograms(path="",tofile=0,CountResponses=PrelCalcExp$CountResponses)
Calculates, based on the Leontief model, qS or the reduction in stakeholder ineffectiveness
ImpactAnalysis(data, BenefCost, NoStakeholders, NameStakeholders)
ImpactAnalysis(data, BenefCost, NoStakeholders, NameStakeholders)
data |
data gathered from a questionnaire employing a five-point Likert scale. The csv file is preferable due to the volume of data |
BenefCost |
the benefit indicator and the cost indicator. The $BenefCostInd from the BenefCost function should be used |
NoStakeholders |
the number of stakeholder groups (from the PrelCalc function) |
NameStakeholders |
the names of stakeholder groups (from the PrelCalc function) |
The function calculates, based on the Leontief model, qS or the reduction in stakeholder ineffectiveness and then determines the stakeholder influence (SI) indicator, as described by Hester and Adams (2013). In addition, it calculates the indicator of benefits and the indicator of costs, factoring in the Leontief coefficient matrix
Leontief |
the first two columns show the indicator of benefits and the indicator of costs. The middle column indicates qS. The two final columns show the indicator of benefits and the indicator of costs, factoring in the Leontief coefficient matrix |
MyImpact , OnMeImpact , MeanImpact
|
matrices of impact-based stakeholder relationships |
Sebastian Susmarski, Lech Kujawski, Anna Zamojska, Piotr Zientara
Hester and Adams (2013)
# first import DataExp data(DataExp) # then execute PrelCalc(), BenefCost() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) BenefCostExp=BenefCost(CountResponses=PrelCalcExp$CountResponses) # ImpactAnalysis() ImpactAnalysisExp=ImpactAnalysis(data=DataExp, BenefCost=BenefCostExp$BenefCostInd, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) ImpactAnalysisExp
# first import DataExp data(DataExp) # then execute PrelCalc(), BenefCost() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) BenefCostExp=BenefCost(CountResponses=PrelCalcExp$CountResponses) # ImpactAnalysis() ImpactAnalysisExp=ImpactAnalysis(data=DataExp, BenefCost=BenefCostExp$BenefCostInd, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) ImpactAnalysisExp
Performs preliminary calculations on raw data. Counts responses to items measuring stakeholder attributes as well as benefits and costs from a questionnaire employing a five-point Likert scale
PrelCalc(data, NoAtt, NoPow, NoUrg, NoLeg, NoBen, NoCos)
PrelCalc(data, NoAtt, NoPow, NoUrg, NoLeg, NoBen, NoCos)
data |
data gathered from a questionnaire employing a five-point Likert scale. The csv file is preferable due to the volume of data |
NoAtt |
indicates col numbers related to the Attitude construct |
NoPow |
indicates col numbers related to the Power construct |
NoUrg |
indicates col numbers related to the Urgency construct |
NoLeg |
indicates col numbers related to the Legitimacy construct |
NoBen |
indicates col numbers related to the Benefits construct |
NoCos |
indicates col numbers related to the Costs construct |
Data are collected by means of a questionnaire survey with a five-point Likert scale. PrelCalc performs preliminary calculations on raw data, counting responses to items measuring all the constructs (Attitude, Power, Urgency, Legitimacy, Benefits, Costs). These denote stakeholder attributes and benefits/costs. In addition, it identifies particular stakeholder groups (based on their names)
CountResponses |
30 x number of stakeholder groups matrix of counted responses related to all the constructs |
NoStakeholders |
the number of stakeholder groups |
NameStakeholders |
the names of stakeholder groups |
NoAttrib |
$Att, $Pow, $Urg, $Leg, $Ben, $Cos |
NoAttrib$Att |
numbers in the raw data set related to the Attitude construct |
NoAttrib$Pow |
col numbers in the raw data set related to the Power construct |
NoAttrib$Urg |
col numbers in the raw data set related to the Urgency construct |
NoAttrib$Leg |
col numbers in the raw data set related to the Legitimacy construct |
NoAttrib$Ben |
col numbers in the raw data set related to the Benefits construct |
NoAttrib$Cos |
col numbers in the raw data set related to the Costs construct |
Lech Kujawski, Sebastian Susmarski, Anna Zamojska, Piotr Zientara
# first import DataExp data(DataExp) # PrelCalc() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) PrelCalcExp
# first import DataExp data(DataExp) # PrelCalc() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) PrelCalcExp
Draws a picture of stakeholder relationships
RelationPict(path, tofile, MeanImpact, StakeholdClassif)
RelationPict(path, tofile, MeanImpact, StakeholdClassif)
path |
a path of a particular catalogue in which pictures are saved, set path="" when tofile=0 |
tofile |
logical. 1=save-to-file. 0=show-on-screen |
MeanImpact |
the Leontief coefficient matrix. The $MeanImpact from the ImpactAnalysis function should be used |
StakeholdClassif |
the result of the StakeholdClassif function |
The function draws a picture of stakeholder relationships with arrows and circles in different colours
A picture of stakeholder relationships
Sebastian Susmarski, Lech Kujawski, Anna Zamojska, Piotr Zientar
# first import DataExp data(DataExp) # then execute PrelCalc(), RespVerif(), AttribIdent(), CollabPotential() # BenefCost(), StakeholdClassif(), ImpactAnalysis() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) RespVerifExp=RespVerif(CountResponses=PrelCalcExp$CountResponses, NoStakeholders=PrelCalcExp$NoStakeholders) AttribIdentExp=AttribIdent(TestedResponses=RespVerifExp, NoAttrib=PrelCalcExp$NoAttrib, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) CollabPotentialExp=CollabPotential(AttribIdent=AttribIdentExp) BenefCostExp=BenefCost(CountResponses=PrelCalcExp$CountResponses) StakeholdClassifByMean=StakeholdClassif(BenefCostTest=BenefCostExp$BenefCostTest, CollabPotential=CollabPotentialExp$Mean,AttribIdent=AttribIdentExp$Mean) ImpactAnalysisExp=ImpactAnalysis(data=DataExp, BenefCost=BenefCostExp$BenefCostInd, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) # RelationPict() RelationPict(path="",tofile=0,MeanImpact=ImpactAnalysisExp$MeanImpact, StakeholdClassif=StakeholdClassifByMean)
# first import DataExp data(DataExp) # then execute PrelCalc(), RespVerif(), AttribIdent(), CollabPotential() # BenefCost(), StakeholdClassif(), ImpactAnalysis() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) RespVerifExp=RespVerif(CountResponses=PrelCalcExp$CountResponses, NoStakeholders=PrelCalcExp$NoStakeholders) AttribIdentExp=AttribIdent(TestedResponses=RespVerifExp, NoAttrib=PrelCalcExp$NoAttrib, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) CollabPotentialExp=CollabPotential(AttribIdent=AttribIdentExp) BenefCostExp=BenefCost(CountResponses=PrelCalcExp$CountResponses) StakeholdClassifByMean=StakeholdClassif(BenefCostTest=BenefCostExp$BenefCostTest, CollabPotential=CollabPotentialExp$Mean,AttribIdent=AttribIdentExp$Mean) ImpactAnalysisExp=ImpactAnalysis(data=DataExp, BenefCost=BenefCostExp$BenefCostInd, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) # RelationPict() RelationPict(path="",tofile=0,MeanImpact=ImpactAnalysisExp$MeanImpact, StakeholdClassif=StakeholdClassifByMean)
Performs tests of statistical significance of the means and fractions of responses
RespVerif(CountResponses, NoStakeholders)
RespVerif(CountResponses, NoStakeholders)
CountResponses |
the $CountResponses result of the PreCalc function (i.e., 30 x number of stakeholder groups matrix of counted responses related to all the constructs) |
NoStakeholders |
the number of stakeholder groups (i.e., the $NoStakeholders result of the PreCalc function) |
The function performs two tests of statistical significance: (1) the means and (2) the fractions of responses. As regards (1), H0 states that the mean of responses to a particular item is equal to "3" (i.e., a neutral response on a five-point Likert scale); H1 states that the mean is not equal to "3" (i.e., a two-sides alternative hypothesis). As regards (2), H0 states that the fraction of the "1" and "2" responses is equal to the fraction of the "4" and "5" responses; H1 states that the fraction of the "1" and "2" responses is not equal to the fraction of the "4" and "5" responses (i.e., a two-sides alternative hypothesis)
Mean |
(3 x the number of stakeholder groups) x 6 matrix. The first row indicates the mean response. The second row reports stat value. The third row indicates prob. The same pattern applies to each stakeholder group |
Fra |
(3 x the number of stakeholder groups) x (3 x 6) matrix. The first row indicates the number of negative ("1" and "2"), neutral ("3") and positive ("4" and "5") responses. The second row reports fractions of responses. The third row reports stat/prob |
Sebastian Susmarski, Lech Kujawski, Anna Zamojska, Piotr Zientara
# first import DataExp data(DataExp) # then execute PrelCalc() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) # RespVerif RespVerifExp=RespVerif(CountResponses=PrelCalcExp$CountResponses, NoStakeholders=PrelCalcExp$NoStakeholders) RespVerifExp
# first import DataExp data(DataExp) # then execute PrelCalc() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) # RespVerif RespVerifExp=RespVerif(CountResponses=PrelCalcExp$CountResponses, NoStakeholders=PrelCalcExp$NoStakeholders) RespVerifExp
Classifies stakeholder groups and suggests communication strategies
StakeholdClassif(BenefCostTest, CollabPotential, AttribIdent)
StakeholdClassif(BenefCostTest, CollabPotential, AttribIdent)
BenefCostTest |
the result of a Student's t-test (with H0 stating that the mean of benefits and the mean of costs are equal). The $BenefCostTest from the BenefCost function should be used |
CollabPotential |
the potential for collaboration. The $Mean or the $Fra from the CollabPotential function should be used |
AttribIdent |
identified stakeholder attributes. The $Mean or the $Fra from the AttribIdent function should be used |
The function first classifies stakeholder groups into categories, as described by Mitchell, Agle and Wood (1997). It then determines their attitudes ("supportive", "non-supportive", "mixed", "neutral", "insignificant") and, with the potential for collaboration taken into account, suggests a communication strategy vis-a-vis a particular stakeholder group
The number of stakeholder groups x 3 data frame. The first column indicates stakeholder classification. The second column shows stakeholder attitudes. The third column suggests a communication strategy
Sebastian Susmarski, Lech Kujawski, Anna Zamojska, Piotr Zientara
Mitchell, Agle and Wood (1997)
# first import DataExp data(DataExp) # then execute PrelCalc(), RespVerif(), AttibIdent(), BenefCost() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) RespVerifExp=RespVerif(CountResponses=PrelCalcExp$CountResponses, NoStakeholders=PrelCalcExp$NoStakeholders) AttribIdentExp=AttribIdent(TestedResponses=RespVerifExp, NoAttrib=PrelCalcExp$NoAttrib, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) CollabPotentialExp=CollabPotential(AttribIdent=AttribIdentExp) BenefCostExp=BenefCost(CountResponses=PrelCalcExp$CountResponses) # StakeholdClassif() StakeholdClassifByMean=StakeholdClassif(BenefCostTest=BenefCostExp$BenefCostTest, CollabPotential=CollabPotentialExp$Mean,AttribIdent=AttribIdentExp$Mean) StakeholdClassifByFraction=StakeholdClassif(BenefCostTest=BenefCostExp$BenefCostTest, CollabPotential=CollabPotentialExp$Fra,AttribIdent=AttribIdentExp$Fra) StakeholdClassifByMean StakeholdClassifByFraction
# first import DataExp data(DataExp) # then execute PrelCalc(), RespVerif(), AttibIdent(), BenefCost() PrelCalcExp=PrelCalc(data=DataExp, NoAtt=c(2,11,13,15),NoPow=c(3,8,14,16), NoUrg=c(4,6,10,12),NoLeg=c(5,7,9,17),NoBen=18:22,NoCos=23:27) RespVerifExp=RespVerif(CountResponses=PrelCalcExp$CountResponses, NoStakeholders=PrelCalcExp$NoStakeholders) AttribIdentExp=AttribIdent(TestedResponses=RespVerifExp, NoAttrib=PrelCalcExp$NoAttrib, NoStakeholders=PrelCalcExp$NoStakeholders, NameStakeholders=PrelCalcExp$NameStakeholders) CollabPotentialExp=CollabPotential(AttribIdent=AttribIdentExp) BenefCostExp=BenefCost(CountResponses=PrelCalcExp$CountResponses) # StakeholdClassif() StakeholdClassifByMean=StakeholdClassif(BenefCostTest=BenefCostExp$BenefCostTest, CollabPotential=CollabPotentialExp$Mean,AttribIdent=AttribIdentExp$Mean) StakeholdClassifByFraction=StakeholdClassif(BenefCostTest=BenefCostExp$BenefCostTest, CollabPotential=CollabPotentialExp$Fra,AttribIdent=AttribIdentExp$Fra) StakeholdClassifByMean StakeholdClassifByFraction