Page 136 - Hojnik, Jana. 2017. In Persuit of Eco-innovation. Drivers and Consequences of Eco-innovation at Firm Level. Koper: University of Primorska Press
P. 136
In Pursuit of Eco-innovation
as growth of employees, which can lead to the missing data. We investi-
gated data for missing values and concluded that data were missing com-
pletely at random since no pattern of missing data was found. Regard-
ing the missing data related to the company’s financial data (profitability
indicator ratios and regarding the company’s growth), as we explained
above, in such a case imputation is not an appropriate solution. Thus, the
number of retained responses usable for analysis is 223.
Common method variance assessment
Since we used a single informant from each of the companies to complete
the survey, concerns of common method variance (hereinafter CMV)
should be addressed (Podsakoff et al. 2003). CMV is addressed because
the majority of data are self-reported (using a single informant from each
136 of the companies) and the data were collected through the same ques-
tionnaire during the same period of time with a cross-sectional research
design. Thus, the CMV is attributed to the measurement method rather
than the constructs of interest and may cause systematic measurement er-
ror and further bias the estimates of the true relationship among the the-
oretical constructs. Therefore, we also analyzed data for common method
variance problems by following the recommendations of Podsakoff et al.
(2003). The potential for common method variance has been reduced by
ensuring confidentiality to respondents participating in our study and, as
aforementioned, by pre-testing the questionnaire items for their unambi-
guity, clearness and familiarity of wording. In this study, CMV is exam-
ined by Harman’s single factor test, which is the most widely used meth-
od to assess the possibility of CMV. Podsakoff and Organ (1986) stressed
that if CMV is present, a single factor will emerge from the factor analysis
of all survey items. Therefore, we used all survey items from the 223 ques-
tionnaires to conduct an exploratory factor analysis in SPSS. The un-ro-
tated principal components factor analysis results demonstrate that no
single factor accounts for the majority of the variance and that the first
factor captures only 34.189% of the variance, which suggests that CMV
is not present.
Data analyses
The data were analyzed using univariate and multivariate statistical
methods conducted with the statistical program SPSS (version 21). For
each construct used in our eco-innovation model, we tested the reliabil-
ity of the construct (using Cronbach’s alpha), and we further conduct-
as growth of employees, which can lead to the missing data. We investi-
gated data for missing values and concluded that data were missing com-
pletely at random since no pattern of missing data was found. Regard-
ing the missing data related to the company’s financial data (profitability
indicator ratios and regarding the company’s growth), as we explained
above, in such a case imputation is not an appropriate solution. Thus, the
number of retained responses usable for analysis is 223.
Common method variance assessment
Since we used a single informant from each of the companies to complete
the survey, concerns of common method variance (hereinafter CMV)
should be addressed (Podsakoff et al. 2003). CMV is addressed because
the majority of data are self-reported (using a single informant from each
136 of the companies) and the data were collected through the same ques-
tionnaire during the same period of time with a cross-sectional research
design. Thus, the CMV is attributed to the measurement method rather
than the constructs of interest and may cause systematic measurement er-
ror and further bias the estimates of the true relationship among the the-
oretical constructs. Therefore, we also analyzed data for common method
variance problems by following the recommendations of Podsakoff et al.
(2003). The potential for common method variance has been reduced by
ensuring confidentiality to respondents participating in our study and, as
aforementioned, by pre-testing the questionnaire items for their unambi-
guity, clearness and familiarity of wording. In this study, CMV is exam-
ined by Harman’s single factor test, which is the most widely used meth-
od to assess the possibility of CMV. Podsakoff and Organ (1986) stressed
that if CMV is present, a single factor will emerge from the factor analysis
of all survey items. Therefore, we used all survey items from the 223 ques-
tionnaires to conduct an exploratory factor analysis in SPSS. The un-ro-
tated principal components factor analysis results demonstrate that no
single factor accounts for the majority of the variance and that the first
factor captures only 34.189% of the variance, which suggests that CMV
is not present.
Data analyses
The data were analyzed using univariate and multivariate statistical
methods conducted with the statistical program SPSS (version 21). For
each construct used in our eco-innovation model, we tested the reliabil-
ity of the construct (using Cronbach’s alpha), and we further conduct-
