Page 185 - Hojnik, Jana. 2017. In Persuit of Eco-innovation. Drivers and Consequences of Eco-innovation at Firm Level. Koper: University of Primorska Press
P. 185
Results
N Mean St. Dev. Skew St. Err. Kurt St. Err.
Skew Kurt
Reduced soil pol- 223 5.73 1.507 -1.400 0.163 1.579 0.324
lution.
223 5.53 1.524 -1.190 0.163 1.008 0.324
Reduced noise pol-
lution. 223 5.60 1.433 -1.285 0.163 1.513 0.324
Replaced materials
with less hazardous
substitutes.
Note: N = number of observations; Mean = mean value on the Likert scale, which ranges 185
from 1 to 7 (1 = strongly disagree, 7 = strongly agree); St. Dev. = standard deviation; Skew =
skewness; St. Err. of Skew = standard error of skewness; Kurt = kurtosis; St. Err. Kurt = stan-
dard error of kurtosis. *Measurement items for process eco-innovation used also in the final
analyses pertaining to the model testing.
As above, we conducted an exploratory factor analysis. Before the
analysis, all measurement items were checked for normality of distribu-
tion (see Table 47). Results have shown that the ratio of standard errors
of kurtosis and skewness range between values of -2 and 2, which im-
plies normality of distribution. The method of extraction in the explor-
atory analysis was Maximum Likelihood Method, while the selected ro-
tation was Direct Oblimin rotation, which assumes that different factors
are related.
The appropriateness of factor analysis was determined by examining
the correlation matrix of process eco-innovation items. The Bartlett’s test
of sphericity showed that correlation matrix has significant correlations
(sig. = 0.000 for all items). Furthermore, the Kaiser-Meyer-Olkin meas-
ure of sampling adequacy was examined and indicated similar results;
specifically, the KMO value was 0.861, which indicates an excellent sam-
ple adequacy.
The number of expected factors was one, and the extracted factor was
one, explaining 68.441% of variance. After consideration of each item’s
communality index and its contribution, we retained all the items (the
lowest communality after extraction was 0.512).
N Mean St. Dev. Skew St. Err. Kurt St. Err.
Skew Kurt
Reduced soil pol- 223 5.73 1.507 -1.400 0.163 1.579 0.324
lution.
223 5.53 1.524 -1.190 0.163 1.008 0.324
Reduced noise pol-
lution. 223 5.60 1.433 -1.285 0.163 1.513 0.324
Replaced materials
with less hazardous
substitutes.
Note: N = number of observations; Mean = mean value on the Likert scale, which ranges 185
from 1 to 7 (1 = strongly disagree, 7 = strongly agree); St. Dev. = standard deviation; Skew =
skewness; St. Err. of Skew = standard error of skewness; Kurt = kurtosis; St. Err. Kurt = stan-
dard error of kurtosis. *Measurement items for process eco-innovation used also in the final
analyses pertaining to the model testing.
As above, we conducted an exploratory factor analysis. Before the
analysis, all measurement items were checked for normality of distribu-
tion (see Table 47). Results have shown that the ratio of standard errors
of kurtosis and skewness range between values of -2 and 2, which im-
plies normality of distribution. The method of extraction in the explor-
atory analysis was Maximum Likelihood Method, while the selected ro-
tation was Direct Oblimin rotation, which assumes that different factors
are related.
The appropriateness of factor analysis was determined by examining
the correlation matrix of process eco-innovation items. The Bartlett’s test
of sphericity showed that correlation matrix has significant correlations
(sig. = 0.000 for all items). Furthermore, the Kaiser-Meyer-Olkin meas-
ure of sampling adequacy was examined and indicated similar results;
specifically, the KMO value was 0.861, which indicates an excellent sam-
ple adequacy.
The number of expected factors was one, and the extracted factor was
one, explaining 68.441% of variance. After consideration of each item’s
communality index and its contribution, we retained all the items (the
lowest communality after extraction was 0.512).
