Statistical package for social science software version 23

Both CSNs and nurse managers’ quantitative data were analysed with Statistical Package for Social Science software version 23 (IBM Corp, 2015, IBM SPSS Statistics for Windows, Version 23.0. Armonk, New York) and descriptive statistical methods (mean, standard deviation, frequency, percentage) and inferential statistical tests (Pearson correlation coefficient significance level, α = 0.5). Table 1 depicts the mentoring factors that were highlighted by CSNs. Majority of the CSNs agreed mostly on all mentoring factor items, with the scoring of above 90%, as compared to those who did not agree.
Out of the 174 nurse managers, the majority agreed on the mentoring factors as depicted in Table 2. The nurse managers also scored above 90% on all the mentoring factor items.
The qualitative data analysis process started by organising and preparing data from CSNs and nurse managers. Transcribed data were typed and again verified by listening to audio recordings repeatedly. ATLAS.ti 7 software (Berlin) was used to organise, manage and analyse data (Friese 2013 :4).
Both CSNs’ and nurse managers’ quantitative and qualitative results were then merged with an in-depth literature review to develop the mentoring guidelines.

The data were analyzed for a total of 380 samples. Among them, 98 samples were excluded from the analysis (the 98 samples that were detected as high concentration by unspecific factors were considered as robustness weights). All statistical analyses were performed using Statistical Package for Social Science software, Version 23 (IBM Corp., SPSS Inc., Armonk, NY, USA). In this study, Pearson’s correlation coefficient was used as the main correlation analysis, as it is most commonly used to statistically measure the level of correlation among the variables. Among the regression analysis, the stepwise regression analysis method was used because it only contains the variables that are able to influence the dependent variable into the equation. In order to certify the multiple regression model’s significance, the VIF coefficient was used to check multicollinearity.