Quantitative Data Analysis(with SPSS)

  • Category:
    Management
  • Document type:
    Assignment
  • Level:
    Masters
  • Page:
    2
  • Words:
    851

5. Discussion

Descriptive and inferential data analyses were done on the three variables, Satisfaction, Commitment and TurnoverIntention, using the Statistical Package for Social Sciences (SPSS). Inferential statistics is used to test the following hypotheses;

H1: Job satisfaction and turnover intention negatively related

H2: Job satisfaction and commitment positively related

H3: Commitment and turnover intention negatively related.

Descriptive statistics indicates the number of cases or sample size for each variable, measure of central tendency(mean) for each of the three variables and measure of variation (standard deviation for each of the three variables. From the descriptive table below, there were 146 cases for each of the three variables with absence of missing data from each of the three variables.

Table 1: Descriptive statistics for satisfaction, commitment and turnover intention

Descriptive Statistics

Std. Deviation

Satisfaction

Commitment

TurnoverIntention

Valid N (listwise)

Bivariate correlation analyses will be carried out to infer on the correlation between two variables. Pearson’s correlation statistic will be used to measure correlation.

The pearson’s correlation works under the following assumptions,

  1. Variables are linear

  2. Data is normally distributed

  3. There are no outliers in the data distribution.

A scatter plot matrix is used to test for linearity of the variables as shown in the table below.

Table 2: Scatter plot matrix for satisfaction, commitment and turnover intention

Quantitative Data Analysis(with SPSS)

A linear relationship can be inferred from the three sets of scatter plots above. Commitment and satisfaction have a positive linear relationship. TurnoverIntention and satisfaction have a relatively negative linear relationship. TurnoverIntention and commitment also have a negative linear relationship.

Normal P-P plots will be used to determine the normality of the distribution for the three variables and infer on outliers for the data values. The P-P plots in the Appendix indicate that all the variables are normaly distributed without. There are no observable outliers on any of the three variables.

With the three assumption proven, we carry out bivariate correlational tests on the data variables. The correlation matrix table below indicates the results of the bivariate correlation tests for the three variables.

Table 3: Correlation matrix for satisfaction, commitment and turnover intention

Correlations

Satisfaction

Commitment

TurnoverIntention

Satisfaction

Pearson Correlation

Sig. (1-tailed)

Commitment

Pearson Correlation

Sig. (1-tailed)

TurnoverIntention

Pearson Correlation

Sig. (1-tailed)

H2: Job satisfaction and commitment positively related

Satisfaction and commitment have a positive correlation co-efficient, 0.584. This correlation is significant since the p-value, 0.000 is less than the level of significance 5%.

Table 4: Model summary on relationship between commitment and satisfaction

Model Summary

Adjusted R Square

Std. Error of the Estimate

a. Predictors: (Constant), Commitment

The co-efficient of determination for relationship between commitment and satisfaction is 0.341. This is relatively weak relationship implying that 34.1% of the variance in commitment is attributed to satisfaction while 33.6% of the variance in commitment when controlled for covariance is attributed to the change in satisfaction.

H1: Job satisfaction and turnover intention negatively related

The correlation co-efficient for the relationship between satisfaction and turnoverintention is -0.564. This means that satisfaction is inversely (negatively) related to turnoverintention. The correlation is significant since the p-value, 0.000 is less than the level of significance, 5%.

Table 5: Model summary on relationship between turnover intention and satisfaction

Model Summary

Adjusted R Square

Std. Error of the Estimate

a. Predictors: (Constant), TurnoverIntention

31.8% of the variance in satisfaction is attributed to turnoverIntention. 31.4% of the change in Satisfaction is attributed to turnoverIntention when controlled for covariates. Therefore, satisfaction and TurnoverIntention have a relatively weak negative relationship.

H3: Commitment and turnover intention negatively related.

The correlation between Commitment and TurnoverIntention, -0.376 is significant since the p-value, 0.000 is less than the level of significance, 5%. Therefore, there exists a significant negative correlation between Commitment and TurnoverIntention.

Table 6: model summary on relationship between commitment and turnover intention

Model Summary

Adjusted R Square

Std. Error of the Estimate

a. Predictors: (Constant), TurnoverIntention

14.2% of the change in commitment is attributed to a change in TurnoverIntention. This implies that the relationship between TurnoverIntention and commitment is weak.

Implication

Health care needs both committed and long serving nurses for effective delivery of health care services. This study can help in healthcare human resource management by relating the factors that increase or reduce commitment and turnover of nurses. For example, in order to increase commitment for nurses, there is need to promote factors that boost job satisfaction for nurses. This would consequently lead to a reduction in turnover for nurses and improved healthcare system.

Limitation

The study does not comprehensively cover all the variables and factors that influence the job performance of a nurse. Therefore, the implication of the relationship established between job satisfaction, turnover intention and commitment may have little effect on the performance of nurses. With these limited number of variables for the study, the research may have limited implications on the application of its findings to nursing human resource management.

Recommendation for further research

Due to the limitations of the study variables, we recommend future study that incorporates more variables that affect and influence nurses’ performance. This study would conclude on a more detailed model that predicts nurses’ performance with more power and reliability.

Appendix

Quantitative Data Analysis(with SPSS) 1

Quantitative Data Analysis(with SPSS) 2

Quantitative Data Analysis(with SPSS) 3