Assignment 1
Dsimms
2025-03-21
Job Satisfaction Survey
Introduction
The following report is an analysis of a job satisfaction survey. There were 32 respondents answering 10 questions (a portion is shown below).The objective of this survey is to look at the overall satisfaction of the employees and understand some factors that impact it. There are some areas of concern and excellence that will be mentioned. This report will look at some key graphs and provide predictive value for future surveys. The resulting confusion matrices will determine and other factors will determine the usefulness of the predictive methods.
| Department | Years | Ideas | Communication | Recognition | Training | Conditions | Tools | Balance | Satisfaction |
|---|---|---|---|---|---|---|---|---|---|
| Administrative | 16 | 2 | 3 | 2 | 2 | 4 | 5 | 2 | 3 |
| Administrative | 2 | 4 | 4 | 3 | 4 | 4 | 5 | 3 | 9 |
| Administrative | 14 | 4 | 3 | 2 | 2 | 5 | 5 | 5 | 6 |
| Maintenance | 17 | 5 | 4 | 3 | 5 | 5 | 5 | 3 | 8 |
| Maintenance | 15 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | 9 |
Notes on Data
With only 32 responses, there is a limit to the quality of analysis. There are no outliers in Satisfaction nor are there any missing values in the data table. There has been some data transformation for particular instances. In every case a disclaimer and explanation is provided.
Histogram Summary
The following is a summary of the given numerical values of each attribute. Years has been binned with a bin width of 5 years.
Findings
Distribution It seems the only category where the data resembles normal distribution is recognition. The rest seem to be skewed.
Satisfaction by Department
By breaking the data down by department, department managers can better understand their individual departments. They can evaluate how it is doing in each category. They may be able to do follow up studies or customize their approach to their employees. The following graphs show
The following boxplots examine the overall satisfaction of the
company by department.
A further breakdown of each departments the average scores in each scored category. To keep the graph focused, Satisfaction scores have been transformed to a scale of 0 to 5, meaning they are half of their original scores.
Findings
Areas of success: The Departments with the highest median satisfaction score were Maintenance and QC with a score of 8.5. With the exception of Balance, these two had first and second highest mean values in every category. Tools is the category which received the highest mean score from every department. The workers seem to believe they have the equipment needed for their tasks.
Areas of Concern: Administration finished with the lowest average satisfaction. Their mean Recognition score was the lowest mean category score of any department. Further investigation may be warranted. SR had the lowest median satisfaction. Management had very low training scores. This combined with other deficiencies, resulted in this department having the third lowest satisfaction. Low satisfaction among management may negatively impact the efficiency and morale of other workers. So, this should be further investigated.
Satisfaction by Tenure
Correlation Geat map
| Years | Ideas | Communication | Recognition | Training | Conditions | Tools | Balance | Satisfaction | |
|---|---|---|---|---|---|---|---|---|---|
| Years | 1.00 | -0.25 | -0.38 | -0.34 | 0.13 | -0.17 | 0.10 | -0.38 | -0.32 |
| Ideas | -0.25 | 1.00 | 0.63 | 0.78 | 0.52 | 0.49 | 0.22 | 0.63 | 0.85 |
| Communication | -0.38 | 0.63 | 1.00 | 0.69 | 0.51 | 0.43 | 0.34 | 0.54 | 0.72 |
| Recognition | -0.34 | 0.78 | 0.69 | 1.00 | 0.55 | 0.56 | 0.25 | 0.67 | 0.84 |
| Training | 0.13 | 0.52 | 0.51 | 0.55 | 1.00 | 0.55 | 0.21 | 0.29 | 0.69 |
| Conditions | -0.17 | 0.49 | 0.43 | 0.56 | 0.55 | 1.00 | 0.23 | 0.52 | 0.65 |
| Tools | 0.10 | 0.22 | 0.34 | 0.25 | 0.21 | 0.23 | 1.00 | 0.19 | 0.20 |
| Balance | -0.38 | 0.63 | 0.54 | 0.67 | 0.29 | 0.52 | 0.19 | 1.00 | 0.71 |
| Satisfaction | -0.32 | 0.85 | 0.72 | 0.84 | 0.69 | 0.65 | 0.20 | 0.71 | 1.00 |
Findings
Tenure and Satisfaction With the is a negative correlation between years worked at the company and the score given to most of the other variables, particularly Satisfaction. Though the correlations are weak, since this is the only predetermined numerical variable for each employee, these relationships should be examined.
Satisfaction and other variables The perceived value of employee ideas and corresponding recognition are the most important variables when looking at overall satisfaction.
Prediction Methods
KNN
Translated Data
The objective of using KNN is to predict if an individual will have above average satisfaction.No partitioning of the data was done.| Department | Years | Ideas | Communication | Recognition | Training | Conditions | Tools | Balance | Satisfaction.Level |
|---|---|---|---|---|---|---|---|---|---|
| Administrative | 16 | 2 | 3 | 2 | 2 | 4 | 5 | 2 | Low |
| Administrative | 2 | 4 | 4 | 3 | 4 | 4 | 5 | 3 | High |
| Administrative | 14 | 4 | 3 | 2 | 2 | 5 | 5 | 5 | Low |
| Maintenance | 17 | 5 | 4 | 3 | 5 | 5 | 5 | 3 | High |
| Maintenance | 15 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | High |
| Management | 1 | 5 | 4 | 4 | 3 | 5 | 3 | 5 | High |
| Management | 3 | 3 | 4 | 3 | 3 | 4 | 5 | 5 | High |
| Management | 3 | 2 | 2 | 2 | 2 | 3 | 5 | 3 | Low |
| Production | 16 | 2 | 3 | 2 | 4 | 4 | 4 | 2 | Low |
| Production | 15 | 2 | 3 | 1 | 4 | 4 | 4 | 2 | Low |
| Production | 13 | 3 | 3 | 3 | 4 | 4 | 4 | 3 | High |
| Production | 3 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | High |
| Production | 6 | 2 | 2 | 1 | 3 | 3 | 4 | 2 | Low |
| Production | 1 | 5 | 4 | 4 | 3 | 4 | 5 | 5 | High |
| Production | 3 | 3 | 4 | 3 | 4 | 5 | 5 | 4 | High |
| Production | 2 | 4 | 4 | 4 | 4 | 5 | 5 | 5 | High |
| Production | 3 | 3 | 4 | 3 | 3 | 2 | 4 | 4 | Low |
| Production | 2 | 4 | 3 | 4 | 3 | 3 | 4 | 4 | Low |
| Production | 2 | 4 | 5 | 4 | 4 | 4 | 4 | 4 | High |
| Production | 15 | 5 | 4 | 3 | 4 | 3 | 5 | 3 | High |
| Production | 5 | 4 | 5 | 3 | 2 | 3 | 5 | 4 | High |
| Production | 8 | 5 | 5 | 3 | 5 | 3 | 5 | 3 | High |
| Production | 17 | 4 | 3 | 4 | 3 | 3 | 5 | 2 | Low |
| Production | 15 | 5 | 3 | 4 | 5 | 5 | 5 | 5 | High |
| Production | 5 | 2 | 4 | 2 | 2 | 2 | 5 | 3 | Low |
| QC | 1 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | High |
| QC | 11 | 3 | 4 | 4 | 4 | 5 | 5 | 2 | High |
| SR | 21 | 3 | 2 | 2 | 3 | 2 | 4 | 3 | Low |
| SR | 8 | 3 | 2 | 2 | 2 | 2 | 4 | 2 | Low |
| SR | 32 | 2 | 3 | 2 | 4 | 2 | 5 | 3 | Low |
| SR | 2 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | High |
| SR | 18 | 4 | 4 | 4 | 5 | 5 | 5 | 5 | High |
## k-Nearest Neighbors
##
## 32 samples
## 9 predictor
## 2 classes: 'High', 'Low'
##
## No pre-processing
## Resampling: Cross-Validated (7 fold, repeated 3 times)
## Summary of sample sizes: 27, 27, 28, 28, 27, 27, ...
## Resampling results across tuning parameters:
##
## k Accuracy Kappa
## 5 0.8111111 0.5890887
## 7 0.7587302 0.4466835
## 9 0.6682540 0.2232878
##
## Accuracy was used to select the optimal model using the largest value.
## The final value used for the model was k = 5.
| Department | Years | Ideas | Communication | Recognition | Training | Conditions | Tools | Balance | Satisfaction.Level | prediction |
|---|---|---|---|---|---|---|---|---|---|---|
| Administrative | 16 | 2 | 3 | 2 | 2 | 4 | 5 | 2 | Low | Low |
| Administrative | 2 | 4 | 4 | 3 | 4 | 4 | 5 | 3 | High | High |
| Administrative | 14 | 4 | 3 | 2 | 2 | 5 | 5 | 5 | Low | High |
| Maintenance | 17 | 5 | 4 | 3 | 5 | 5 | 5 | 3 | High | High |
| Maintenance | 15 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | High | High |
| Management | 1 | 5 | 4 | 4 | 3 | 5 | 3 | 5 | High | High |
| Management | 3 | 3 | 4 | 3 | 3 | 4 | 5 | 5 | High | High |
| Management | 3 | 2 | 2 | 2 | 2 | 3 | 5 | 3 | Low | Low |
| Production | 16 | 2 | 3 | 2 | 4 | 4 | 4 | 2 | Low | Low |
| Production | 15 | 2 | 3 | 1 | 4 | 4 | 4 | 2 | Low | Low |
| Production | 13 | 3 | 3 | 3 | 4 | 4 | 4 | 3 | High | High |
| Production | 3 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | High | High |
| Production | 6 | 2 | 2 | 1 | 3 | 3 | 4 | 2 | Low | Low |
| Production | 1 | 5 | 4 | 4 | 3 | 4 | 5 | 5 | High | High |
| Production | 3 | 3 | 4 | 3 | 4 | 5 | 5 | 4 | High | High |
| Production | 2 | 4 | 4 | 4 | 4 | 5 | 5 | 5 | High | High |
| Production | 3 | 3 | 4 | 3 | 3 | 2 | 4 | 4 | Low | Low |
| Production | 2 | 4 | 3 | 4 | 3 | 3 | 4 | 4 | Low | High |
| Production | 2 | 4 | 5 | 4 | 4 | 4 | 4 | 4 | High | High |
| Production | 15 | 5 | 4 | 3 | 4 | 3 | 5 | 3 | High | High |
| Production | 5 | 4 | 5 | 3 | 2 | 3 | 5 | 4 | High | High |
| Production | 8 | 5 | 5 | 3 | 5 | 3 | 5 | 3 | High | High |
| Production | 17 | 4 | 3 | 4 | 3 | 3 | 5 | 2 | Low | Low |
| Production | 15 | 5 | 3 | 4 | 5 | 5 | 5 | 5 | High | High |
| Production | 5 | 2 | 4 | 2 | 2 | 2 | 5 | 3 | Low | Low |
| QC | 1 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | High | High |
| QC | 11 | 3 | 4 | 4 | 4 | 5 | 5 | 2 | High | High |
| SR | 21 | 3 | 2 | 2 | 3 | 2 | 4 | 3 | Low | Low |
| SR | 8 | 3 | 2 | 2 | 2 | 2 | 4 | 2 | Low | Low |
| SR | 32 | 2 | 3 | 2 | 4 | 2 | 5 | 3 | Low | Low |
| SR | 2 | 5 | 5 | 5 | 5 | 5 | 5 | 5 | High | High |
| SR | 18 | 4 | 4 | 4 | 5 | 5 | 5 | 5 | High | High |
## Confusion Matrix and Statistics
##
## Reference
## Prediction High Low
## High 19 2
## Low 0 11
##
## Accuracy : 0.9375
## 95% CI : (0.7919, 0.9923)
## No Information Rate : 0.5938
## P-Value [Acc > NIR] : 1.452e-05
##
## Kappa : 0.8672
##
## Mcnemar's Test P-Value : 0.4795
##
## Sensitivity : 1.0000
## Specificity : 0.8462
## Pos Pred Value : 0.9048
## Neg Pred Value : 1.0000
## Prevalence : 0.5938
## Detection Rate : 0.5938
## Detection Prevalence : 0.6562
## Balanced Accuracy : 0.9231
##
## 'Positive' Class : High
## Findings
Optimal K The optimal K was 7 with a 94% accuracy rate.
ConcernsThere is an issue with using KNN due to the number of predictor variables and limited respondents. This will limit this tools ability to accurately predict. To remedy this problem, add more respondents or remove dimensions.
Naive Bayes
Translated Data
The objective of using Naive Bayes is to predict if an individual will have above average satisfaction. No partitioning of the data was done. However there has been some data transformation, where each numerical attribute is converted to a categorical value of “High” or “Low” referring to the original value in relationship to the mean score of the attribute.| Dep | Yrs | Ids | Com | Rec | Tra | Con | Tls | Bal | Sat |
|---|---|---|---|---|---|---|---|---|---|
| Administrative | High | Low | Low | Low | Low | High | High | Low | Low |
| Administrative | Low | High | High | Low | High | High | High | Low | High |
| Administrative | High | High | Low | Low | Low | High | High | High | Low |
| Maintenance | High | High | High | Low | High | High | High | Low | High |
| Maintenance | High | High | High | High | High | High | High | High | High |
| Management | Low | High | High | High | Low | High | Low | High | High |
| Management | Low | Low | High | Low | Low | High | High | High | High |
| Management | Low | Low | Low | Low | Low | Low | High | Low | Low |
| Production | High | Low | Low | Low | High | High | Low | Low | Low |
| Production | High | Low | Low | Low | High | High | Low | Low | Low |
| Production | High | Low | Low | Low | High | High | Low | Low | High |
| Production | Low | High | High | High | High | High | High | High | High |
| Production | Low | Low | Low | Low | Low | Low | Low | Low | Low |
| Production | Low | High | High | High | Low | High | High | High | High |
| Production | Low | Low | High | Low | High | High | High | High | High |
| Production | Low | High | High | High | High | High | High | High | High |
| Production | Low | Low | High | Low | Low | Low | Low | High | Low |
| Production | Low | High | Low | High | Low | Low | Low | High | Low |
| Production | Low | High | High | High | High | High | Low | High | High |
| Production | High | High | High | Low | High | Low | High | Low | High |
| Production | Low | High | High | Low | Low | Low | High | High | High |
| Production | Low | High | High | Low | High | Low | High | Low | High |
| Production | High | High | Low | High | Low | Low | High | Low | Low |
| Production | High | High | Low | High | High | High | High | High | High |
| Production | Low | Low | High | Low | Low | Low | High | Low | Low |
| QC | Low | High | High | High | High | High | High | High | High |
| QC | High | Low | High | High | High | High | High | Low | High |
| SR | High | Low | Low | Low | Low | Low | Low | Low | Low |
| SR | Low | Low | Low | Low | Low | Low | Low | Low | Low |
| SR | High | Low | Low | Low | High | Low | High | Low | Low |
| SR | Low | High | High | High | High | High | High | High | High |
| SR | High | High | High | High | High | High | High | High | High |
Predicted Classes and Values
| Dep | Yrs | Ids | Com | Rec | Tra | Con | Tls | Bal | Sat | High | Low | Predicted |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Administrative | High | Low | Low | Low | Low | High | High | Low | Low | 0.0032 | 0.9968 | Low |
| Administrative | Low | High | High | Low | High | High | High | Low | High | 0.9794 | 0.0206 | High |
| Administrative | High | High | Low | Low | Low | High | High | High | Low | 0.2269 | 0.7731 | Low |
| Maintenance | High | High | High | Low | High | High | High | Low | High | 0.9999 | 0.0001 | High |
| Maintenance | High | High | High | High | High | High | High | High | High | 1.0000 | 0.0000 | High |
| Management | Low | High | High | High | Low | High | Low | High | High | 0.9926 | 0.0074 | High |
| Management | Low | Low | High | Low | Low | High | High | High | High | 0.8978 | 0.1022 | High |
| Management | Low | Low | Low | Low | Low | Low | High | Low | Low | 0.0022 | 0.9978 | Low |
| Production | High | Low | Low | Low | High | High | Low | Low | Low | 0.0183 | 0.9817 | Low |
| Production | High | Low | Low | Low | High | High | Low | Low | Low | 0.0183 | 0.9817 | Low |
| Production | High | Low | Low | Low | High | High | Low | Low | High | 0.0183 | 0.9817 | Low |
| Production | Low | High | High | High | High | High | High | High | High | 0.9999 | 0.0001 | High |
| Production | Low | Low | Low | Low | Low | Low | Low | Low | Low | 0.0002 | 0.9998 | Low |
| Production | Low | High | High | High | Low | High | High | High | High | 0.9983 | 0.0017 | High |
| Production | Low | Low | High | Low | High | High | High | High | High | 0.9874 | 0.0126 | High |
| Production | Low | High | High | High | High | High | High | High | High | 0.9999 | 0.0001 | High |
| Production | Low | Low | High | Low | Low | Low | Low | High | Low | 0.0775 | 0.9225 | Low |
| Production | Low | High | Low | High | Low | Low | Low | High | Low | 0.1452 | 0.8548 | Low |
| Production | Low | High | High | High | High | High | Low | High | High | 0.9992 | 0.0008 | High |
| Production | High | High | High | Low | High | Low | High | Low | High | 0.8497 | 0.1503 | High |
| Production | Low | High | High | Low | Low | Low | High | High | High | 0.8673 | 0.1327 | High |
| Production | Low | High | High | Low | High | Low | High | Low | High | 0.9188 | 0.0812 | High |
| Production | High | High | Low | High | Low | Low | High | Low | Low | 0.0682 | 0.9318 | Low |
| Production | High | High | Low | High | High | High | High | High | High | 0.9875 | 0.0125 | High |
| Production | Low | Low | High | Low | Low | Low | High | Low | Low | 0.0675 | 0.9325 | Low |
| QC | Low | High | High | High | High | High | High | High | High | 1.0000 | 0.0000 | High |
| QC | High | Low | High | High | High | High | High | Low | High | 0.9998 | 0.0002 | High |
| SR | High | Low | Low | Low | Low | Low | Low | Low | Low | 0.0001 | 0.9999 | Low |
| SR | Low | Low | Low | Low | Low | Low | Low | Low | Low | 0.0001 | 0.9999 | Low |
| SR | High | Low | Low | Low | High | Low | High | Low | Low | 0.0045 | 0.9955 | Low |
| SR | Low | High | High | High | High | High | High | High | High | 0.9997 | 0.0003 | High |
| SR | High | High | High | High | High | High | High | High | High | 0.9994 | 0.0006 | High |
Confusion Matrix Data
## Confusion Matrix and Statistics
##
## Reference
## Prediction High Low
## High 18 0
## Low 1 13
##
## Accuracy : 0.9688
## 95% CI : (0.8378, 0.9992)
## No Information Rate : 0.5938
## P-Value [Acc > NIR] : 1.303e-06
##
## Kappa : 0.936
##
## Mcnemar's Test P-Value : 1
##
## Sensitivity : 0.9474
## Specificity : 1.0000
## Pos Pred Value : 1.0000
## Neg Pred Value : 0.9286
## Prevalence : 0.5938
## Detection Rate : 0.5625
## Detection Prevalence : 0.5625
## Balanced Accuracy : 0.9737
##
## 'Positive' Class : High
## Findings
Using Naive Bayes, we can predict if an individual’s satisfaction level compared to the mean with 97% accuracy.
Concerns There are instances that a predictor category may be absent (eg. People from QC with low Satisfaction). This will limit this tools ability. To remedy this more data is needed.