The Use Of The Classification And Regression Tree (CART) Method For The Classification Of The Labor Force Participation Level In Medan In 2019

by ADMIN 143 views

The use of the Classification and Regression Tree (CART) method for the Classification of the Labor Force Participation Level in Medan in 2019

Introduction

Increasing the participation of the workforce is one of the most important indicators in measuring the economic growth of a region. In Medan, there are various factors that affect the level of labor force participation (TPAK), including gender, education level, and marital status. To understand more in these factors, this study uses the Classification and Regression Tree (CART) method with 2019 data. The CART method, which was developed in 1984 by Breiman, Friedman, Olshen, and Stone, is a classification method that builds a decision tree based on historical data. This method allows us to identify patterns and relationships between variables, so that it can help in understanding the factors that affect TPAK.

Background

The labor force participation rate (TPAK) is a crucial indicator of a region's economic growth. It measures the percentage of the population that is actively participating in the workforce. In Medan, the TPAK rate has been increasing over the years, but there are still many factors that affect it. These factors include gender, education level, and marital status. Understanding these factors is essential in formulating policies to increase the participation of the workforce in Medan.

Methodology

The CART method is a classification method that builds a decision tree based on historical data. It uses a recursive partitioning algorithm to identify patterns and relationships between variables. The method has been widely used in various fields, including economics, sociology, and medicine. In this study, the CART method was used to analyze the TPAK data in Medan in 2019.

Results

Based on the TPAK data analysis in the city of Medan in 2019, the CART method succeeded in identifying five groups with different characteristics:

1. Women with Moderate Education

This group is the largest group with a total of 861 people (33.58% of the total sample). These results indicate that women with secondary education levels tend to be more active in the workforce than other groups.

2. Women with Higher and Low Education

This group totaling 472 people (18.41%), shows that higher or lower education levels do not significantly affect women's participation in the workforce.

3. Married Men

This group totaling 740 people (28.86%), showing that married men tend to be more active in the workforce compared to other groups.

4. Men Not Married with Low Education

This group totaling 247 people (9.55%), indicating that men who are not married and have low education tend to be less active in the workforce.

Implications and Recommendations

The results of the CART analysis show that sex factors, education levels, and marriage status have an important role in determining the level of labor force participation in Medan. To increase the participation of the workforce, especially for women, efforts need to be made to increase access to education and better job opportunities. On the other hand, the government needs to pay special attention to men not married with low education so that they can get better job opportunities and improve their standard of living.

Conclusion

The CART method has succeeded in identifying patterns and relationships between variables that affect TPAK in the city of Medan. The results of this analysis provide important information for stakeholders in formulating the right policies to increase the participation of the workforce in Medan. The study highlights the importance of considering sex factors, education levels, and marriage status in formulating policies to increase the participation of the workforce in Medan.

Limitations

This study has several limitations. Firstly, the study only used data from 2019, which may not be representative of the current situation. Secondly, the study only considered three factors: sex, education level, and marriage status. Other factors, such as age and occupation, may also affect the level of labor force participation in Medan. Future studies should consider these limitations and expand the scope of the study.

Future Research Directions

Future studies should consider the following research directions:

  1. Longitudinal study: Conduct a longitudinal study to analyze the changes in the level of labor force participation in Medan over time.
  2. Multivariate analysis: Conduct a multivariate analysis to consider the effects of multiple factors on the level of labor force participation in Medan.
  3. Comparative study: Conduct a comparative study to compare the level of labor force participation in Medan with other cities in Indonesia.

References

  • Breiman, L., Friedman, J., Olshen, R. A., & Stone, C. J. (1984). Classification and regression trees. Wadsworth & Brooks/Cole Advanced Books & Software.
  • Medan City Government. (2019). Medan City in Figures 2019.
  • World Bank. (2019). World Development Indicators 2019.

Appendices

  • Appendix A: TPAK data in Medan in 2019
  • Appendix B: CART analysis results
  • Appendix C: Implications and recommendations for stakeholders
    Frequently Asked Questions (FAQs) about the Classification and Regression Tree (CART) Method for Labor Force Participation in Medan

Q: What is the Classification and Regression Tree (CART) method?

A: The CART method is a classification method that builds a decision tree based on historical data. It uses a recursive partitioning algorithm to identify patterns and relationships between variables.

Q: What is the purpose of using the CART method in this study?

A: The purpose of using the CART method in this study is to identify the factors that affect the level of labor force participation in Medan, and to understand the relationships between these factors.

Q: What are the key findings of the study?

A: The key findings of the study are that sex factors, education levels, and marriage status have an important role in determining the level of labor force participation in Medan. Women with secondary education levels tend to be more active in the workforce than other groups, while married men tend to be more active in the workforce compared to other groups.

Q: What are the implications of the study for policymakers?

A: The study highlights the importance of considering sex factors, education levels, and marriage status in formulating policies to increase the participation of the workforce in Medan. Policymakers should focus on increasing access to education and better job opportunities for women, and providing better job opportunities and improving the standard of living for men not married with low education.

Q: What are the limitations of the study?

A: The study has several limitations, including the use of data from 2019, which may not be representative of the current situation, and the consideration of only three factors: sex, education level, and marriage status. Other factors, such as age and occupation, may also affect the level of labor force participation in Medan.

Q: What are the future research directions?

A: Future studies should consider the following research directions:

  1. Longitudinal study: Conduct a longitudinal study to analyze the changes in the level of labor force participation in Medan over time.
  2. Multivariate analysis: Conduct a multivariate analysis to consider the effects of multiple factors on the level of labor force participation in Medan.
  3. Comparative study: Conduct a comparative study to compare the level of labor force participation in Medan with other cities in Indonesia.

Q: What are the practical applications of the study?

A: The study has practical applications in the field of labor economics and policy-making. The findings of the study can be used to inform policies and programs aimed at increasing the participation of the workforce in Medan, and to improve the standard of living for men not married with low education.

Q: What are the potential benefits of using the CART method in this study?

A: The potential benefits of using the CART method in this study include:

  1. Improved understanding of the factors that affect labor force participation: The CART method allows for the identification of complex relationships between variables, which can lead to a better understanding of the factors that affect labor force participation.
  2. Development of targeted policies: The CART method can be used to develop targeted policies that address the specific needs of different groups, such as women with secondary education levels or married men.
  3. Improved decision-making: The CART method can be used to inform decision-making in the field of labor economics and policy-making.

Q: What are the potential limitations of using the CART method in this study?

A: The potential limitations of using the CART method in this study include:

  1. Overfitting: The CART method can be prone to overfitting, which can lead to models that are too complex and do not generalize well to new data.
  2. Interpretability: The CART method can be difficult to interpret, especially for complex models.
  3. Data quality: The CART method requires high-quality data, which can be difficult to obtain in some cases.

Q: What are the future research directions for the CART method?

A: Future research directions for the CART method include:

  1. Development of new algorithms: New algorithms can be developed to improve the performance of the CART method.
  2. Application to new data sets: The CART method can be applied to new data sets to identify new patterns and relationships.
  3. Comparison with other methods: The CART method can be compared with other methods, such as random forests and support vector machines, to identify the strengths and weaknesses of each method.