International Journal of Eco-Innovation in Science and Engineering (IJEISE) Vol.
, 2025 .
https://ijeise.
id / E-ISSN: 2721-8775 Article Analysis of the Effect of Labor Quantity on the Output Value of Micro-Industries in Indonesia Using Simple Linear Regression Method Isna Nugraha 1.
Nida An Khofiyah2.
Gilang Ramadhan1.
c and Friska Aryanti1.
1 Department of Industrial Engineering.
Faculty of Engineering and Science.
Universitas Pembangunan Nasional Veteran Jawa Timur.
Surabaya 60294.
Indonesia 2 Department of Industrial Engineering.
Faculty of Engineering.
Universitas Pelita Bangsa.
Cikarang 17530.
Indonesia Email: a*isna.
ti@upnjatim.
id, bnida.
khofiyah@pelitabangsa.
c22032010004@student.
id, d22032010136@student.
*Corresponding author: .
ti@upnjatim.
|Telephone number: 6285293006434 Received: 08th May 2025.
Revised: 19th May 2025.
Accepted: 28th May 2025.
Available online: 30th May 2025.
Published regularly: May and November Abstract In the current era of globalization, rapid advancements are driving nations to compete in strengthening their economies.
Companies and industrial enterprises play a vital role as economic units actively contributing to national economic activities.
Economic growth is closely associated with the output value of industries, which is significantly influenced by the number of workers.
This study aims to examine the effect of the number of workers in micro-industries on the output value of micro-industries in Indonesia.
The research employs two variables: the independent variable (X), representing the number of micro industry workers, and the dependent variable (Y), representing the output value of micro-industries.
simple linear regression analysis was applied to measure the extent of the relationship between these The results show a regression equation of Y = 217.
512,365 46,669X with a coefficient of determination (RA) of 0,896, indicating that 89,6% of the variation in output value can be explained by the number of micro-industry workers.
This suggests a strong influence of labor quantity on microindustry output in Indonesia.
Keywords: Labour.
Micro-Industry.
Output Value.
Regression Introduction Micro.
Small, and Medium Enterprises (MSME.
are pivotal to Indonesia's economy, contributing approximately 61% to the national Gross Domestic Product (GDP) and employing about 97% of the total workforce .
Among these, micro-industries, characterized by having 1 to 4 employees, constitute the majority, accounting for 98.
7% of all business units in the country .
Their significant presence underscores their role in fostering inclusive economic growth and reducing unemployment rates .
Despite their substantial contribution, micro-industries often face challenges related to limited resources, access to capital, and scalability .
Understanding the factors influencing their output value is essential for formulating effective development strategies .
Labor quantity is a fundamental input in the production process, directly impacting the output levels of micro-industries .
Theoretically, an increase in labour should lead to higher production output.
however, empirical studies present mixed findings .
For instance, research on small-scale footwear industries in Mojokerto indicated that labour quantity significantly affects production output .
Conversely, a study in DOI:10.
International Journal of Eco-Innovation in Science and Engineering (IJEISE) Vol.
, 2025
Magetan found that the number of workers did not have a significant impact on output, suggesting that other factors may play a more dominant role .
These discrepancies highlight the need for further investigation into the labour output relationship within micro industries.
Simple linear regression analysis serves as an effective tool to examine the relationship between labour quantity and output value in micro industries .
This statistical method allows researchers to assess the strength and direction of the association between an independent variable .
abour quantit.
and a dependent variable .
utput valu.
Prior studies utilizing regression analysis have provided insights into various factors affecting micro-industries, such as capital investment, raw material availability, and technological adoption .
By applying this method, researchers can isolate the effect of labour quantity on output, controlling for other variables that may influence production levels .
This approach facilitates a clearer understanding of labourAos role in micro industrial In the context of Indonesia, where microindustries are dispersed across diverse regions with varying economic conditions, analysing the labour output relationship becomes even more Regional disparities in infrastructure, education, and access to markets can influence the efficiency and productivity of labour in microindustries .
Studies have shown that in areas with better infrastructure and access to resources, labour tends to be more productive, leading to higher output values .
Conversely, in regions lacking such facilities, the same quantity of labour may yield lower outputs, emphasizing the importance of contextual factors .
Therefore, a comprehensive analysis considering regional variations is crucial for accurate assessments.
Given these regional disparities, a nationwide analysis of labor quantity and its effect on output is necessary to capture the broader pattern across Indonesia's micro-industrial landscape.
Microindustries in Indonesia face persistent challenges in maximizing output due to resource limitations, particularly in labour and capital .
Prior research has emphasized that labour dynamics remain a key determinant of productivity, especially in labour-intensive sectors .
Therefore, a focused analysis of labour input is necessary to identify efficiency gaps and potential improvements in production systems .
This study aims to analyse the effect of labour quantity on the output value of micro-industries in Indonesia using the simple linear regression By focusing on this relationship, the research seeks to provide empirical evidence that can inform policymakers and stakeholders in developing targeted interventions to enhance micro-industrial productivity.
Understanding whether and how labour quantity influences output can aid in optimizing workforce allocation, training programs, and resource distribution.
Ultimately, the findings are expected to contribute to the broader discourse on micro-industrial development and economic planning in Indonesia .
Materials and methods This study was conducted to analyse the influence of the number of workers in microindustries on the output value of these industries in Indonesia.
The research covers a three-year period, specifically the years 2018, 2019, and 2020, and includes data from all provinces in Indonesia.
A total of 102 data points were collected from the official website of Statistics Indonesia (Badan Pusat Statisti.
at w.
These data represent aggregated provincial-level information on two key variables: the number of workers in micro-industries and the output value generated by these enterprises.
The use of official and recent government statistics enhances the validity and credibility of the findings.
Table 1.
Raw Data Labour Output Score Labour Output Score DOI:10.
International Journal of Eco-Innovation in Science and Engineering (IJEISE) Vol.
, 2025
Labour
Output
Score
Output
Score
69 159683 6534833
70 200851 9334141
71 155646 7495519
74 134620 5859708
76 166382 7389456
80 1042971 87451650
81 1459752 51961225
82 240628 6280897
83 1345443 48309789
84 182853 11193229
85 221793 9001272
86 143937 4607349
87 212530 3227113
94 178605 4301418
95 222034 9217201
Labour The research model is built around two main The dependent variable (Y) is the output value of micro-industries, defined as the total monetary value of goods and services produced by micro-industrial units, including industrial services from third parties and non-industrial revenues.
The independent variable (X) is the number of workers employed in micro-industries, which includes both paid and unpaid workers, measured as the average number of workers per day across the sampled years.
These variables were selected to test the hypothesis that the labour force size has a significant impact on production output in micro-scale industrial enterprises.
Data collection involved direct extraction and tabulation of numerical information from publicly available statistical records.
The dataset covers a wide range of micro-industries, from very small enterprises employing only a few workers to larger aggregations approaching the upper limit of the micro-industry classification.
Such variation ensures a comprehensive analysis across different industrial intensities and geographical regions.
The data were processed and analysed using SPSS (Statistical Package for the Social Science.
version SPSS was chosen for its robust statistical processing capabilities and its accessibility for both descriptive and inferential statistical analyses.
The analytical method employed in this study is simple linear regression, a statistical technique used to model the relationship between a single independent variable and a dependent variable.
Prior to regression analysis, data were tested for normality, linearity, and significance through Pearson correlation.
ANOVA, and model validity To explore the relationship between the number of workers and output value in microindustries, this study employed a quantitative This method was chosen to model the linear association between the number of workers .
ndependent variabl.
and the output value of micro-industries .
ependent variabl.
To ensure the validity of the model, supporting statistical tests were conducted prior to the regression A concise summary of the key components in the data analysis process is presented in Table 1.
Table 2.
Data Analysis Overview Component Detail Analysis Technique Simple Linear Regression Purpose To assess the relationship between labor and output Preliminary Tests Pearson Correlation.
Linearity Test.
ANOVA Regression Tool SPSS (Statistical Package for the Social Science.
Output Disagree Regression equation and significance test results Results and Discussion DOI:10.
International Journal of Eco-Innovation in Science and Engineering (IJEISE) Vol.
, 2025
In this research, data analysis involved several stages including correlation testing, linearity verification, model significance evaluation through ANOVA, and regression analysis using SPSS software.
The results are presented in a sequential manner, beginning with correlation testing, followed by linearity testing, regression analysis, and model interpretation through SPSS Pearson Product Moment Correlation Test The first step in the analysis involved testing the strength and direction of the relationship between the number of workers .
ndependent variabl.
and the output value of micro-industries .
ependent variabl.
The Pearson Product Moment Correlation coefficient was calculated to determine whether a statistically significant correlation exists between the two variables.
Table 3.
Pearson Correlation Result Number of Workers Output Value Pearson Correlation Sig.
-taile.
Pearson Correlation Sig.
-taile.
Number of Output Value ** Correlation is significant at the 0.
01 level .
-taile.
The analysis yielded a correlation coefficient (R) of 0,947 which indicates a very strong positive linear relationship.
Furthermore, the p-value was 0,000 which is significantly lower than the standard significance threshold of 0,05.
As a result, the null hypothesis (H.
, which posits that no correlation exists, is rejected in favour of the alternative hypothesis (H.
Therefore, it can be concluded that a strong and statistically significant correlation exists between the number of workers and the output value of micro-industries in Indonesia.
Linearity Test To ensure the appropriateness of applying linear regression, the next step involved verifying whether the data exhibit a linear relationship.
The Test of Linearity was conducted via SPSS to evaluate this assumption.
Table 4.
Linearity Test Result Sum of Mean square Sig.
New Output Value*New Number of Labor Employees Between Groups (Combine.
Linearity Deviation from Linearity Within Groups Total The analysis produced a significance value of 0,000 for the linearity component.
Since the significance value is less than 0,05.
the null hypothesis .
hat the data are not linea.
is rejected.
Consequently, it can be concluded that the relationship between the number of workers and output value is linear, which justifies the application of linear regression for further Simple Linear Regression Analysis Model Summary Table 5.
Model Summary Model Adjusted R Std.
Error of the Estimate R Square Change Change Statistics F Change Df1 Df2 Sig.
Change a Predicators: (Constan.
Total Empower Employment The Model Summary output provides the R and R Square values, which represent the strength of the modelAos explanatory power.
The analysis resulted in an R Square value of 0,896.
that 89,6% of the variance in the output value can be explained by the number of workers.
The remaining 10,4% may be attributed to other external factors not included in the model, such as capital investment, production technology, or managerial efficiency.
ANOVA (F-Tes.
Table 6.
ANOVA Test
Model
Sum of Squares Regression 710E 16
Residual 135E 15
Total
024E 16
Dependent Variable: Output Value Predictors .
Number of Workers Mean
Square 710E 16
135E 13
Sig.
To determine whether the overall regression model is statistically significant and suitable for prediction, an Analysis of Variance (ANOVA) test was performed.
ANOVA evaluates the proportion of the variance in the dependent variable that can be attributed to the independent The results show an F-statistic of 864,415 with a significance value .
of 0,000.
Since the pvalue is well below the commonly accepted alpha level of 0,05.
the null hypothesis that the regression model has no predictive power is This indicates that the number of DOI:10.
International Journal of Eco-Innovation in Science and Engineering (IJEISE) Vol.
, 2025
workers significantly explains the variation in output value across micro-industries in Indonesia.
Regression Coefficient Analysis Table 7.
Regression Coefficient Result Model Unstandardized Standardized Coefficients Coefficients Std.
Error Beta (Constan.
Number of employees Correlations Sig.
Zeroorder Collinearity Statistics Partial Part Tolerance VIF Dependent Variable: Output Value The strength and direction of the relationship between the independent and dependent variables are further elaborated through the regression The unstandardized coefficient .
of 46,669 indicates that for every additional unit of labour .
, worke.
, the output value increases by approximately IDR 46,669.
assuming all other factors are held constant.
The intercept of 217.
512,365 represents the estimated base output when no labour is employed, which may reflect baseline productivity or fixed output Both coefficients were found to be statistically significant with p-values of 0000.
suggesting that the model terms contribute meaningfully to explaining the variation in output.
This reinforces the conclusion that labour is a key determinant of output in IndonesiaAos microindustrial sector and that the formulated model:
Y = 217.
512,365 46,667X
Regression Coefficient Analysis To validate the assumptions of classical linear regression, particularly the normality of residuals, a Normal Probability Plot (P-P Plo.
of the standardized residuals was reviewed.
This plot assesses whether the residualsAithe differences between observed and predicted valuesAiare normally distributed.
The visual output illustrates that the data points align closely with the diagonal line, suggesting that residuals are symmetrically distributed and do not deviate markedly from Fig 1.
Regression Coefficient Result This outcome supports the assumption that the residuals of the regression model are normally distributed, satisfying a key requirement for the reliability of inferential statistics derived from the Therefore, the regression results can be interpreted with greater confidence in their validity and generalizability.
Analysis and Interpretation The findings of this study demonstrate a strong and statistically significant relationship between the number of workers in microindustries and their output value.
The correlation coefficient of 0,947 reflects a robust positive association, while the regression analysis shows that 89,6 percent of the variation in output can be explained by changes in the number of workers.
The resulting regression equation.
Y = 512,365 46,669X.
indicates that each additional worker contributes approximately IDR 46,669 to the output value.
These results are further supported by the ANOVA test, which confirms the overall model significance with a pvalue of 0,000.
The linearity of the data was validated through a Linearity Test, which showed a significance value of 0,000.
confirming the appropriateness of the linear regression approach.
In addition, the Normal Probability Plot confirmed that the residuals were normally distributed, satisfying one of the core assumptions of regression modelling.
The combination of these statistical indicators underscores the reliability and robustness of the analytical model used in this study.
From a policy and managerial perspective, the results offer valuable implications.
They suggest that expanding employment within micro- DOI:10.
International Journal of Eco-Innovation in Science and Engineering (IJEISE) Vol.
, 2025
industries could directly and substantially enhance This highlights the potential of micro-industrial sectors as engines of inclusive economic growth, particularly in areas with labour Supporting initiatives such as workforce training, business incentives, and employment subsidies could therefore play a critical role in strengthening the output capacity of micro-industries across Indonesia.
Conclusion .
Evidence from the regression analysis highlights the crucial role that labor plays in shaping the productivity of micro industries in Indonesia.
A strong positive correlation between the number of workers and output value, supported by an R Square of 0,896 and a significance level of 0,000, affirms that labor is not only a production input but a key economic lever in this sector.
This suggests that enhancing the scale and quality of the workforce could lead to performance, especially in labor surplus regions.
To capitalize on this potential, it is recommended that government agencies, local authorities, and industry stakeholders invest in workforce development through vocational training, business assistance programs, and targeted employment incentives.
Supporting micro industries with integrated labor and productivity strategies may also increase resilience, competitiveness, and sustainability.
Additionally, future studies are encouraged to incorporate other explanatory variables such as capital input, infrastructure, or market access to build a more comprehensive model of micro industrial growth.
Reference