Review Reports - Performance Analysis of the Main Coffee-Producing Regions in Brazil: A Methodological Triangulation Based on Principal Component Analysis and Data Envelopment Analysis

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

- The introduction provides a strong justification for the research focus. However, could the authors elaborate on why PCA and DEA specifically were chosen to assess sustainable performance, and how these methods are superior to other alternatives (e.g., regression, ANN, or fuzzy MCDM approaches) for this type of analysis?

- The study is based on Brazilian coffee production. Could the authors discuss the generalizability of the proposed method to other regions or agribusiness sectors?

- The criteria for selecting the first three principal components (PC1, PC2, PC3) are based on "explained variance." Could the authors include a scree plot or cumulative variance table to support this choice?

- Please compare this applied method with existing studies to emphasize that it is superior to other methods. In recent years, many different studies have been done on MCDM and Taguchi. Please mention these two studies in detail. The depth of your article will increase.

Sustainable Thermoplastic Material Selection for Hybrid Vehicle Battery Packs in the Automotive Industry: A Comparative Multi-Criteria Decision-Making Approach
https://doi.org/10.3390/polym16192768

Optimization of Micro-Drilling of Laminated Aluminum Composite Panel (Al–PE) Using Taguchi Orthogonal Array Design
https://doi.org/10.3390/ma16134528

- While the study outlines input and output variables well, can the authors explain how they validated or normalized these data across regions to ensure comparability, especially given differences in region size, farming system (manual vs. mechanized), and socio-economic context?

- In the discussion of efficiency, recommendations like reducing the number of female workers are mentioned. Can the authors contextualize this ethically and align it with gender equality principles and SDG goals, rather than presenting it as a simple numerical optimization?

- The study mentions performance indices, but how are these indices practically useful to decision-makers in agribusiness? Are they implementable on-farm, or are they more of an analytical tool for policymakers?

- In the conclusion, the authors suggest expanding to other agribusiness sectors. Could they propose a replication framework or share lessons learned that could help researchers apply this PCA–DEA hybrid method to other crops?

Author Response

Response to reviewers

Manuscript ID: Sustainability-3595323

“Performance analysis of the main coffee producing regions in Brazil: a methodological triangulation based on Principal Component Analysis (PCA) and Data Envelopment Analysis (DEA)”

Comments and Suggestions for Authors

Reviewer #1

Response: We appreciate the reviewer’s comment. PCA and DEA were chosen due to their suitability for analyzing multidimensional and empirical datasets with sustainability indicators across economic, environmental, and social domains. PCA was applied to reduce dimensionality and multicollinearity, allowing the creation of global performance indices with strong explanatory power (Johnson & Wichern, 2007; Granato et al., 2018). DEA, as a non-parametric method, does not require a predefined functional form and is more appropriate than regression models for efficiency analysis (Cooper et al., 2011). Unlike ANN models, DEA provides transparency and interpretability—important for guiding decision-making in agricultural settings (Ferreira et al., 2009). Fuzzy MCDM methods, though relevant in subjective contexts, are less suitable for objective, quantitative datasets. Thus, the PCA–DEA combination offers a robust, interpretable, and data-driven approach to assess sustainable performance.

- The study is based on Brazilian coffee production. Could the authors discuss the generalizability of the proposed method to other regions or agribusiness sectors?

Response: We thank the reviewer for this important observation. Although the empirical application of the study focuses on Brazilian coffee production, the methodological approach—based on PCA for dimensionality reduction and DEA for efficiency assessment—is generalizable to other agricultural contexts. Both methods are data-driven and adaptable to different crops, regions, and sustainability indicators, provided that relevant and consistent data are available (Cooper et al., 2011; Granato et al., 2018). Similar frameworks have been applied in livestock, forestry, and horticulture sectors (Peykani et al., 2019; Kohl et al., 2019). Therefore, this approach may support performance diagnostics and benchmarking in diverse agribusiness systems worldwide, especially those committed to sustainable development.

Response: We appreciate the reviewer’s suggestion. The selection of the first three principal components (PC1, PC2, and PC3) was based on their cumulative explained variance, which together accounted for the largest share of total variability in the dataset. To enhance transparency and reproducibility, we have now included a scree plot, as supplementary material. These visualizations clearly illustrate the inflection point and support the choice of retaining the first three components, in line with established practices in multivariate analysis.

Sustainable Thermoplastic Material Selection for Hybrid Vehicle Battery Packs in the Automotive Industry: A Comparative Multi-Criteria Decision-Making Approach
https://doi.org/10.3390/polym16192768

Optimization of Micro-Drilling of Laminated Aluminum Composite Panel (Al–PE) Using Taguchi Orthogonal Array Design
https://doi.org/10.3390/ma16134528

Response: We appreciate the reviewer’s suggestion to strengthen the methodological comparison. While several recent studies have applied MCDM and Taguchi methods for sustainability assessment and process optimization, our approach offers distinct advantages. For instance, the study by [45] used MCDM to evaluate thermoplastic materials for electric vehicle batteries, integrating multiple subjective weighting techniques. Similarly, [46] employed the Taguchi method for optimizing drilling parameters in composite panels. Unlike these methods, which rely on expert judgment or experimental designs, the PCA–DEA combination allows for objective, data-driven analysis and benchmarking without requiring prior weighting or distributional assumptions. This increases its transparency, replicability, and applicability across agribusiness systems.

Response: We thank the reviewer for this important question. To ensure comparability across regions with diverse socio-economic and operational characteristics, all input and output variables were normalized using min-max scaling prior to the DEA application. This standardization process ensures that variables measured on different scales (e.g., hectares, liters, currency) are transformed to a common range [0,1], preserving relative differences while eliminating scale bias. In addition, the PCA stage helped reduce dimensionality and mitigate potential collinearity among variables, increasing the robustness of the input-output structure. The regional differences in farming systems (manual vs. mechanized) were indirectly captured through variables such as labor composition, fuel consumption, and production capacity. These procedures are aligned with best practices in performance benchmarking literature [25,35].

Response: We appreciate the reviewer’s valuable comment. The recommendation regarding the reduction in the number of female workers was a technical result derived from the DEA output-oriented model, which identifies numerical targets for improving efficiency. However, we acknowledge that such interpretations must be ethically contextualized. We have revised the discussion to clarify that these results do not advocate for gender-based labor reduction. On the contrary, they highlight structural disparities in labor allocation across regions and farming systems. We emphasize the importance of promoting gender equality in agribusiness and align our reflections with SDG 5. The findings should thus be interpreted as an invitation to reevaluate labor practices and foster inclusive strategies that improve efficiency without compromising equity.

Although the efficiency results derived from the DEA model include recommendations such as reducing the number of female workers in certain production units, it is essential to interpret these outputs within a broader ethical and developmental context. Such numerical targets should not be viewed as prescriptive actions, but rather as indicators of structural inefficiencies that may reflect disparities in labor organization or resource allocation. The study does not support any reduction in women's participation in agricultural activities. Instead, it recognizes the importance of fostering inclusive and equitable labor strategies aligned with the United Nations Sustainable Development Goals, particularly SDG 5 (Gender Equality). Therefore, the interpretation of efficiency results must be guided by ethical principles, reinforcing the role of women in sustainable agribusiness and promoting strategies that improve performance while upholding social responsibility and equity.

Response: We thank the reviewer for this relevant question. The performance indices developed in this study serve both operational and strategic purposes. At the farm level, these indices help producers identify specific areas for improvement—such as optimizing water use, enhancing income generation, or increasing the use of organic fertilizers—enabling more informed resource allocation. Because the indices are based on objective variables and normalized data, they can be easily integrated into farm management practices and training programs. At the policy level, the indices allow for regional benchmarking and the identification of systemic inefficiencies, supporting targeted public interventions and incentive programs. Therefore, the indices are not merely analytical tools, but practical instruments for continuous performance improvement across scales.

Response: Based on the findings of this study, we propose a generalizable replication framework for applying the PCA–DEA hybrid method to other crops or agribusiness sectors. First, researchers should ensure access to a comprehensive dataset combining technical, economic, and sustainability-related variables. Second, PCA should be used to reduce dimensionality and identify the most relevant indicators, facilitating interpretability and avoiding multicollinearity. Third, DEA can then be applied using an output-oriented BCC model to measure pure technical efficiency, adapted to the scale of each production system. Lessons learned from this study highlight the importance of integrating both quantitative rigor and contextual knowledge—such as farming system type, regional constraints, and sustainability goals—to generate meaningful performance benchmarks. This framework supports the development of targeted strategies for continuous improvement across diverse agricultural contexts.

Author Response File: Author Response.docx

Reviewer 2 Report

Comments and Suggestions for Authors

Manuscript ID: Sustainability-3595323

“Performance analysis of the main coffee producing regions in Brazil: a methodological triangulation based on Principal Component Analysis (PCA) and Data Envelopment Analysis (DEA)”

General comments

In this work, the authors evaluated the performance of the main Arabica and Conilon coffee producing regions in Brazil in the 2018-2019 and 2020-2021 harvest years. For this, they used triangulation of the Principal Component Analysis and Data Envelopment Analysis techniques. And the study followed a qualitative-quantitative approach, descriptive character and inductive logic. The timeframe for this was 12 months to complete all methodological stages. Regarding efficiencies, 6 inefficient producers were identified for 2018-2019 (effectiveness is related to reductions in labor hiring and the creation of mechanisms to increase income on inefficient properties) and 9 for 2020-2021 The contributions of the study were related to the identification of inefficient producers and, above all, the variables that most impact the performance of these sampling units so that they can reestablish their efficiencies.

*The study on performance of the main Arabica and Conilon coffee producing regions in Brazil in the 2018-2019 and 2020-2021 harvest years , this work is focused in Brasilian producers. This study has correlation with other producer’s countries?

*In general the ingles could be improved. Particularly in some parte the texts use the word Table and in another Board. Please only use Table

* The title refers to “methodological triangulation based on Principal Component Analysis (PCA) and Data Envelopment Analysis (DEA)” but the author not shows the graphical. Please include this graphic because it is the basis of this study.

* Several abbreviations are used along of the text. Please describe the abbreviation only the first time that it is used. Then use the abbreviation along the text. Not include abbreviation in key words and title.

*Please check the format of the legends. Most legends should be improved by adding more description. Equations must be numbered.

*Table 2 please replace socioeconomic by Socioeconomic

*Fig 3 and 4 are a low quality. The author should be improving these figures, the date is too small. Please include the letters to each figure. The authors use letters for these figures in the text but their not included in the figures. Also add a description of each figure in the legend

*Pag 10, line 376. PC|1, eliminate the line

Overall, the text is too long and heavy. It's difficult to follow the idea of the work.

Comments on the Quality of English Language

In general ingles could be improved. Particularly in some parte the texts use the word "Table" and in another "Board". Please only use Table

Author Response

Response to reviewer 2

Manuscript ID: Sustainability-3595323

“Performance analysis of the main coffee producing regions in Brazil: a methodological triangulation based on Principal Component Analysis (PCA) and Data Envelopment Analysis (DEA)”

Comments and Suggestions for Authors

Reviewer #2

General comments

Response: Thank you for the comment. The authors have made this adjustment (lines 724-727): This study is relevant to major players in the global coffee industry. Price fluctuations or changes in international demand can impact both Brazil and other coffee-producing countries. Additionally, droughts and pests are global challenges faced by the sector. Finally, pressures for sustainable practices affect all producers.

*In general the ingles could be improved. Particularly in some parte the texts use the word Table and in another Board. Please only use Table.

Response: Thank you for the comment. The authors have made this adjustment.

Response: Thank you for the comment. The authors have added the figure to the text (Figure 3).

Response: Thank you for the comment. The authors have removed abbreviations from the title and keywords. A caption for inputs and outputs was created in Table 2 to aid reader's understanding.

*Please check the format of the legends. Most legends should be improved by adding more description. Equations must be numbered.

Response: Thank you for the comment. The authors have made these adjustments. The captions for all tables and figures have been improved. We have numbered the equations.

*Table 2 please replace socioeconomic by Socioeconomic

Response: Thank you for the comment. The authors have made this adjustment.

*Pag 10, line 376. PC|1, eliminate the line.

Response: Thank you for the comment. The authors have made this adjustment.

Overall, the text is too long and heavy. It's difficult to follow the idea of the work. In general ingles could be improved. Particularly in some parte the texts use the word "Table" and in another "Board". Please only use Table.

Response: Thank you for the comment. The authors have made this adjustment.

Reviewer #3

The paper provides an analysis of some coffee producing areas. First, i think that the authors should explain more how the areas have been selected and how the producers have been selected. In the title it is written that "main coffee producing regions", but more information should be provided.

Response: Thank you for the comment. The authors have made this adjustment. We detailed the sampling process in the Methods section: The selection criterion adopted for producers was the choice of individuals who demonstrated the greatest commitment to the Campo Futuro project through their participation in project meetings. Campo Futuro is a project carried out by the Brazilian Confederation of Agriculture and Livestock (CNA) and the National Rural Learning Service (SENAR). The project, aimed at rural producers, is implemented in partnership with the following universities and research centers: Cepea Esalq/USP; CIM/UFLA; Labor Rural/UFV; and Pecege.

In terms of methods and data collection, more information should be given. The dataset is quite small, as well as the selected time period.

Response: We thank the reviewer for this observation. We acknowledge that the dataset is limited in size and scope, as it covers 33 producers across two harvest periods (2018–2019 and 2020–2021). This constraint reflects the availability of reliable, field-level data, which was obtained through structured surveys under the CIM/UFLA “Campo Futuro” project. Despite the sample size, the study complies with DEA guidelines recommending a minimum ratio of three DMUs per variable (Cooper et al., 2011), and the use of PCA ensured dimensionality reduction and robustness of results. We have now added a statement clarifying these aspects in the Materials and Methods section and highlighted the dataset limitation explicitly as an avenue for future research expansion in the Conclusions.

Furthermore, the results seems to be very specific and hard to extrapolate to other situations. Thus, from my point of view the paper better fits a conference than a journal.

Response: We appreciate the reviewer’s opinion and respectfully acknowledge the concern regarding the generalizability of the findings. While the results are indeed context-specific, the main contribution of this study lies in the methodological framework that combines PCA and DEA to assess sustainability performance—an approach that is both replicable and adaptable to other crops, regions, and agribusiness systems. As suggested in the revised Conclusions, we provide a replication framework and lessons learned to facilitate broader application. Furthermore, the methodological triangulation and indicator construction respond to ongoing academic discussions on performance benchmarking in sustainable agriculture, aligning with the journal’s scope. We believe this contribution goes beyond a case study, offering conceptual and analytical value suitable for a peer-reviewed journal.

Furthermore, more attention should be given to the manner in which the information has been presented, as highlighted in the following:

Please note that some sections are missing or the numbering of the sections is not appropriate. For example, after section 2, sub-section 2.1, the next section, is the sub-section 3.1.

Response: Thank you for the comment. The authors have made this adjustment.

Please use another editor for adding the equations as they look like figures rather than text.

Response: Thank you for the comment. The authors have made this adjustment.

Text in rows 277-297 seems to have a different formatting.

Response: Thank you for the comment. The authors have made this adjustment.

I think that the explications related to the methodology and the equations used for various methods should be presented in section 3. In this form, the text is messy and it is hard to follow the information. please try to better structure the information.

Please add references where needed - e.g. in rows 428-429 there is no reference to the text "Efficiency analysis from the perspective of Banker and Chang’s super-efficiency model".

Response: Thank you for the comment. The authors have made this adjustment.

Limitations should be added.

Response: Thank you for the comment. The authors have made this adjustment. We have added more limitations related to the study: This study has several limitations that should be acknowledged. First, the dataset is limited to 33 coffee producers from selected regions in Brazil and covers only two harvest periods (2018–2019 and 2020–2021), which may restrict the generalizability of the findings. Second, the use of cross-sectional data does not capture dynamic changes in efficiency or sustainability performance over time. Third, the analysis depends on self-reported and survey-based data, which may be subject to recall bias or variability in measurement accuracy. Fourth, while the PCA–DEA hybrid method allows for objective benchmarking, it is sensitive to variable selection and may not fully capture contextual qualitative factors (e.g., institutional support, farmer knowledge, or market access). Lastly, the exclusive use of the BCC output-oriented model may overlook potential insights obtainable from alternative DEA formulations or other frontier-based models. These limitations suggest avenues for future research, including longitudinal analysis, the inclusion of additional variables and regions, and the adoption of alternative efficiency models.

Please use the citation style imposed by the journal - e.g. "According to [13]" here the names of the authors should have been added before [13].

Response: Thank you for the comment. Done.

Please create your own figures - fig 2 cannot be taken from a source.

Response: Thank you for the comment. Done.

Reviewer #4

This article requires revision before publication.

This study evaluated the performance of 22 major coffee producing regions in the 2018-2019 and 2020-2021 harvest years through triangular analysis of PCA and DEA. This year is 2025. What causes the lag in research data and results?

Response: We appreciate the reviewer’s observation. The time gap between data collection and publication reflects the rigorous process involved in data validation, index construction, and methodological triangulation using PCA and DEA. The dataset was sourced from the CIM/UFLA “Campo Futuro” project, which releases micro-level agricultural data with some delay due to quality control protocols and access permissions. Additionally, the multidimensional structure of the data required extensive preprocessing and robustness testing to ensure the reliability of results. Although the dataset covers past harvest years, the methodological insights and performance benchmarks remain highly relevant for evaluating sustainability strategies in similar agribusiness contexts today. This limitation has now been acknowledged in the revised manuscript.

The introduction to the DEA method in Section 3.1 suggests citing more recent high-quality studies. For example: A modified slacks-based measure of efficiency in data envelopment analysis (2020); Evaluation and prediction of water-energy-carbon nexus efficiency in China based on a new multiregional input-output perspective (2023); Evaluating environmental performance using data envelopment analysis: The case of European countries (2020)…

Response: We thank the reviewer for this valuable recommendation. In response, we have enriched Section 3.1 by incorporating recent high-quality studies that expand the theoretical and applied understanding of Data Envelopment Analysis. These include Fukuyama and Weber (2020), who propose a modified slacks-based efficiency measure; Ren et al. (2023), who assess the water-energy-carbon nexus in China using DEA; and Lozano et al. (2020), who evaluate environmental efficiency in Europe through DEA models. These additions help to contextualize our methodological approach within the latest scholarly developments and reinforce the robustness and adaptability of DEA in sustainability research. All references have been properly cited and added to the updated reference list.

This study conducted a semi-structured questionnaire survey on 33 coffee producers. How were these 33 coffee producers selected? What was the questionnaire like? When did it start? Was it a phased survey or a supplementary survey? This information is not fully explained in the article.

Response: Data Envelopment Analysis (DEA) is a widely used non-parametric method for evaluating the relative efficiency of decision-making units (DMUs) when multiple inputs and outputs are involved. In recent years, several high-quality studies have expanded its applications and methodological formulations. For instance, [47] proposed a modified slacks-based measure (SBM) that improves discrimination among efficient units and addresses input–output slacks more precisely in production systems. [48] employed DEA combined with a multiregional input-output model to evaluate and predict the efficiency of the water–energy–carbon nexus across Chinese regions, demonstrating its applicability to complex sustainability scenarios. Similarly, [49] applied DEA to compare environmental efficiency across European countries, highlighting the method’s capacity to benchmark sustainability performance at a national level. These advances support the methodological robustness and practical relevance of DEA in sustainability assessments, validating its use in this study to analyze the performance of coffee-producing regions in Brazil.

BBC is a very traditional DEA method. This study chose to use BBC instead of other new DEA methods. What is the reason? What are the unique advantages of BCC?

Response: We thank the reviewer for this important observation. The BCC model was selected due to its suitability for assessing technical efficiency under variable returns to scale (VRS), which reflects the heterogeneity in production scales among the sampled coffee producers. Unlike newer DEA variants that often require larger datasets or additional parameter calibration, BCC provides a robust and interpretable efficiency frontier while distinguishing between pure technical and scale inefficiencies. This is particularly important in agribusiness contexts where input-output relationships may vary significantly across farms. Additionally, the output-oriented BCC model aligns with the study’s goal of maximizing desirable outcomes (e.g., income, sustainable practices) rather than minimizing inputs. Despite the emergence of advanced models, the BCC approach remains a widely accepted and validated method for small to medium-sized datasets in performance benchmarking.

The description of the limitations of the study is too brief and should be supplemented.

Response: This study has several limitations that should be acknowledged. First, the dataset is limited to 33 coffee producers from selected regions in Brazil and covers only two harvest periods (2018–2019 and 2020–2021), which may restrict the generalizability of the findings. Second, the use of cross-sectional data does not capture dynamic changes in efficiency or sustainability performance over time. Third, the analysis depends on self-reported and survey-based data, which may be subject to recall bias or variability in measurement accuracy. Fourth, while the PCA–DEA hybrid method allows for objective benchmarking, it is sensitive to variable selection and may not fully capture contextual qualitative factors (e.g., institutional support, farmer knowledge, or market access). Lastly, the exclusive use of the BCC output-oriented model may overlook potential insights obtainable from alternative DEA formulations or other frontier-based models. These limitations suggest avenues for future research, including longitudinal analysis, the inclusion of additional variables and regions, and the adoption of alternative efficiency models.

6. References for the past three years (2023-2025) are lacking. Additional references are recommended.

Response: Thank you for the comment. The authors have made this adjustment

Author Response File: Author Response.doc

Reviewer 3 Report

Comments and Suggestions for Authors

In terms of methods and data collection, more information should be given. The dataset is quite small, as well as the selected time period.

Furthermore, the results seems to be very specific and hard to extrapolate to other situations. Thus, from my point of view the paper better fits a conference than a journal.

Furthermore, more attention should be given to the manner in which the information has been presented, as highlighted in the following:

Please note that some sections are missing or the numbering of the sections is not appropriate. For example, after section 2, sub-section 2.1, the next section, is the sub-section 3.1.

Please use another editor for adding the equations as they look like figures rather than text.

Text in rows 277-297 seems to have a different formatting.

Please add references where needed - e.g. in rows 428-429 there is no reference to the text "Efficiency analysis from the perspective of Banker and Chang’s super-efficiency model".

Limitations should be added.

Please use the citation style imposed by the journal - e.g. "According to [13]" here the names of the authors should have been added before [13].

Please create your own figures - fig 2 cannot be taken from a source.

Author Response

Response to reviewer 3

Manuscript ID: Sustainability-3595323

“Performance analysis of the main coffee producing regions in Brazil: a methodological triangulation based on Principal Component Analysis (PCA) and Data Envelopment Analysis (DEA)”

Comments and Suggestions for Author

Reviewer #3

In terms of methods and data collection, more information should be given. The dataset is quite small, as well as the selected time period.

Furthermore, the results seems to be very specific and hard to extrapolate to other situations. Thus, from my point of view the paper better fits a conference than a journal.

Furthermore, more attention should be given to the manner in which the information has been presented, as highlighted in the following:

Please note that some sections are missing or the numbering of the sections is not appropriate. For example, after section 2, sub-section 2.1, the next section, is the sub-section 3.1.

Response: Thank you for the comment. The authors have made this adjustment.

Please use another editor for adding the equations as they look like figures rather than text.

Response: Thank you for the comment. The authors have made this adjustment.

Text in rows 277-297 seems to have a different formatting.

Response: Thank you for the comment. The authors have made this adjustment.

Please add references where needed - e.g. in rows 428-429 there is no reference to the text "Efficiency analysis from the perspective of Banker and Chang’s super-efficiency model".

Response: Thank you for the comment. The authors have made this adjustment.

Limitations should be added.

Please use the citation style imposed by the journal - e.g. "According to [13]" here the names of the authors should have been added before [13].

Response: Thank you for the comment. Done.

Please create your own figures - fig 2 cannot be taken from a source.

Response: Thank you for the comment. Done.

Author Response File: Author Response.doc

Reviewer 4 Report

Comments and Suggestions for Authors

This article requires revision before publication.

1. This study evaluated the performance of 22 major coffee producing regions in the 2018-2019 and 2020-2021 harvest years through triangular analysis of PCA and DEA. This year is 2025. What causes the lag in research data and results?

2. The introduction to the DEA method in Section 3.1 suggests citing more recent high-quality studies. For example: A modified slacks-based measure of efficiency in data envelopment analysis (2020); Evaluation and prediction of water-energy-carbon nexus efficiency in China based on a new multiregional input-output perspective (2023); Evaluating environmental performance using data envelopment analysis: The case of European countries (2020)…

3. This study conducted a semi-structured questionnaire survey on 33 coffee producers. How were these 33 coffee producers selected? What was the questionnaire like? When did it start? Was it a phased survey or a supplementary survey? This information is not fully explained in the article.

4. BBC is a very traditional DEA method. This study chose to use BBC instead of other new DEA methods. What is the reason? What are the unique advantages of BCC?

5. The description of the limitations of the study is too brief and should be supplemented.

6. References for the past three years (2023-2025) are lacking. Additional references are recommended.

Author Response

Response to reviewer 4

Manuscript ID: Sustainability-3595323

“Performance analysis of the main coffee producing regions in Brazil: a methodological triangulation based on Principal Component Analysis (PCA) and Data Envelopment Analysis (DEA)”

Comments and Suggestions for Author

Reviewer #4

This article requires revision before publication.

This study evaluated the performance of 22 major coffee producing regions in the 2018-2019 and 2020-2021 harvest years through triangular analysis of PCA and DEA. This year is 2025. What causes the lag in research data and results?

The introduction to the DEA method in Section 3.1 suggests citing more recent high-quality studies. For example: A modified slacks-based measure of efficiency in data envelopment analysis (2020); Evaluation and prediction of water-energy-carbon nexus efficiency in China based on a new multiregional input-output perspective (2023); Evaluating environmental performance using data envelopment analysis: The case of European countries (2020)…

This study conducted a semi-structured questionnaire survey on 33 coffee producers. How were these 33 coffee producers selected? What was the questionnaire like? When did it start? Was it a phased survey or a supplementary survey? This information is not fully explained in the article.

BBC is a very traditional DEA method. This study chose to use BBC instead of other new DEA methods. What is the reason? What are the unique advantages of BCC?

The description of the limitations of the study is too brief and should be supplemented.

6. References for the past three years (2023-2025) are lacking. Additional references are recommended.

Response: Thank you for the comment. The authors have made this adjustment

Author Response File: Author Response.doc

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

Response: Thank you for the comment. The authors have added the figure to the text (Figure 3).

Response: Is figure 4? I considered interesting that introduced the score plot showing the date dispersion of sample (not show data)

Response: Thank you for the comment. The authors have removed abbreviations from the title and keywords. A caption for inputs and outputs was created in Table 2 to aid reader's understanding.

Response: This is not true, e.g. PCA and DEA. Please cheque all cases

Abstract: This study aimed to evaluate the performance of the main Arabica and Conilon coffee producing regions in Brazil in the 2018-2019 and 2020-2021 harvest years, through the triangula-tion of the Principal Component Analysis (PCA) and Data Envelopment Analysis (DEA)

4. Results
4.1 Selection and classification of variables into inputs and outputs to evaluate the perfor-mance of the main coffee-producing regions in Brazil
Based on Principal Component Analysis (PCA), the variables were selected for the harvest

So, Data Envelopment Analysis (DEA) is a widely used non-parametric method for evalu-ating the relative efficiency of decision-making units (DMUs) when multiple inputs and outputs are involved.

Response: Thank you for the comment. The authors have made this adjustment.

Response: These figures were simply enlarged. This isn't the purpose of correction; they're too large this way. They take up a lot of space and create an ugly perspective, making comparison difficult. The idea was to somehow reduce the data on the axes so that the data would gain more importance.

Author Response

Response: Thank you for the comment. The authors have added the figure to the text (Figure 3).

Response: Is figure 4? I considered interesting that introduced the score plot showing the date dispersion of sample (not show data)

Response: Thank you for your valuable comment. We appreciate your observation regarding the graphical representation of the methodological triangulation. In response, we have included the figure that visually synthesizes the methodology adopted in the study. This has been added as Figure 3, titled “Performance analysis framework of Arabica and Conilon coffee-producing regions in Brazil (2018–2019 and 2020–2021 harvest seasons)”. The figure clearly illustrates the two-stage methodological sequence involving PCA for dimensionality reduction and variable selection, followed by DEA for efficiency assessment.

Additionally, we agree with your suggestion regarding the graphical exploration of PCA results. To enhance clarity, we retained Figure 4, which presents the scree plot showing the explained variance ratio by principal components for both harvest years. This visualization supports the selection of the main components and justifies the dimensional reduction process. The individual data points from the sample are not shown to preserve confidentiality, but the figure conveys the dispersion of variance, contributing to the interpretability of the PCA step.

Response: Thank you for the comment. The authors have removed abbreviations from the title and keywords. A caption for inputs and outputs was created in Table 2 to aid reader's understanding.

Response: This is not true, e.g. PCA and DEA. Please cheque all cases

Response: Thanks for the comment. The authors excluded these abbreviations in the text.

Results
4.1 Selection and classification of variables into inputs and outputs to evaluate the performance of the main coffee-producing regions in Brazil based on Principal Component Analysis (PCA).

The variables were selected for the harvest so, Data Envelopment Analysis (DEA) is a widely used non-parametric method for evalu-ating the relative efficiency of decision-making units (DMUs) when multiple inputs and outputs are involved.

Response: Thank you for your observation. We acknowledge that the original sentence in Section 4.1 was unclear due to the incorrect connection between two distinct methodological concepts. To improve the clarity and coherence of the section, we have revised the paragraph to clearly separate the description of the PCA-based variable selection process from the general explanation of DEA.

The revised section now first explains the selection and classification of variables into inputs and outputs using Principal Component Analysis (PCA), and then introduces DEA as a subsequent methodological step. This adjustment ensures that the methodological flow—PCA followed by DEA—is correctly conveyed, and the transition between the techniques is logically structured. The updated text can be found in Section 4.1 of the manuscript.

4.1 Selection and Classification of Variables into Inputs and Outputs to Evaluate the Performance of the Main Coffee-Producing Regions in Brazil Based on Principal Component Analysis (PCA)

The selection of variables was performed for the 2018–2019 and 2020–2021 harvest seasons using Principal Component Analysis (PCA). This technique allowed the identification of the most representative variables with strong correlations to the principal components (PC1, PC2, and PC3), facilitating the construction of global performance indices for each dimension analyzed (Demographic, Socioeconomic, Agricultural, Certification, and Circular Economy). The selected variables were then classified as either inputs or outputs, respecting the methodological requirements for the subsequent application of Data Envelopment Analysis (DEA).

4.2 Application of Data Envelopment Analysis (DEA) for Efficiency Assessment

Data Envelopment Analysis (DEA) is a widely used non-parametric method for evaluating the relative efficiency of decision-making units (DMUs) when multiple inputs and outputs are involved. In this study, an output-oriented BCC model was applied to measure pure technical efficiency among coffee producers. The model's flexibility enables the separation of scale efficiency from technical efficiency, which is particularly relevant in heterogeneous production systems such as those found in Brazil’s coffee-producing regions.

Response: Thank you for the comment. The authors have made this adjustment.

Response: We apologize for the poor quality of the figures. We have made this adjustment to the figures.

Author Response File: Author Response.docx

Reviewer 3 Report

Comments and Suggestions for Authors

I thank the authors for the revised version of their paper.

I have to mention that it has been hard to see the changes made into the paper as they have not been marked in any manner - e.g. red text, highlighted text, track changes, etc.

Even though the authors have provided answers to the previously mentioned comments, I think that some of them are vague presented and not fully fundamented - e.g. the selection of the coffee main coffee production regions - I would have expected to see some data that support the selection of the regions, or connection with other studies that have conducted similar analyses on the same areas.

The quality of the figures is poor, and should be further enhanced.

The paper remains - in terms of contribution - highly connected to the presented case study.

Comparison with other studies from the field should be provided. I suggest to the authors to use tables and provide a point-by-point comparison with other approaches from the field to justify the reliability of the proposed approach.

Author Response

I thank the authors for the revised version of their paper.

I have to mention that it has been hard to see the changes made into the paper as they have not been marked in any manner - e.g. red text, highlighted text, track changes, etc.

Response: We appreciate your valuable comments and the opportunity to improve our manuscript. We have made the requested changes to better inform the selection of coffee-producing regions, incorporating empirical data and connections with previous studies (lines 279-289).

The quality of the figures is poor, and should be further enhanced.

Response: We apologize for the poor quality of the figures. We have made this adjustment to the figures.

The paper remains - in terms of contribution - highly connected to the presented case study.

Response: Thank you for your insightful comment. We acknowledge that the contributions of the paper are closely tied to the specific case study of coffee-producing regions in Brazil. However, we would like to emphasize that the methodological approach adopted—based on the triangulation of Principal Component Analysis (PCA) and Data Envelopment Analysis (DEA)—is generalizable and applicable to other agribusiness sectors and geographic contexts. To reinforce this broader applicability, we have revised the manuscript to highlight, in both the Methods and Conclusions sections, how the proposed framework can be adapted to evaluate performance in different agricultural systems, provided relevant and structured data are available. These additions aim to enhance the general contribution of the study beyond the initial case study.

Response: Table 1 was created to attend to this suggestion in topic “Materials and Methods”:

To strengthen the discussion of our methodological framework and its reliability, Table 1 presents a comparative overview of recent studies that have applied similar or alternative methods for performance evaluation in agribusiness and sustainability. This comparison highlights the methodological structure, scalability, and core contributions of each approach, reinforcing the advantages of the proposed PCA–DEA hybrid method.

Study	Sector/Case	Methodological Approach	Dimensionality Reduction	Efficiency Analysis	Scalability/Generalizability	Key Contribution
This study	Coffee-producing regions in Brazil	PCA + DEA (BCC, output-oriented)	PCA (to reduce multicollinearity and select variables)	DEA (to assess pure technical efficiency)	High – applicable to other crops and sustainability indicators	Introduces a replicable PCA–DEA framework for sustainability benchmarking
Duan et al. [2]	Agriculture Decision Support Systems	MCDM (AHP-TOPSIS)	Not applied	MCDM ranking	Moderate – dependent on expert judgment	Multicriteria ranking of agri-tech systems
Jiménez-Ortega et al. [4]	Organic coffee farms (Mexico)	Participatory Sustainability Assessment	Not applied	Not applied	Limited – qualitative and context-specific	Emphasizes participatory stakeholder engagement
Riaño-Calderón [3]	Differentiated coffee chain	Custom sustainability-profitability model	Not applied	Not applied	Moderate – adapted to coffee value chain	Models trade-off between sustainability and profitability
La Scalia et al. [1]	Circular economy in agroindustry	Life Cycle Assessment (LCA)	Not applied	Not applied	Low – LCA is process/product-specific	Evaluates circularity and environmental impact

Table 1 - Comparative overview of recent studies on performance assessment methodologies in agribusiness and sustainability contexts.

Author Response File: Author Response.docx