Stochastic Forecasting of Regional Age-Specific Fertility Rates: An Outlook for German NUTS-3 Regions
Round 1
Reviewer 1 Report
Comments and Suggestions for Authorssee the attached file
Comments for author File: 
Comments.pdf
Author Response
Thank you for your time and suggestions. Please see the attachment for our reply.
Author Response File: Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThere are some issues that the authors should review before publishing the article.
Introduction
1. The introduction needs to clearly articulate the limitations of existing studies and detail how this research aims to fill these gaps.
2. It is recommended to particularly emphasize the importance of regional fertility rate forecasting for Germany or similar countries, as well as the contributions of this study in this field.
3. "Despite the variety of methods regarding approaches to fertility forecasting, the majority of forecasts of multiregional fertility are of rather simplistic nature (see for the recent practice in regional fertility forecasting)."
The author states that other forecasts are relatively simple, but does not specify why these methods are simple and their limitations. It is advised to add a specific evaluation of the existing forecasting methods in this section, and clearly indicate the differences and connections between this research and existing studies.
4. "First, regional country-wide forecasts for larger countries, such as Germany, exhibit a high dimensionality...... dimensionality."
The issue of "high dimensionality" is mentioned, but not clearly explained what it specifically refers to. Also, the "effective methods" referred to should be clearly defined.
5. "Third, common approaches......forecasts are preferable."
Regarding the statement that "common approaches are deterministic," please specify what these common methods are and explain what is meant by "deterministic" in this context. Additionally, a more in-depth discussion on why probabilistic forecasts are preferable to point forecasts is recommended.
Methods
1. Although the issue of collinearity is mentioned in the introduction, there is no collinearity check in the data processing part. It is suggested to conduct necessary collinearity checks to enhance the rigor of the research.
2. The author mentions the use of the Backtesting method for model selection, but there is no literature to explain why the Backtesting method is superior to other methods, which requires clarification.
3. It is recommended that the author thoroughly explains the reasons for using PCA and Monte Carlo simulation, and details the steps of data collection and processing, including any key data preprocessing and selection criteria.
4. The ARIMA model is mentioned in the abstract, but not in the methods section. The abstract should be consistent with the content of the full text.
Discussion
1. Suggestion: Conduct an in-depth discussion of the practical and theoretical significance of the research findings.
Author Response
Thank you for your time and suggestions. Please see the attachment for our reply.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for Authors Line 99, replace "Between World War II and 1990, Germany has been split into West and East Germany" with "Between World War II and 1990, Germany was split into West and East Germany". Line 148, replace "We used annual" with "We use annual". The authors have mentioned three models in Eq. (4), Eq. (5), and Eq. (6). Are these are newly proposed models? If they are newly proposed, then, provide a comparison of these models with other existing models. If they are not new, then provide their references. In line 158, the authors should mention the programming software that is used to carry out the analysis. How about checking the accuracy of the data set? For better understanding and more insight information, the summary plots of the data set should be presented. Furthermore, the summary values of the data set should also be provided. Line 212, replace 1 000 with "1000". For same correction, please check line 213. The defficiency of the novel forecast model should be clearly highlighted. Comments on the Quality of English LanguageModerate editing of English language required
Author Response
Thank you for your time and suggestions. Please see the attachment for our reply.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Comments and Suggestions for AuthorsThe paper considerably improved. The authors completely answered my questions in their paper. I suggest to publish in |Mathematics.
Reviewer 3 Report
Comments and Suggestions for AuthorsThe authors have incorporated my comments. The paper is now suitable for publication.
