Predicting Co-Movement of Banking Stocks Using Orthogonal GARCH
Round 1
Reviewer 1 Report
The author(s) aim to investigate whether application of OGARCH in predicting comovement of Indonesian banking sector stocks. The author(s) conclude that the OGARCH approach is appropriate and has advantages over previous methods.
- The entire paper needs to be thoroughly proof-read, to rid it off some of the remaining grammar and typo and spelling errors. e.g., see line 181 - 'a' should be removed. 'Scree' used instead of 'Screen' within Figure 2.
- On page 2, line 72, what does 'right degree of co-movement' mean?
- Line 80, the meaning of the 1st sentence is very unclear. Similar comment goes for line 100 (1st line on page 3).
- In line 84, there is a mention of 'dominant players in...'. The author(s) will need to include some statistics to justify/substantiate/back that statement.
- The data requires further description. A brief on each will be good. Further, it will be good to have a Descriptive Statistics table showing basic order statistics e.g. mean, standard deviation, kurtosis, number of observations, etc.
- The application of the OGARCH appears to have been well executed.
- More detail should be reported for the robustness checks. In particular, for the impulse response function (IRF) analysis, the author(s) state that they use the Cholesky one s.d. shock, but they do not provide the 'ordering' they employ, which should then come with the reasons for the particular ordering. This is important, because that can have important implications for the outcomes.
- There should be more in depth discussion on the outcomes of the IRF analysis. Why do BBNI, BBRI, and BMRI behave similarly? More importantly, what are the characteristics or attributes of the BBTN stock that makes it behave differently?
- Aside of suggesting on composition of investors' portfolios, the author(s) do not go further to discuss any policy relevance. This is an important omission, otherwise it is simply a number crunching exercise.
- The author(s) should discuss how specifically this study adds to knowledge, and relate their findings to already existing articles which address a similar issue for ASEAN countries i.e. at a country/regional level. Given the interlinkages among countries in the ASEAN region and even globally, the narrow focus on these 4 stocks is a rather myopic view of the real world. The author(s) have to provide the reader with better reasoning to motivate this narrow and pin-point analysis.
Author Response
Dear Editor,
We are pleased to resubmit for possible publication, the revised version of risks-1774598: “Predicting Co-Movement of Banking Stocks using Orthogonal GARCH”. We would also like to thank the reviewers for the insightful and helpful comments on the manuscript. We have addressed reviewer comments as outlined below:
Reviewer 1
1. |
COMMENT: “The entire paper needs to be thoroughly proof-read, to rid it off some of the remaining grammar and typo and spelling errors. RESPONSE: We are thankful for the comments given and we have done grammarly proofread due to the limited time provided. However we are willing to use the English editing service provided by the journal should the paper is accepted. In figure 2, we have changed the screen by scree. |
|||||||||||||||||||||||||||||||||||
2. |
COMMENT: “On page 2, line 72, what does 'right degree of co-movement' mean?” RESPONSE: We have added the explanation as follows: “The results indicated that the OGARCH produced the right degree of co-movement compared to other methods. It means OGARCH is able to produce a positive definite covariance to overcome the estimation problems using other GARCH model.” |
|||||||||||||||||||||||||||||||||||
3. |
COMMENT: “Line 80, the meaning of the 1st sentence is very unclear. Similar comment goes for line 100 (1st line on page 3).” RESPONSE: We have revised the sentence as below: Line 80: By implementing the OGARCH method, this research is expected to produce a more straightforward approach to predicting the SOE stocks' co-movement in Indonesia's banking sector, since the capital market players is not yet familiar with this method. Instead, they use the heuristic methods such as correlation coefficient in constructing stock portfolios. Line 100: This research also provides a novelty in predicting the co-movement of SOE stocks in the banking sector in Indonesia since most researchers still use heuristic measures such as multivariate GARCH which posses some estimation problems. |
|||||||||||||||||||||||||||||||||||
4. |
COMMENT: In line 84, there is a mention of 'dominant players in...'. The author(s) will need to include some statistics to justify/substantiate/back that statement. RESPONSE: We agree with the reviewer suggestions to back the statement. The revision is as follows: “The objects studied are the state-owned banks because they are the dominant players in the Indonesian banking Industry. According to the industry profile report December 2019, during the 2018-2019 period, banking SOE account for 43 to 44% market share in terms of total assets compared to all banking industry players in Indonesia. “ |
|||||||||||||||||||||||||||||||||||
5. |
COMMENT: it will be good to have a Descriptive Statistics table showing basic order statistics e.g. mean, standard deviation, kurtosis, number of observations, etc RESPONSE: We agree with the reviewer suggestions to provide descriptive statistics as follows: Table 1 presents the statistic descriptive of all SOE banking stocks in this study: BBNI, BBRI, BBTN and BMRI.
Table 1. Descriptive statistics.
Source: Bloomberg, processed.
In Table 1, BBRI shows the highest average daily stock return (0.0877%) compared to other banking stock. This might relate to its strong fundamental conditions as indicated by BBRI being the most SOE banking stocks hold by foreign investors. BBRI has the widest outreach with its coverage scattered all over Indonesia. It focuses on SMEs lending compared to other SOE banking stocks. In contrast, BBTN has the lowest average daily return (0.0499%) over the research period. It also has the highest deviation (2.35%) compared to other SOE banking stocks. Focusing on mortgage loans differentiate BBTN substantially from other SOE banks. The focus strategy might contribute to its low return and high daily stock fluctuation.
|
|||||||||||||||||||||||||||||||||||
6 |
COMMENT: There should be more indepth discussion on the outcomes of the IRF analysis. Why do BBNI, BBRI, and BMRI behave similarly? More importantly, what are the characteristics or attributes of the BBTN stock that makes it behave differently? RESPONSE: We have added the arguments as follows: BBTN focused on mortgage loans which is evidence from its loan type composition where mortgage loans dominates other loans. Thus, the pricing of loans and its return is mainly affected by the property market and economic cycle. When focused mainly on mortgage loans, it becomes concentrated and no longer diversified. Pricing and return are lower than other diversified banks but it is backed by a definite collateral, provided that the property market is in a stable condition (does not collapse).
|
|||||||||||||||||||||||||||||||||||
7 |
COMMENT: Aside of suggesting on composition of investors' portfolios, the author(s) do not go further to discuss any policy relevance. This is an important omission, otherwise it is simply a number crunching exercise We have provided a further discussion as follows: The policy implication of this research is related to the importance of addressing the specific characteristics of each government- owned bank under consideration when aiming to form a bank holding company. It is advisable to place banks with similar characteristics in terms of co movement into one holding company instead of placing banks with different co movement into one holding company. |
|||||||||||||||||||||||||||||||||||
8 |
COMMENT: The author(s) should discuss how specifically this study adds to knowledge. We have provided a further discussion as follows: The theoretical implication of this research is providing empirical evidence from Indonesian banking sector in the ability of OGARCH in remedying the inherent estimation problems found in multivariate ARCH modelling. |
|||||||||||||||||||||||||||||||||||
9 |
COMMENT: The author(s) should relate their findings to already existing articles which address a similar issue for ASEAN countries i.e. at a country/regional level. We have provided a further discussion as follows: In the context of ASEAN countries, this research contribute to the knowledge related to portfolio construction involving government-owned banking stocks since there is a similarity of banking industry structure in some ASEAN countries where a few government-owned banks dominate the banking industry |
Author Response File: Author Response.docx
Reviewer 2 Report
The authors use O-Garch to examine state-owned bank stock prices from four banks in the Indonesian market. The data used are from 2013 to 2019. The authors attempted to expalin in the introduction the reason why OGARCH is advantageous, it is because the shares are in the same sector, so the use of Principal Component analysis could explain , by using 1 or 2 PCs, a lot of price variation, to be used in GARCH analysis.
They use PCs that have Eigenvalue that is above 1, and on total these PCs explain 85% of variation, which is the right method.
However, IRFs show that responses to shocks in two of the cases starts 6 and 7 months up to 9 months after the event, something that does not make sense and indicates poor aplication of data and method.
Indeed, the authors use monthly data, while share price are available on a daily basis. It is unlikely that any information can systematically affect prices after 8 or 9 months.
The problem with authors work is exactly this.
While they provide an interesting discussion about the OGARCH method and its usefulness, they make use of data in a way that is wrong. They should use daily data, because daily data reflect quickly and effectively information about the market.
Therefore I must say that sadly I have to reject this work, and propose to the authors, to rewrite their empirical part by using daily data and resubmit it, because simply monthly data analysis does not provide ANY information usefulness for the study they want to make. I will happily examine their study if they submit it by using daily data.
Author Response
Dear Editor,
We are pleased to resubmit for possible publication, the revised version of risks-1774598: “Predicting Co-Movement of Banking Stocks using Orthogonal GARCH”. We would also like to thank the reviewers for the insightful and helpful comments on the manuscript. We have addressed reviewer comments as outlined below:
REVIEWER 2
|
COMMENT: They should use daily data, because daily data reflect quickly and effectively information about the market. RESPONSE: We are thankful for the comments given and we have done daily data for all of our analysis
|
Author Response File: Author Response.docx
Round 2
Reviewer 2 Report
The authors now used daily data as suggested in the previous review.
I am happy to accept the study now for publication.