India's Total Natural Resource Rents (NRR) and GDP: An Augmented Autoregressive Distributed Lag (ARDL) bound test

Taneja, Sanjay; Bhatnagar, Mukul; Kumar, Pawan; Rupeika-Apoga, Ramona Article India's Total Natural Resource Rents (NRR) and GDP: An Augmented Autoregressive Distributed Lag (ARDL) bound test Journal of Risk and Financial Management Provided in Cooperation with: MDPI – Multidisciplinary Digital Publishing Institute, Basel Suggested Citation: Taneja, Sanjay; Bhatnagar, Mukul; Kumar, Pawan; Rupeika-Apoga, Ramona (2023) : India's Total Natural Resource Rents (NRR) and GDP: An Augmented Autoregressive Distributed Lag (ARDL) bound test, Journal of Risk and Financial Management, ISSN 1911-8074, MDPI, Basel, Vol. 16, Iss. 2, pp. 1-14, https://doi.org/10.3390/jrfm16020091 This Version is available at: https://hdl.handle.net/10419/275159 Standard-Nutzungsbedingungen: Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden. Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen. Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in EconStor may be saved and copied for your personal and scholarly purposes. You are not to copy documents for public or commercial purposes, to exhibit the documents publicly, to make them publicly available on the internet, or to distribute or otherwise use the documents in public. If the documents have been made available under an Open Content Licence (especially Creative Commons Licences), you may exercise further usage rights as specified in the indicated licence. https://creativecommons.org/licenses/by/4.0/ Citation: Taneja, Sanjay, Mukul Bhatnagar, Pawan Kumar, and Ramona Rupeika-Apoga. 2023. India’s Total Natural Resource Rents (NRR) and GDP: An Augmented Autoregressive Distributed Lag (ARDL) Bound Test. Journal of Risk and Financial Management 16: 91. https://doi.org/10.3390/jrfm16020091 Academic Editors: Tiiu Paas and Hakan Eratalay Received: 8 December 2022 Revised: 23 January 2023 Accepted: 31 January 2023 Published: 3 February 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). Journal of Risk and Financial Management Article India’s Total Natural Resource Rents (NRR) and GDP: An Augmented Autoregressive Distributed Lag (ARDL) Bound Test Sanjay Taneja 1, Mukul Bhatnagar 1, Pawan Kumar 1and Ramona Rupeika-Apoga 2,* 1University School of Business, Chandigarh University, Mohali 140413, India 2Faculty of Business, Management and Economics, University of Latvia, LV-1586 Riga, Latvia *Correspondence: ramona.r[email protected] Abstract: Utilizing natural resources wisely, reducing pollution, and taking other environmental factors into account are now critical to the prospects for long-term economic growth and, by extension, sustainable development. We investigate the impact of total natural resource rents (NRR) on India’s GDP in this study. The data sample consists of NRR and GDP data from the World Bank’s official website collected between 1993 and 2020. In the study, the Granger causality test and an augmented autoregressive distributed lag (ARDL) bound test were used. The NNR have a significant impact on India’s GDP, according to the results of the ARDL model on the framed time series data set. Furthermore, the ARDL bound test reveals that the NRR have a significant short-term and long-term impact on the GDP of the Indian economy. This research contributes to understanding whether an exclusive policy is required for effective management of the complex interactions between various forces in the economic, political, and social environments. This is significant because there is no standard policy in India to improve the efficiency of utility extraction from natural resources. Keywords: total natural resource rents; GDP; sustainable development; ARDL bound test; India 1. Introduction Countries endowed with natural resources should fare better and develop faster than countries devoid of valuable natural capital. However, this is not always the case, as some countries with abundant natural resources experience higher levels of poverty, inequality, and civil unrest than others (Ampofo et al. 2020). Existing empirical studies show that natural resource abundance has a negative effect on economic growth, a phenomenon known in most countries as the resource curse (Sachs and Warner 1995). According to Auty and Furlonge (2019), abundant natural resources have not been the panacea for igniting or sustaining economic growth and development in many countries. The purely economic view of the natural resource curse is based on explaining why resource-rich countries grow more slowly than resource-poor countries (Frankel 2010;Sachs and Warner 1997). The economic value derived from natural resources such as land, minerals, and water is referred to as resource rent. The difference between the market price of the resource and the cost of production can be used to calculate resource rent (OECD 2022). The economic value of resource rent is not accounted for in the calculation of a country’s GDP. While resource rent helps a country’s economy grow, it does not directly contribute to GDP. For example, if a country extracts oil from its land, the revenue from selling the oil increases the country’s GDP, but the value of the oil itself does not. Resource rent, on the other hand, is the difference between the market price of oil and the cost of extracting it (OECD 2022). In recent years, after the introduction of the Sustainable Development Goals (SDG) in 2015, several governments have prioritized environmental challenges such as air pollution, poor sanitation, and significant damage to natural resource rents (OECD 2011) and forest reserves (Pereira-Romeiro et al. 2021). Governments are also focusing on green finance J. Risk Financial Manag. 2023,16, 91. https://doi.org/10.3390/jrfm16020091 https://www.mdpi.com/journal/jrfm J. Risk Financial Manag. 2023,16, 91 2 of 14 to solve environmental issues (Bhatnagar et al. 2022b). Human health and economic well-being are jeopardized by poor environmental conditions (Tallis et al. 2008). These aspects, including well-being, environmental and physical capital, and approaches to water, food, and land, are all susceptible to climate change (Ibarrarán et al. 2009). These environmental concerns have generated a global movement to combat climate change (Han and Ahn 2020). Nonetheless, the majority of the Belt and Road Initiative countries must struggle to update their manufacturing progress (Tekdal 2018), resulting in significant fossil fuel energy consumption in the production division (York 2012), which contributes to global warming. Carbon (CO2) emissions have historically been employed as a proxy for environmental quality in the present ecological sustainability literature (Alola and Kirikkaleli 2019). However, numerous researchers have questioned this measure, claiming that CO2 emissions only account for a small percentage of the whole environment and do not adequately capture environmental contamination (Han et al. 2019). GDP has been the focus of all policymakers because it represents the welfare of the nation. Furthermore, many researchers have contributed to the discovery of the factors responsible for driving economic growth (Hegwood and Papell 2007;Auty and Furlonge 2019;Fleissig and Strauss 1999;Zaidi and Rupeika-Apoga 2021). The aim of this study is to investigate the impact of total natural resource rents (NRR) on India’s GDP. We analyzed NRR and GDP data from the World Bank’s official website collected between 1993 and 2020 to achieve the study’s aim. To identify causality between NRR and GDP, we used the Granger causality test. The augmented autoregressive distributed lag (ARDL) bound test was used to estimate the effect of NRR on GDP. We discovered that NRR has a significant short-term and long-term impact on the Indian economy’s GDP. This study helps to determine whether an exclusive policy is necessary for the effective management of the complex interactions between various forces in the economic, political, and social environments. This study makes a contribution by emphasizing the need for India to develop standard policies to improve utility extraction efficiency from natural resources. The article is organized as follows: Section 2includes a review of the literature, which we used to develop the hypotheses, and Section 3discusses the research methodology used. The research findings are presented in Section 4. The scientific and practical implications of the study’s findings are discussed in Section 5. Section 6summarizes the results and makes recommendations for additional study. 2. Literature Review and Hypotheses Development Natural resource rents are calculated as the difference between an item’s value and the average cost of producing it (Hamilton and Clemens 1999). This is accomplished by calculating the value of units of specific supplies and subtracting valuations of typical unit expenses for extraction or harvesting costs (Hung 1993). The rents on all of these modules are then multiplied by the amount of material extracted or harvested by nations to obtain the rents on each item as a percentage of GDP (Hamilton and Ruta 2006). Records for the influence of natural resources on financial production is vital in establishing an systematic outline for sustainable progress (Shi and Gill 2005). Profits from natural assets, particularly minerals and fossil fuels, account for a significant portion of GDP in some countries, and the majority of these revenues are in the form of monetary rents—income above the cost of extracting the resources (Mehar et al. 2018). As natural resources are not created, they generate economic rents (Mehar et al. 2018). For created services and commodities, competitive forces increase supply until revenues are pushed to zero, whereas natural assets that have a predetermined supply typically command revenues far in excess of their production costs (Arrow and Debreu 1954). Rents from nonrenewable resources such as fossil fuels and minerals, as well as rents from overharvesting of the jungle, demonstrate a “liquidation of a country’s capital stock” (Mehar et al. 2018). When governments use such rents to fund current expenditure rather than new wealth J. Risk Financial Manag. 2023,16, 91 3 of 14 expenditure to replenish what has been depleted, they borrow from their future prospects (Schumpeter and Keynes 1936). According to a review of the literature, natural resource rent has had a significant impact on major economic indicators (Dramani et al. 2022;Ben-Salha et al. 2021;Frankel 2010;Ampofo et al. 2020). Many studies of the variables, i.e., natural resources and economic indicators (Bhatnagar and Pathak 2021;Özen and Taneja 2022), are conducted around the world (Clootens and Kirat 2017;Hegwood and Papell 2007;Ibrahim 2017; Fleissig and Strauss 1999;Sachs and Warner 1995;Stijns 2005), but significantly less research has been conducted in India (Ampofo et al. 2020). This paper attempts to fill a gap in the assessment of the trend analysis of natural resource rent and the measurement of its impact on India’s economic growth. Revenue collected through taxation systems or schemes is a significant economic source for a country’s project development and the achievement of its macroeconomic goals. As a result, natural resources are important in both established and emerging economies. Rent-based resources are crucial in determining economic well-being (Mpofu 2021). The consequences of financial globalization on environmental dilapidation (CO2 emissions) were examined for the G7 nations from 1996 to 2017. The empirical evidence indicates that economic globalization, financial growth, and the exploitation of natural assets contribute to the rise in carbon emissions. For the long-term and short-term findings of the empirical research, this work employs innovative econometric methodologies such as CS-ARDL (Wang et al. 2020). This study aimed to determine if NRR may amplify the positive relationship between industrial growth and human capital with a sample of 14 Sub- Saharan African nations, covering the period of 1995 to 2015. The empirical data specify that NRR has a negative and statistically negligible effect on industrial improvement. It was also disclosed that the industrial sector has yet to reap significant benefits despite the enormous rents generated by natural resources (Bolarinwa et al. 2019). Decentralization of fiscal policy and rent from natural resources affect CO2 emissions. The article of Tufail et al. (2021) accomplishes this purpose by analyzing panel data from seven highly decentralized members of the OECD nations from 1990 to 2018. At the 1st difference, all variables are shown to be stationary. Long-run results indicate that devolution and natural capital rents help the environment reduce CO2 emissions (Tufail et al. 2021). Given China’s severe environmental degradation, the current study establishes the different factors’ dependency trends, emphasizing the intersection of eco-revolution and biological impact throughout many quantiles of the distributions, which has not been investigated previously in the research. As experimental evidence demonstrates, growing private-sector debt and ecological benefits contribute to environmental deterioration (Afshan and Yaqoob 2022). Total resource rents (coal rentals, mineral rents, natural gas rental costs, and forest rents) have been evaluated in a worldwide sample of 90 countries. Economic expansion, FDI inflows, investment, government expenditures, and demographic considerations were used as control variables. The global sample consisted of 90 economies. Natural rents are influenced by economic complexity, but only in low- and lower-middle income economies and high-income economies, and not in upper-middle income economies, according to the findings (Canh et al. 2020). Development in underdeveloped nations is directly linked to the amount of natural resource rents they obtain from their natural resources. Research on the consequences of natural resource rents shows that this connection varies by area, income level, degree of development, and export structure. When CO2 emissions are added as an interaction variable for Africa, natural resource rents have a detrimental influence on inclusive personal expansion (Nchofoung et al. 2021). It is crucial for ecological progress to focus on both sustainable production and consumption (Rupeika-Apoga and Petrovska 2022). Panel data analysis yielded robust findings by combining different econometric methodologies. Granger causality arises between two variables, particularly financing and natural resource rents. The second place indicates J. Risk Financial Manag. 2023,16, 91 4 of 14 that a deepening of the financial markets has a favorable impact on natural resource rents (Nguyen and Nguyen 2020). Researchers have long been interested in what happens when natural resources are abundant and how this affects economic development, both theoretically and empirically. However, opinions differ on whether a resource surplus helps or hinders economic growth. The studies found no discernible pattern despite using a variety of samples, data sources, and approaches. Torvik (2002) develops a novel and relatively simple mechanism to explain how an abundance of natural resources may be detrimental to people’s well-being. Gyamfi et al. (2022) agree with the assertion that the majority of profits from natural resource rents go toward increasing production, which has a negative impact on the environment and a country’s economic development. A country’s stable monetary system supports economic growth, which in turn supports the growth of other industries (Rupeika-Apoga et al. 2022). The empirical findings have important policy implications, particularly for the need to promote globalization and human capital development in order to ensure the appropriate management of natural resource rent, which is critical for financial sector growth (Guan et al. 2020). While most empirical results of the resource effect include how the development path is decided through the channel of institutions, the question of why resource rents frequently fail to inspire more robust governance is more important than ever for the nation’s economic development (Fagbemi and Adeoye 2020). The relationship between NRR and GDP is complicated and is affected by a number of factors, including the type of resource, the country’s economic policies, and its ability to diversify its economy (Dramani et al. 2022;Ben-Salha et al. 2021;Ibrahim 2017). The Granger causality test is frequently used to investigate the relationship between NRR and GDP, as this statistical hypothesis test determines whether NRR is useful in forecasting GDP. The Granger causality test had an insignificant impact in Australia, Brazil, Canada, China, Saudi Arabia, the United States, and Venezuela (Ampofo et al. 2020). Long-run Granger causality tests conducted by Mohamed (2020) revealed a unidirectional causal relationship running from resource rents to GDP growth, as well as development expenditure to GDP growth. The Toda–Yamamoto test method also revealed a unidirectional causality connecting oil resource rent to Ghana’s economic growth (Adabor et al. 2022). Considering this, we proposed the following hypotheses: H1a. Total natural resource rents (NRR) do not Granger-cause GDP in India. H1b. GDP does not Granger-cause total natural resource rents (NRR) in India. Natural resource rents, according to one study (Mehar et al. 2018), have a significant impact on a country’s GDP and overall economic activity. Natural resources, according to Stijns (2005), are not significant determinants of economic growth due to the coexistence of positive and negative channels of effect running from natural resources to factors affecting economic growth. According to Ben-Salha et al. (2021), there has been a massive body of research on the impact of natural capital on GDP development over the last several decades. The research has focused on developed and emerging countries, particularly those with abundant natural resources (Rudra and Jensen 2011). In empirical studies of the natural resources–economic growth nexus, two primary indicators, resource dependency and resource abundance, have been considered (Xu et al. 2022). The former describes a scenario in which a country’s earnings are primarily derived from the extraction and sale of natural resources, whereas the latter describes a scenario in which such resources are abundant (Mehlum et al. 2006). The yearly per capita rent of resource output captures the abundance of resources. Natural resource rents over GDP, the percentage of total natural resource exports in GDP, and the share of natural resources in total exports, on the other hand, are indicators of resource dependency (Yilanci et al. 2021). According to the study by Topcu et al. (2020), the majority of natural resource rent earnings are invested in expanding production, which has a negative impact on the environment and slows a country’s economic growth. A country’s stable monetary system promotes economic J. Risk Financial Manag. 2023,16, 91 5 of 14 development, which in turn encourages the expansion of other businesses (Friedman 2017). Natural resource rent management is critical to financial sector expansion, and Ncube et al.’s (2014) empirical findings have important policy implications on this front. Even though most empirical data on resource impact conclude that the development path is chosen through institutions (Khan et al. 2020), it is more important than ever for a country’s economic growth to address why resource rents frequently fail to inspire more strong governance (Collier 2005;Kaur et al. 2021). Therefore, we hypothesize: H2. Total natural resources rents (NRR) have no significant impact on India’s GDP. 3. Materials and Methods For meeting the research objective on the basis of the research gap drawn from the conducted literature review, data of total natural resources rents and India’s GDP was obtained from the official website of World Bank and time series data is exhibited in Figure 1 (World Bank 2022). J. Risk Financial Manag. 2023, 16, x FOR PEER REVIEW 5 of 15 sale of natural resources, whereas the latter describes a scenario in which such resources are abundant (Mehlum et al. 2006). The yearly per capita rent of resource output captures the abundance of resources. Natural resource rents over GDP, the percentage of total natural resource exports in GDP, and the share of natural resources in total exports, on the other hand, are indicators of resource dependency (Yilanci et al. 2021). According to the study by Topcu et al. (2020), the majority of natural resource rent earnings are invested in expanding production, which has a negative impact on the environment and slows a country’s economic growth. A country’s stable monetary system promotes economic development, which in turn encourages the expansion of other businesses (Friedman 2017). Natural resource rent management is critical to financial sector expansion, and Ncube et al.’s (2014) empirical findings have important policy implications on this front. Even though most empirical data on resource impact conclude that the development path is chosen through institutions (Khan et al. 2020), it is more important than ever for a country’s economic growth to address why resource rents frequently fail to inspire more strong governance (Collier 2005; Kaur et al. 2021). Therefore, we hypothesize: H2. Total natural resources rents (NRR) have no significant impact on India’s GDP. 3. Materials and Methods For meeting the research objective on the basis of the research gap drawn from the conducted literature review, data of total natural resources rents and India’s GDP was obtained from the official website of World Bank and time series data is exhibited in Figure 1 (World Bank 2022). Figure 1. Time series data of total natural resource rents and India’s GDP from 1993 to 2020. Source: (World Bank (2022)). Due to a lack of the literature on causality between GDP and NRR in the Indian economy, the Granger causality test was used to distinguish which variable was acting as a dependent and which variable was acting as an independent. The autoregressive distributed lag (ARDL) model was used to examine the short- and long-run effects of NRR on India’s GDP. The ARDL model was helpful for forecasting and for separating short-run dynamics from long-run relationships. When lag weights fell to zero relatively quickly, the regressor was not highly autocorrelated, and the sample was long in comparison to the length of the lag distribution. The model was best suited to estimating dynamic relationships (Bhatnagar et al. 2022a). Data collection from 1993 to 2020 was completed in order to run the analysis. The following regression equation served as the research’s foundation: -6 -4 -2 0 2 4 6 8 10 12 14 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 Total natural resources rents (% of GDP) GDP growth (annual %) Figure 1. Time series data of total natural resource rents and India’s GDP from 1993 to 2020. Source: (World Bank 2022). Due to a lack of the literature on causality between GDP and NRR in the Indian economy, the Granger causality test was used to distinguish which variable was acting as a dependent and which variable was acting as an independent. The autoregressive distributed lag (ARDL) model was used to examine the short- and long-run effects of NRR on India’s GDP. The ARDL model was helpful for forecasting and for separating short-run dynamics from long-run relationships. When lag weights fell to zero relatively quickly, the regressor was not highly autocorrelated, and the sample was long in comparison to the length of the lag distribution. The model was best suited to estimating dynamic relationships (Bhatnagar et al. 2022a). Data collection from 1993 to 2020 was completed in order to run the analysis. The following regression equation served as the research’s foundation: yt=c0+ p ∑ k=1 βkyt−k+ l ∑ j=0 αj+1xt−j+ut(1) where, yt= India’s GDP of Current Year, yt−k= India’s GDP of Previous Year, xt−j= Total natural resources rents of Previous Year, ut= Error Terms. J. Risk Financial Manag. 2023,16, 91 6 of 14 The above equation will serve as the foundation for short-term assessment using the ARDL bound test and long-run analysis using F-bound. Before the application of final model of ARDL, in the initial analysis, unit root test was applied by employing the following equation: ∆yt=α+βt+γyt−1+δ1∆yt−1+· · · +δp−1∆yt−p+1+εt(2) Once unit root test projected results at level and first difference of regressor and regressand, granger causality test was levied in following way: Yt= n ∑ i=1 αiYt−i+ n ∑ j=1 βjXt−j+u1t(3) Xt= n ∑ i=1 λiYt−i+ n ∑ j=1 σjXt−j+u2t(4) By the application of these mathematical models an attempt to meet the research objectives has been made in upcoming sections of research. 4. Results Table 1displays descriptive statistics. Table 1. Descriptive Statistics. Particulars Total Natural Resources Rents (% of GDP) GDP Growth (Annual %) Mean 2.937767584 5.993638435 Standard Error 0.236934487 0.58438374 Median 2.44921419 6.727153743 Standard Deviation 1.253739457 3.092268092 Sample Variance 1.571862625 9.56212195 Kurtosis 3.308835486 12.4088011 Skewness 1.702171742 −3.071150803 Range 5.37124876 16.09751034 Minimum 1.729645283 −7.251754782 Maximum 7.100894043 8.845755561 Sum 82.25749234 167.8218762 Count 28 28 Largest (1) 7.100894043 8.845755561 Smallest (1) 1.729645283 −7.251754782 Confidence Level (95.0%) 0.48614941 1.199056391 Table 2shows the unit root test for the dependent variable in the study. Table 2applies unit root test on GDP and NRR by using following equation: ∆yt=α+βt+γyt−1+δ1∆yt−1+· · · +δp−1∆yt−p+1+εt(5) After performing the unit root test on India’s GDP, the likelihood is greater than 0.05, which is marginally related to data stationary. Furthermore, the Dickey–Fuller test t-statistic is less than two, implying that we cannot rule out the possibility that GDP does not have a unit root. The unit root measurement has a lag length of zero, which is automatically determined from SIC with a maximum lag of six. Table 2shows the statistics for using the unit root test with the least squares method on the dependent variable, GDP. These calculations were performed at a level that yielded a log-likelihood of − 67.75. The values in Table 2show that the series is not stationary at the level of India’s GDP. Table 2also includes the augmented Dickey–Fuller test statistics for the first difference with a leg length of zero and a maximum lag of six. It demonstrates critical test values at 1%, 5%, and 10% J. Risk Financial Manag. 2023,16, 91 7 of 14 significance levels. The probability value is 0.0058, which is less than 0.05, and this is why the results are statistically significant. The supporting calculations regarding the augmented Dickey–Fuller test provide insight into the further analysis of whether the series chosen can be considered to have concluded. Log-likelihood and the augmented Dickey–Fuller test were used to validate the unit root test statistics calculations. The negative log-likelihood value ( − 66.46) is a good sign, and the F statistic (15.55) indicates a favorable Dickey–Fuller test result. The p-value of the unit root test, on the other hand, is 0.0006, which is less than 0.05. Based on this value, the series of India’s GDP can be interpreted as stationary at first difference. Table 2. Unit root tests. At Level GDP Growth (Annual %) Total Natural Resources Rents (% of GDP) With Constant t-Statistic −1.471 −7.0906 Prob. 0.5327 0 *** With Constant and Trend t-Statistic −1.3441 −7.0344 Prob. 0.8543 0 *** At First Difference GDP growth (annual %) Total natural resources rents (% of GDP) With Constant t-Statistic −3.9438 −2.2933 Prob. 0.0058 *** 0.1811 With Constant and Trend t-Statistic −4.1889 −2.2241 Prob. 0.0144 ** 0.4583 Notes: (**) significant at the 5%; (***) significant at the 1%; and (no) not significant, lag length based on SIC, probability based on MacKinnon (1996) one-sided p-values. The calculations regarding the augmented Dickey–Fuller to verify the presence of the unit root in the series of NRR are constructed in Table 2. The calculation is initiated by assuming that NRR have a unit root test. The calculations were performed with a leg length of zero and a max lag of six. The probability value was less than 0.05, and the critical test values of the independent variable were tested at three levels of significance: 1%, 5%, and 10%. Based on the values given in Table 2, the sum of the square of residuals (25.39), the log-likelihood ( − 36.58) and the value of F statistics (50.28) indicate a good sign for the time-series data collected as an independent variable. Moreover, the p-value shown in Table 2for the NRR is almost zero, less than 0.05. This value of probability results in the rejection of the null hypothesis for the NRR, which shows the series is stationary at a level. As a result, as an interpretation, the independent variable of the research is stationary at the level and the dependent variable is stationary at the first difference. Therefore, the ARDL model is an optimal model to measure the impact of an independent variable on a dependent variable. Table 3displays the Granger causality test results. The purpose of this test was to determine which variables are dependent and which are independent. The test revealed that unidirectional causality exists from NRR to GDP. Table 3. Pairwise Granger causality. Hypotheses Observations F-Value Prob. NRR does not Granger-Cause GDP 27 9.59353 0.0049 GDP does not Granger-Cause NRR 0.73753 0.3989 It means that NRR have an effect on GDP. As a result, the upcoming analysis will assess the long and short run effects of NNR on India’s GDP. J. Risk Financial Manag. 2023,16, 91 8 of 14 Table 4includes statistical values for the F-bound test, which assumes no levels of relationships as the null hypothesis. In Table 4, the value of the F statistic is analogized with a lower and upper bound at a 10%, 5%, 2.5%, and 1% level of significance for testing the significance of the continuation of a relationship between the regressor and controlled variable. On the test application, the F value is 8.629. This is greater than all of the upper bound values, which are 3.8, 4.6, 5.39, and 6.44 at 10%, 5%, 2.5%, and 1%, respectively. Hence, based on these calculations, it can be deduced that there is cointegration between the variables chosen for research. Table 4. F-Bound Test (Null Hypothesis: No levels relationship). Test Statistic Value Signif. I(0) I(1) Asymptotic: n = 1000 F-statistic 8.629709 10% 3.8 3.8 k1 5% 4.6 4.6 2.5% 5.39 5.39 1% 6.44 6.44 Actual Sample Size 27 Finite Sample: n = 35 10% 3.98 3.98 5% 4.945 4.945 1% 7.35 7.35 Finite Sample: n = 30 10% 4.025 4.025 5% 5.07 5.07 1% 7.595 7.595 The application of the autoregressive distributed lag model on India’s GDP as a dependent variable and NRR as an independent variable shows specific statistics exhibited in Table 5. The test includes a total of 27 observations, which are taken into account after adjustments. Four lags are selected automatically, and the model selection criteria are conducted based on the Akaike info criterion (AIC). The t statistics and probability values show that the model is a good fit, with t-values greater than 2 and p-values less than 0.05. Table 5. ARDL Bound Test (Short Run). Variable Coefficient Std. Error t-Statistic Prob. NRR 0.653355 0.151156 4.32238 0.0002 C (Constant) 1.026983 0.484875 2.118035 0.0443 R-squared 0.827695 Adjusted R-squared 0.804802 S.E. of regression 0.982458 Sum squared residuals 24.13059 Log likelihood −36.7945 F-statistic 18.68296 Prob(F-statistic) 0.000216 Mean dependent var 2.956891 S.D. dependent var 1.273454 Akaike info criterion 2.873669 Schwarz criterion 2.969656 Hannan-Quinn criter. 2.902211 Durbin-Watson stat 2.274002 Notes: p-values and any subsequent tests do not account for model selection. Tables 6and 7contain the conditional error correction regression of ARDL long-run form and bound test. This regression test contains GDP as the dependent variable and NRR as the independent variable. The ARDL model is run as a case of restricted constant