Econometric analysis: Dynamic models in Panel

 Cursus:

Econometric analysis: Dynamic models in Panel

1. Presentation of study data

As part of this project of memory project, we are particularly interested in economic growth in Africa. Variables dictated by literary and empirical journals will be retrieved from the World Bank database. In this case, GDP per capita, fossil energy consumption, physical capital ... etc. Other unobservable variables will be able to be calculated. In this sense, it is the savings rate, the net capital inflow, the rates of commercial opening. Our values are in current dollars. The study period or the interval by which we analyze the theme is between 1960 and 2016. In truth, more data remains unavailable for the year 2017. We will then solicit methods of clearing and correction of the missing values before to be able to carry out studies whose prospects seem already purified in the general introduction.

1. Analyses des résultats économétriques

Table C3.10 shows the estimates of the Dynamic Economic Growth Convergence Test Model using the Arellano-Bond Differential Generalized Moment Method and the Bond-Blundell System. These estimators are consistent if the instruments used are valid (null hypothesis of the Sargan or Hansen test) and there is no autocorrelation (null hypothesis of the Arellano-Bond test). In this context, we realize that there is no conditional convergence of the Solow model in Africa, because its speed of convergence is not accessible with the estimation of the Arellano-Bond and Blundell-Bond estimators. In part, this is due to the presence of 2nd order autocorrelation.

 

 

The method of generalized moments with Arellano-Bover / Bond-Blundell and system difference does not also illustrate an existence of conditional convergence velocity. These estimators are consistent if the instruments used are valid (null hypothesis of the Sargan or Hansen test) and there is no autocorrelation (null hypothesis of the Arellano-Bond test). In this terms, only the GMM in system is valid.

The Anderson-Hsiao and LSDV estimators also prove the lack of convergence in Africa for the Solow model. We have more to do with several diversified economies and especially still nursery We will estimate this time the model Solow increased human capital, approximate the number of students in primary school and compare the results obtained beforehand.

The table opposite shows the results of dynamic panel models. In the literature, as we have already pointed out, there is a variety of dynamic methods, that is to say which includes the endogenous variable delayed by one or more periods. In this sense, we group together a battery of these estimators, among which by the Within autoregressive method (Within_AR (1)), autoregressive generalized least squares method (GLS_AR (1)), Arellano-Bond generalized moment method (Diff_GMM ), generalized moments method of Blundell-Bond (Sys_GMM / BB), generalized method of moments of Arellano-Bover and Blundell-Bond in system and difference (Sys_GMM / AB / Diff_GMM / AB), method of Anderson-Hsiao (IV_GMM ) less square method by dynamic dummy variable (LSDV), orthogonality method (OPM), among others, it happens that the estimators of the method of maximum likelihood in dynamic panel is very competitive that the methods of the moments, but for the sake of a paid application, we will not be able to present it. Despite the coefficient significance of the endogenous explanatory variable, all models show the absence of conditional convergence in Africa.

 

We remind you that the whole of this document is accessible on the Amazon site:

https://www.amazon.fr/Boutique-Kindle-ABDI-BASID-ADAN/s?ie=UTF8&page=1&rh=n%3A672108031%2Cp_27%3AABDI-BASID%20ADAN

ADAN, A.-B. (2018). Croissance Economique et Développement Durable en Afrique: Analyses Statistiques et Econométriques [Kindle]. Amazon Media EU S.à r.l.

 © 2026 The Abdi-Basid Courses Institute (tABCi). All rights reserved.

 

 

🏛️ tABCi Laboratories :

🧪 Abdi-Basid ADAN LABS  | Focus: Interdisciplinary Sciences & Education.

🧠 The Deep Thinking Lab | Focus: Philosophy & Human Sciences.

🌍 The EcoClimate Hub | Focus: Climate Science & Environment.

Contact : Abdi-Basid ADAN [abdi-basid@outlook.com]

Click below to view the full Course Catalogue :

       *The Abdi-Basid Courses Institute*

 © 2017-2026 The Abdi-Basid Courses Institute (tABCi). All rights reserved.

Econometric analysis: Panel Model

1. Presentation of study data

 

As part of this project of memory project, we are particularly interested in economic growth in Africa. Variables dictated by literary and empirical journals will be retrieved from the World Bank database. In this case, GDP per capita, fossil energy consumption, physical capital ... etc. Other unobservable variables will be able to be calculated. In this sense, it is the savings rate, the net capital inflow, the rates of commercial opening. Our values are in current dollars. The study period or the interval by which we analyze the theme is between 1960 and 2016. In truth, more data remains unavailable for the year 2017. We will then solicit methods of clearing and correction of the missing values before to be able to carry out studies whose prospects seem already purified in the general introduction.

 

1. Analyse des résultats économétriques

(4 Significativité des variables exogènes au seuil conventionnels 1%, 5% et 10% : 0.000 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ )

In the results of Table C3.2, the estimates of the basic Solow model and the increase in human capital are shown. The regressions carried out are valid on the assumption that the countries are at their stationary state. The coefficient of the savings rate is not only positive but also very significant. It is perfectly suited to the expected result. This means that the rise in the savings or investment rate has a positive impact on per capita GDP growth.

 

For comparative purposes, the model estimated by dummy or dummy variable scrutinized by the country variable provides a reality opposite to what was expected on the sign of the coefficients compared to that of ordinary least squares. In both models, only the human capital variable of the augmented Solow model is significant with a positive coefficient. We can note that the country variable that has more than 50 modalities is not a better stratification of the studied sample. For this purpose, what about the year variable? This is what we will try to answer with the following estimate.

The least squares estimate by fictitious variable, here taking into account the years show another reality opposite to that by fictitious variable country (country). Rather, the results presented in Table C3.4 are rather close to the ordinary least squares in terms of the signs of the expected coefficients. Again, it is not surprising to see in this case the significance of the variables, because indeed there is a link between production, physical capital and human capital. The definition of the year variable as a dummy variable to measure the specific effect of our sample gives better results than that of grouping by country.

 

 

The grouped estimation method (Pooled) is the most appropriate when each observation is independent of the other. By reducing the observations by a panel observation through the calculation of the average. We have the same results from the least squares method and the fictitious year estimate. Physical capital (savings rate) puts upward pressure on GDP per capita as opposed to human capital. Apart from the comparisons made between the models, it is all the more interesting to determine which model is the most efficient and well suited to test the prediction of the convergence of the Solow model and the increased Solow model.

 

 

We remind you that the whole of this document is accessible on the Amazon site:

https://www.amazon.fr/Boutique-Kindle-ABDI-BASID-ADAN/s?ie=UTF8&page=1&rh=n%3A672108031%2Cp_27%3AABDI-BASID%20ADAN)

ADAN, A.-B. (2018). Croissance Economique et Développement Durable en Afrique: Analyses Statistiques et Econométriques [Kindle]. Amazon Media EU S.à r.l.

 © 2026 The Abdi-Basid Courses Institute (tABCi). All rights reserved.

 

 

🏛️ tABCi Laboratories :

🧪 Abdi-Basid ADAN LABS  | Focus: Interdisciplinary Sciences & Education.

🧠 The Deep Thinking Lab | Focus: Philosophy & Human Sciences.

🌍 The EcoClimate Hub | Focus: Climate Science & Environment.

Contact : Abdi-Basid ADAN [abdi-basid@outlook.com]

 © 2017-2026 The Abdi-Basid Courses Institute (tABCi). All rights reserved.