scholarly journals Approaches to Modelling  Heterogeneity in Longitudinal  Studies

2021 ◽  
Author(s):  
◽  
Xiaomei Li
Keyword(s):  
Longitudinal Data ◽  
Random Effect ◽  
Fixed Effect ◽  
Estimation Methods ◽  
Estimation Bias ◽  
Individual Effect ◽  
Hausman Test ◽  
Explanatory Variables ◽  
Effect Estimation ◽  
The Individual

<p>This thesis is about estimation bias of longitudinal data when there is correlation between the explanatory variable and the individual effect. In our study, we firstly introduce what is longitudinal data, then we introduce the commonly used estimation methods for the general linear model: the least squares method and maximum likelihood method. We apply these estimation methods to three simple general models which are commonly used to analyse longitudinal data. Secondly, we use frequentist and Bayesian analysis to explore the estimation bias theoretically and empirically, with an emphasis on the heterogeneity bias. This bias occurs where random effect estimation is used to analyse data with nonzero correlation between explanatory variables and the individual effect. We then empirically compare the estimated value with the true value. In this way, we demonstrate and verify the theoretical formulation which can be used to determine the size of the bias [Mundlak, 1978]. In order to avoid the estimation bias, the fixed effect estimation should be used to get the better solution under nonzero correlation situation. The Hausman test is used to confirm this. However, the bias not only occurs when we use frequentist analysis, but also exist by using the Bayesian estimation of random effect model. Finally, we follow the Mundlak [1978] idea, then define the special Bayesian model which can be used as Hausman test and as a comparable model. We also prove that it is best fit model among the random effect, fixed effect and pooled model if there is correlation between explanatory variables and individual effect. Throughout this thesis, we illustrate this ideas using examples based on real and simulated data.</p>

scholarly journals Approaches to Modelling  Heterogeneity in Longitudinal  Studies

2021 ◽  
Author(s):  
◽  
Xiaomei Li
Keyword(s):  
Longitudinal Data ◽  
Random Effect ◽  
Fixed Effect ◽  
Estimation Methods ◽  
Estimation Bias ◽  
Individual Effect ◽  
Hausman Test ◽  
Explanatory Variables ◽  
Effect Estimation ◽  
The Individual

<p>This thesis is about estimation bias of longitudinal data when there is correlation between the explanatory variable and the individual effect. In our study, we firstly introduce what is longitudinal data, then we introduce the commonly used estimation methods for the general linear model: the least squares method and maximum likelihood method. We apply these estimation methods to three simple general models which are commonly used to analyse longitudinal data. Secondly, we use frequentist and Bayesian analysis to explore the estimation bias theoretically and empirically, with an emphasis on the heterogeneity bias. This bias occurs where random effect estimation is used to analyse data with nonzero correlation between explanatory variables and the individual effect. We then empirically compare the estimated value with the true value. In this way, we demonstrate and verify the theoretical formulation which can be used to determine the size of the bias [Mundlak, 1978]. In order to avoid the estimation bias, the fixed effect estimation should be used to get the better solution under nonzero correlation situation. The Hausman test is used to confirm this. However, the bias not only occurs when we use frequentist analysis, but also exist by using the Bayesian estimation of random effect model. Finally, we follow the Mundlak [1978] idea, then define the special Bayesian model which can be used as Hausman test and as a comparable model. We also prove that it is best fit model among the random effect, fixed effect and pooled model if there is correlation between explanatory variables and individual effect. Throughout this thesis, we illustrate this ideas using examples based on real and simulated data.</p>

Free Cash Flow and Firms' Growth: An Empirical Investigation of Nigerian Quoted Non - Financial Firms

2018 ◽  
Vol 10 (3(J)) ◽  
pp. 258-267
Author(s):  
Gideon Tayo Akinleye ◽  
Odunayo Magret Olarewaju ◽  
Kole Samson Fajuyagbe
Keyword(s):  
Cash Flow ◽  
Net Present Value ◽  
Negative Impact ◽  
Random Effect ◽  
Free Cash Flow ◽  
Percentage Change ◽  
Total Asset ◽  
Estimation Methods ◽  
Effect Estimation ◽  
The Impact

This study analyzes the effect of free cash flow on the growth of non- financial quoted firms in Nigeria. Specifically, the impact of free cash flow on the percentage change in a total asset of selected quoted firms (Dangote Flour Mills, Honeywell Nig. Plc, Dangote Sugar Refinery, Flour Mills of Nig. Plc, and PZ CussonsPlc) over a period of five years (2012 - 2016) was analysed . Data used in the study were sourced from the annual reports of the selected quoted firms. Correlation analysis, restricted F - test, Hausmantest, and some panel estimation methods (pooled OLS estimation, fixed effect estimation, and random effect estimation) were employed to analyse the data. Results revealed that free cash flow exerts a negative impact on firms ' growth rate, to the tune of - 0.000391(p=0.179 > 0.05). The study, therefore, established that rising free cash flow has the capacity to erode the growth prospect of firms quoted on the Nigeria stock exchange. Based on this result, the study recommends that quoted firms in the country decrease their free cash flow, leverage increased turnover, explore viable/positive net present value projects, and reduce operational costs so as to be positioned for better growth in terms of percentage change in total asset.

scholarly journals Research on the Economic Impact of Shandong Expressway Development

2021 ◽  
Vol 2 (1) ◽  
Keyword(s):  
Capital Investment ◽  
Random Effect ◽  
Random Effect Model ◽  
Highway Construction ◽  
Spatial Effect ◽  
Shandong Province ◽  
Hausman Test ◽  
Explanatory Variables ◽  
Effect Model ◽  
The Impact

By obtaining the panel data of 16prefecture-level cities in Shandong Province from 2005 to 2018 for 14 years, this paper selects Shandong highway mileage as the core explanatory variable, GDP as the explained variable, urbanization rate, passenger volume, freight volume, government participation and fixed capital investment level as other explanatory variables, and adds economic lag effect on this basis. The fixed effect model or random effect model is tested according to the modified Hausman test. In order to make the results more accurate and reliable, the data are tested and corrected by inter-group heteroscedasticity, intra-group autocorrelation, cross-sectional correlation and multiple collinearity, and the spatial effect of Shandong economy is tested by Moran index. In-depth verification of the impact of highway construction on the economy of Shandong Province. The results show that the random effect model has passed the Hausman test. The revised model shows that highway construction has a positive effect on the overall economy of Shandong Province, and other explanatory variables also have varying degrees of pulling effect on the economy, but the spatial effect of economy is not significant, which provides a reference basis and example verification for highway construction in the future. To better promote the close ties between the regions of Shandong Province and make contributions to economic development.

scholarly journals Individual and community-level factors influencing optimal breastfeeding: A multilevel analysis from a national survey study in Ethiopia

2019 ◽  
Author(s):  
Amanuel Hagos ◽  
Mache Tsadik ◽  
Abate Bekele ◽  
Afewerki Tesfahunegn
Keyword(s):  
Child Death ◽  
Random Effect ◽  
Wealth Index ◽  
Community Level ◽  
Survey Study ◽  
Hierarchical Level ◽  
Individual Level ◽  
Explanatory Variables ◽  
Variation Explained ◽  
The Individual

Abstract Background Optimal breastfeeding is critical for healthy growth. Despite this about 820,000 children and 20,000 women lost due to inappropriate breastfeeding each year globally. In Ethiopia, about 50,000 children lost related to malnutrition. Of these, about 18% of child death is contributed by poor breastfeeding habit. Many studies reported the individual-level factors; however, little is known about the determinants of breastfeeding at the hierarchical level. Therefore, this study aimed to identify factors associated with optimal breastfeeding among children age 0-5 month in Ethiopia using multilevel analysis.Methods A five-year representative survey study was conducted to assess the determinants of optimal breastfeeding among 1,087 children aged 0-5 months using the 2016 Ethiopian Demographic and Health Survey data (EDHS). Both bivariate and multivariable multilevel logistic regression analysis were done to identify significant explanatory variables. Fixed effect and random effect were done to estimate the association between the dependent and explanatory variable and to measure the variation explained by the higher level respectively.Results Among the total of 1,087 children, only 45.4% of optimally breastfed. Children aged 4-5 months (AOR =0.19; 95%CI: 0.12-0.27), children from richest wealth index (AOR=2.87; 95% CI: 1.53- 5.43), children born through cesarean section and residing in Afar region were found significantly associated with optimal breastfeeding. The random-effects showed that the variation between communities was statistically significant.Conclusion Both individual and community level factors play a significant role in shaping optimal breastfeeding. Future strategies and health interventions should target individual and community level factors that enhance optimal breastfeeding.

scholarly journals Relation Between Cigarette Smoking and Sarcopenia: Meta-Analysis

2015 ◽  
pp. 419-426 ◽  
Author(s):  
M. STEFFL ◽  
R. W. BOHANNON ◽  
M. PETR ◽  
E. KOHLIKOVA ◽  
I. HOLMEROVA
Keyword(s):  
Risk Factor ◽  
Cigarette Smoking ◽  
Meta Analysis ◽  
Random Effect ◽  
Random Effect Model ◽  
Fixed Effect Model ◽  
Fixed Effect ◽  
Effect Model ◽  
The Individual ◽  
The Relationship

Cigarette smoking is a risk factor for many diseases. It could be associated with sarcopenia. The aim of this meta-analysis was to determine whether smoking is an isolated risk factor for sarcopenia. We searched PubMed, Web of Science, EBSCO, and Science Direct for articles addressing the relationship between cigarette smoking and sarcopenia. A total of 12 studies containing information on 22,515 participants were included in this meta-analysis. Odds ratio (OR) was calculated for each study group and for all studies together. An OR was also calculated separately for each sex. We used a fixed-effect model in overall estimation and in males, because results of small studies were significantly different from the results of large studies in those cases and in females where the estimation showed only moderate heterogeneity we used a random-effect model. According to proposes of the Cochrane Handbook for Systematic Reviews. The resulting OR in the fixed-effect model was 1.12 (95 % CI 1.03-1.21), OR for each sex was in the fixed-effect model 1.20 (95 % CI 1.06-1.35) in males and in the random-effect model 1.21 (95 % CI 0.92-1.59) in females. The results of this meta-analysis indicate that cigarette smoking as an isolated factor may contribute to the development of sarcopenia. However, the results of the individual studies were largely inconsistent due to different approaches of measuring the main variables which affected the results.

scholarly journals Analisis Pengaruh Kesehatan Keuangan Bank Terhadap Kontribusi Sosial Bank Umum Syariah Indonesia

2019 ◽  
Vol 3 (1) ◽  
pp. 1-19
Author(s):  
Sandi Andika
Keyword(s):  
Least Squares ◽  
Error Term ◽  
Random Effect ◽  
Ordinary Least Squares ◽  
Fixed Effect ◽  
Hausman Test ◽  
Chow Test

Pertumbuhan perbankan syariah pasca diterbitkannya Undang-undang Nomor 10 tahun 1998 sangat signifikan, yang sebelumnya hanya ada satu bank syariah yaitu BMI pada tahun 1992. Menjamurnya bank-bank syariah di tengah-tengah masyarakat muslim di Indonesia diharapkan mampu memberikan perubahan yang signifikan terhadap permasalahan yang melanda masyarakat Indonesia yaitu kemiskinan dan berbagai macam kesenjangan sosial lainnya. Dengan demikian, sebagai perbankan yang berbasis Islam, tentu seharusnya bank syariah memberikan keseimbangan antara prestasi bank syariah dalam hal ini diketahui melalui tingkat kesehatan bank syariah dengan kontribusi sosial. Tujuan dari penelitian ini adalah untuk mengetahui kondisi kesehatan keuangan bank syariah, kondisi kontribusi sosial bank syariah dan menganalisis keterpengaruhan antara kesehatan keuangan bank syariah dengan kontribusi sosial bank syariah. Metode yang digunakan dalam penelitian ini adalah analisis deskriptif kuantitatif. Objek penelitian ini adalah 3 (tiga) bank umum syariah yaitu Bank Muamalat Indonesia (BMI), Bank Syariah Mandiri (BSM) dan Bank Mega Syariah Indonesia (BMSI). Periode penelitian ini selama 7 (tujuh) tahun dari tahun 2004 sampai 2010. Melalui analisis deskriptif diketahui bahwa secara umum kesehatan bank syariah dalam kondisi sehat dengan BMI mendapat nilai kredit tertinggi sebesar 97,14 selanjutnya BMSI dan BSM mendapat nilai kredit 89,31 dan 85,48. Sedangkan kontribusi sosial bank syariah secara umum dalam kondisi cukup baik, BSM mendapat nilai kredit tertinggi sebesar 71,85 selanjutnya BMSI dan BMI dengan masing-masing nilai kredit sebesar 68,35 dan 68,07. Analisis data yang digunakan adalah analisis regresi data panel dengan 3 (tiga) metode pendekatan yaitu Pooled Ordinary Least Squares (PLS), Fixed Effect Methode (FEM) dan Random Effect Methode (REM). Melalui pemilihan model dengan Chow Test dan Hausman Test dihasilkan model yang paling efektif adalah metode PLS. Berdasarkan metode PLS dilakukan uji t, diketahui bahwa variabel independen (kesehatan keuangan bank syariah) tidak berpengaruh signifikan terhadap variabel dependen (kontribusi sosial bank syariah) berdasarkan t-statistik 1,80 < t-tabel 2.09 pada tingkat signifikansi  = 5%. Koefesien determinasi R2 menunjukkan bahwa variabel independen kesehatan keuangan bank syariah mampu menjelaskan variasi kontribusi sosial bank syariah sebesar 14% sisanya sebesar 86% dijelaskan oleh variabel lain (error term) yang tidak dimasukkan didalam persamaan model ini.

scholarly journals PENGARUH STRUKTUR MODAL DAN WORKING CAPITAL TURNOVER TERHADAP PROFITABILITAS (Studi Empiris pada Pembayar Pajak Perusahaan yang di Periksa oleh Kantor Pelayanan Pajak Madya Jakarta Pusat)

2017 ◽  
Vol 19 (3) ◽  
pp. 398
Author(s):  
Amdani Amdani ◽  
Desnerita Desnerita
Keyword(s):  
Capital Structure ◽  
Random Effect ◽  
Random Effect Model ◽  
Fixed Effect Model ◽  
Fixed Effect ◽  
Estimation Methods ◽  
Working Capital ◽  
Purposive Sampling ◽  
Effect Model ◽  
The Capital Structure

Penelitian ini bertujuan untuk mendapatkan informasi tentang bagaimana pengaruh Struktur Modal dan Perputaran Modal Kerja baik secara individu atau bersamasama (simultan) terhadap profitabilitas Wajib Pajak perusahaan diperiksa oleh Kantor Pajak Madya Jakarta Pusat. Populasi dalam penelitian ini adalah perusahaan Wajib Pajak yang diperiksa oleh kantor pajak Madya Jakarta Pusat periode 2008-2012, metode sampling dengan teknik purposive sampling, dengan jumlah sampel 15 perusahaan. Data yang digunakan adalah data sekunder, analisis motode adalah analisis data panel dengan Umum Efek Model (pooled kuadrat terkecil), Fixed Effect Model (FEM), dan Random Effect Model (REM) untuk menentukan akurasi dari model yang digunakan kebutuhan Model untuk diuji antara Model tes lain Estimasi Metode, asumsi klasik yang mendasari model regresi. Hasil pengolahan dan analisis data yang diperoleh dari hasilnya adalah efek dari Struktur Modal dan Perputaran Modal Kerja Terhadap Profitabilitas secara signifikan, baik secara parsial maupun secara simultan.This research aims to obtain information on how the influence of the Capital Structure and Working Capital Turnover either individually or jointly (simultaneously) on the profitability of the company Taxpayers inspected by the Tax Office Madya Jakarta Pusat. The population in this study are companies Taxpayers are inspected by the tax office Madya Jakarta Pusat period 2008-2012, the sampling method with purposive sampling technique, with a total sample of 15 companies. The data used is secondary data, motode analysis is the analysis of panel data with Common Effect Model (pooled least squares), Fixed Effect Model (FEM), and Random Effect Model (REM) to determine the accuracy of the model used the model needs to be tested between another test Model Estimation Methods, classical assumption underlying the regression model. The results of processing and analysis of data obtained from the result is the effect of the Capital Structure and Working Capital Turnover On Profitability significantly, either partially or simultaneously.

scholarly journals Impact of East African Community Integration on Trade: Gravity Model Approach

2021 ◽  
Vol 04 (11) ◽  
Author(s):  
Kiptum George Kosgei ◽  
Keyword(s):  
Gravity Model ◽  
Random Effect ◽  
Parametric Model ◽  
Fixed Effect ◽  
East African ◽  
East African Community ◽  
Long Run ◽  
Short Run ◽  
African Community ◽  
Effect Estimation

East African community (EAC) is a regional economic bloc established to foster economic corporation between Kenya, Rwanda, Burundi, Uganda and Tanzania. Using gravity model the study explores the short run and long run effect of East African community (EAC) on trade using parametric, random effect and fixed effect estimation techniques. Secondly, the study investigates whether formation of EAC led to trade creation or trade diversion in the long run among the member countries of EAC. Lastly, the study establishes the effect of entry of Burundi and Rwanda to the economic bloc of EAC on trade. The study used panel data obtained from the five countries of EAC for the period 1985 to 2019. Breausch Pagan LM test for restrictions in the parametric model and Hausman test for endogeinity in the gravity model found out that fixed effect estimation technique produced accurate and plausible results than parametric and random effect estimation techniques. The empirical results of fixed effect model established that trade across EAC member countries rose by 1.6% in the short run while random effect and parametric models recorded 3.6% increase in trade in the short run. This effect was insignificant meaning that trade between EAC member countries did not expand considerably in the short run. In the long run, fixed effect indicate that EAC increased trade by 24.2% while random effect and parametric model each show that EAC increased trade by 16%. The coefficients are statistically significant at 5% ceteris paribus. Secondly, economic corporation of EAC led to trade creation in Burundi, Kenya, Rwanda and Uganda by 41.6%, 12.2%, 33.9% and 30.1% respectively and trade diversion by 4.2% in Tanzania. Thirdly, entry of Burundi and Rwanda to EAC increased trade of EAC countries by 19.6%. The coefficient is statistically significant at 5% level. The results of random effect and parametric model each indicate a growth in trade by 19.1%. The results of parametric, random effect and fixed effect estimation techniques are all consistent. Lastly, the study established that countries in EAC ought to foster greater growth in GDP, to encourage and strengthen use of common language and to reduce cross border restrictions in order to realize more growth in trade.

scholarly journals Capital Adequacy A Moderating Effect of Asset Growth on Performance of Nigerian Agricultural Firms

2021 ◽  
Vol 1 (2) ◽  
pp. 8-19
Author(s):  
Shehu Usman Hassan ◽  
Masud Abdullahi Baba ◽  
Tukur Danlami ◽  
Ibrahim Ayuba Kambai
Keyword(s):  
Firm Size ◽  
Agricultural Sector ◽  
Random Effect ◽  
Fixed Effect ◽  
Capital Adequacy ◽  
Analysis Model ◽  
Hausman Test ◽  
Asset Growth ◽  
Longitudinal Regression ◽  
Level Of Significance

This study examines capital adequacy and the moderating impact of asset growth on the performance of firms in the agricultural sector. 4 listed agricultural firms were examined over a period of 10 years and data were extracted from their financial statements which were analyzed through a STATA 13 tool of analysis. Regression, correlation matrix and descriptive methods of analysis were employed to present and analyze results. Other post estimation tests like skewness and kurtosis test, Variance Inflation Factor test, specification test, heteroskedasticity tests and hausman test to select between fixed effect and random effect regression model were conducted to ensure robustness of results. The fixed effect stochastic longitudinal regression analysis model was adopted as guided by the hausman test. From the findings posited by the study, liquidity structure, liquidity structure moderated by asset growth and the combined effect of firm size moderated by asset growth were found to be significantly impacting on return on asset of firms at 1% level of significance. Firm size was found not to have any significant impact on return on assets. It was therefore recommended that the management should ensure considerable excess of current assets over current liabilities at all times so that there will always be positive liquidity structure; management should ensure consistent and prudent capital acquisition to ensure larger firm size; management should ensure steady asset growth by asset revaluation and new acquisition over time; the regulatory authority in the agricultural sector should establish a firm size benchmark below which no firm should operate.

Language in mental retardation: Individual and syndromic differences, and neurogenetic variation 1Based on a keynote presentation at the Third European Conference on Psychological Theory and Research in Mental Retardation, Geneva, September 1st, 2000.

2001 ◽  
Vol 60 (3) ◽  
pp. 161-178 ◽  
Author(s):  
Jean A. Rondal
Keyword(s):  
Mental Retardation ◽  
Language Development ◽  
Oral Language ◽  
Psychological Theory ◽  
Genetic Syndromes ◽  
Explanatory Variables ◽  
Keynote Presentation ◽  
Genetic Origins ◽  
The Sixties ◽  
The Individual

Predominantly non-etiological conceptions have dominated the field of mental retardation (MR) since the discovery of the genetic etiology of Down syndrome (DS) in the sixties. However, contemporary approaches are becoming more etiologically oriented. Important differences across MR syndromes of genetic origin are being documented, particularly in the cognition and language domains, differences not explicable in terms of psychometric level, motivation, or other dimensions. This paper highlights the major difficulties observed in the oral language development of individuals with genetic syndromes of mental retardation. The extent of inter- and within-syndrome variability are evaluated. Possible brain underpinnings of the behavioural differences are envisaged. Cases of atypically favourable language development in MR individuals are also summarized and explanatory variables discussed. It is suggested that differences in brain architectures, originating in neurological development and having genetic origins, may largely explain the syndromic as well as the individual within-syndrome variability documented. Lastly, the major implications of the above points for current debates about modularity and developmental connectionism are spelt out.

Sign in / Sign up

Export Citation Format

Share Document