Quantile regression : applications on experimental and cross section data using EViews / I GustiI Gusti Agung.

I Gusti Ngurah Agung, PhD, The Ary Suta Center, Jakarta, Indonesia. Professor Agung taught at the State University of Makassar from 1960–1987, and at the University of Indonesia from 1987–2018. His research has focused on finding expected or unpredictable statistical results based on various models of time series, cross-section, experimental data, and panel data models. In addition, he is also interested in cross-section data over times and a special or uncommon panel data in indexes.

Includes bibliographical references.

TABLE OF CONTENTS
Ch. 1: Test for Equality of Medians by Series/Group OF Variables

Ch. 2: One and Two-Way ANOVA Quantile Regressions

Ch. 3: N-Way ANOVA Quantile Regressions

Ch. 4: Quantile Regressions Based On (Xi,Yi)

Ch. 5: Quantile Regressions with Two Numerical Predictors

Ch. 6: Quantile Regressions with Multi Numerical Predictors

Ch. 7: Quantile Regressions with the Ranks of Numerical Predictors

Ch. 8: Heterogeneous Quantile Regressions based on Experimental Data

Ch. 9: Quantile Regressions Based On CPS88.wf1

Ch.10 : QUANTILE REGRESSIONS OF A LATENT VARIABLE

Appendix A

Appendix B

Appendix C

Bibliography

"Quantile regression aims at estimating either the conditional median or other quantiles of the response variable. Essentially, quantile regression is the extension of linear regression and we use it when the conditions of linear regression are not applicable. LS-Regressions, Ordinary-Regressions or Mean-Regressions, the Quantile-Regressions (QRs) can be classified into three groups. The first group consists of the QRs with categorical variables, caller ANOVA QRs, where ordinal variables are treated as nominal variables and the numerical independent variables (IVs) are transformed to ordinal variables. The second group consists of the QRs with numerical variables, where the ordinal variables are treated as the numerical IVs. The third group consists of the various interaction QRs with numerical and categorical IV, where the ordinal variables can be treated as either numerical or nominal categorical IVs. Applications of Quantile Regression of Experimental and Cross Section Data using EViews presents examples of statistical results of various QRs in order to display their richer characteristics, based on the LS-Regression, Ordinary-Regressions, or Mean-Regressions. It offers instructions how to develop the best possible QRs and how to present more advanced analysis by using the Quantile Process, the Wald test, the Redundant Variables test, Omitted Variables Test, and forecasting, as well as to draw the best conclusions from results. A mathematical knowledge of quantile regression is not necessary so this book is applicable to students and lecturers in statistics, data analysis and engineering"-- Provided by publisher.

Description based on print version record and CIP data provided by publisher; resource not viewed.