Introduction to panel data, multiple regression method, and principal components analysis using stata: study on the determinants of executive Compensation—A behavioral approach using evidence from Chinese listed firms

Gao, Angela and Cowling, Marc (2019) Introduction to panel data, multiple regression method, and principal components analysis using stata: study on the determinants of executive Compensation—A behavioral approach using evidence from Chinese listed firms. Sage Research Methods Cases. pp. 1-27.

[img] PDF - Published Version
Restricted to SRO admin only

Download (8MB)

Abstract

This case study illustrates a quantitative research study on accounting and finance using panel data from firm databases. Our research argues for the existence of a reference point effect on executive compensation determination, internally (the pay of other directors on board), externally (the industry peer executives’ average pay), and historically (the executive’s pay in the last period), in Chinese listed firms. We illustrate (1) the research process of variable design, including the design and understanding of dependent variables, independent variables, and control variables, as well as the relevant hypotheses development and multiple regression models using firm data and the panel data context; (2) the process of data collection using secondary data from financial database and the construction of a panel dataset; (3) the commands in Stata to run the ordinary least squares multiple regression; and (4) the principal components analysis capturing the systematic effect of the three reference points and perform the principal components analysis in Stata.

Item Type: Article
Schools and Departments: University of Sussex Business School > Accounting and Finance
Subjects: H Social Sciences > HG Finance > HG0101 Theory. Method. Relation to other subjects
H Social Sciences > HG Finance > HG4001 Finance management. Business finance. Corporation finance
Depositing User: Angela Gao
Date Deposited: 28 Nov 2019 09:54
Last Modified: 03 Dec 2019 09:46
URI: http://sro.sussex.ac.uk/id/eprint/88321

View download statistics for this item

📧 Request an update