Office for E-Book Marketing


LEE, R.-S. (2024), "Improving Standard Moment Estimators of Beta Random Variables"



Abstract

The beta distribution of the first kind, including two shape parameters, is a flexible curve specification in studying the classical moment method of statistical principles. The research of this paper, originating with a need similar to that in econometrics, further finds a sequence of explicit high-order moment estimators for the beta distribution. In addition to the trials of weighting different moment estimators, this research also examines a deserving-emphasis condition for estimating the classic four-parameter beta distribution and permitting moment-equation substitution. 24 pages (20.00 USD)



LEE, R.-S. (2024), "Special Disequilibrium Estimates of Demand and Supply Models"



Abstract

This paper uses a small sample of simulated disequilibrium quantities and prices to estimate major parameters of the originated demand and supply regressions. The model's structural equations are frequently specified to analyze the equilibrium and disequilibrium conditions of a market. The research included is interested in interpreting and resolving estimation difficulties for a type of econometric models where the demand and supply quantities are partially observed. The simplified question is ``How to estimate the parameters of the demand and supply distributions just from the data of the minimal quantity and the traded price without information of other explanatory variables?" After studying classical statistical methods more thoroughly, the method of moments plus cumulants is verified achievable in deriving a primary estimator under the assumptions of price endogeneity and stationarity. If the market's price mechanism of eliminating excess demand or supply is explicitly deleted, the proposed moment estimator is not consistent, but it is modifiable to be a plausible approximation for the intended maximum likelihood estimation. Two examples of the estimation process are exposed in the paper with a number of realistic and flexible adjustments to support the combined estimation procedures. 26 pages (20.00 USD)



LEE, R.-S. (2024), "Evaluating Referential Estimations of the Probit and Logit Models," (forthcoming)



Abstract

The probit and logit regression models taught in econometric courses require referential estimations to increase the confidence on the preferred distribution forms of the disturbance terms. Since the normality of the probit model is mesokurtic and symmetric, it is recommended that in application one should add the leptokurtic, platykurtic, and non-symmetric modification to the original maximum likelihood estimation. Similarly, because the logistic random variable's probability density curve is leptokurtic, the continuing estimation is to include the mesokurtic, platykurtic, and non-symmetric modification. This paper performs an actual application of the referential estimations, from analyzing the residential housing decision data in a micro-economic survey.​