Tag Archives: Seemingly Unrelated Regression

Bayesian Estimation of Seemingly Unrelated Regression with Collinear Categorical Explanatory Variables (Published)

The efficiency of Seemingly Unrelated Regression (SUR) not only depends on contemporaneous correlation between errors term but also on the degree of collinearity among explanatory variables in the equations of the model. The problem of collinearity consequentially leads to biased estimation, rank deficient, large standard deviations and misleading interpretation of the estimates among others in analysis. This study examines the robustness of the Bayesian estimator to varying degree of correlation among categorical explanatory variables of seemingly unrelated regression model. The result revealed an asymptotic property of the Bayesian method and the best estimates were obtained when sample size, N is large irrespective of the degree of correlation among the regressors.

Keywords: Bayesian estimator, Seemingly Unrelated Regression, collinearity, posterior standard deviations

Arbitrage Pricing Theory as Investment Decision Making Tools. Case of the Indonesian Oil, Gas, and Coal Mining Firms (Published)

Fossil energy sources such as oil, gas, and coal are the primary energy sources to support global modern economy. Over the last six years, global coal and oil prices has fell to its lowest in the last decades and drove Indonesian energy mining sector performances to collapse. The dependency to global energy prices creates uncertainty among investor, thus compelling the necessity of investment tools that could advise investor to take investment decision. Arbitrage Pricing Theory (APT) has been proven to be one of the most reliable asset pricing tools utilizing macro-multifactors. This research purposes are to utilize APT model as tools to predict eleven firms in coal, oil, and gas mining prices and analyzing macro factors of global coal, oil, and gas prices, exchange rate, interest rate, and consumer price index to give investment decision-making indication. This research use Seemingly Unrelated Regression weighted pooled least square method in panel data structure. Observing 6-year period using monthly data. This reasearch found that APT model could be use as technical tools to estimate the prices and return of stock prices of eleven firms. By utilizing mispricing moment, this model could also give investment decision making indication to investor.

Keywords: Arbitrage Pricing Theory, Energy Mining Sector, Indonesia Stock Exchange, Seemingly Unrelated Regression