Estimation of shrub biomass: development and evaluation of allometric models leading to innovative teaching methods

摘要: Accurate estimation of biomass is becoming vital for selling carbon into national and international markets. Being a dry continent, Australia’s natural forest has several shrub species. However, because limited availability methodology difficulty in they are unaccounted many cases. This paper three objectives: (a) to address the major problem multiple regressions, (b) develop best allometric equation popular species, wild raspberry (Rubus probus) (c) prepare teaching tool, by following systematic logical steps, using ForecastXTM software. We identified possible explanatory variables, discussing with experts citing literature, then measured them destructive sampling at Taabinga, near Kingaroy, Queensland. Our research suggests that careful analysis correlation matrices gives very important clues which variables we should select not models. High multicollinearity among independent regressions. study shows this could easily be solved basic scientific formula applying single variable instead highly correlated model. Unlike most statistical books, our does suggest reject from model whose coefficient statistically significantly different zero as it influential another set combination. Similarly, recommend 'intercept' even if its value cost extra money included but help predictive power Although developed range prediction models (for raspberry) can used circumstances, first recommendation based on girth crown volume. Where issues, prefer employs area, good result needs only measured. These findings helpful practical applications regression courses such Data Analysis Business Forecasting.