OLS linear regression analysis is a crucial statistical tool for estimating the relationship between variables. Usually the estimator indicates the causality between one variable and another (A Sykes, 1993) (for example the price of the product and its quantity demanded). This report will analyze the product "Supa-clean", a new detergent in Cleano-max PLC, through two models: a demand function and a multivariate demand function. After analyzing the estimator, the weaknesses and room for improvement of this statistical tool will be discussed.Ⅱ Estimation of demand with constant price elasticityⅰ. The following tables demonstrate the calculation of key values ​​on the demand function estimate for Supa-clean. ⅱ. When explaining how crucial OLS linear regression analysis is in estimating own price elasticity, three aspects need to be taken into consideration: the analysis of two objects, the relationship between them, and the diagnostic methods used for the consequences. In general, elasticity measures how a dependent variable varies with n independent variable (n = 1 in the demand function). Therefore, the elasticity of demand measures the change in quantity relative to the change in price. Its formula is: η= (percentage change in price / percentage change in price) (2.4) Percentage changes in Q or P means that the proportion of the change in Q or the change in P occupied the total of Q or P. and represents the change in quantity and price, respectively, which could be calculated as: η= = * (2.5)= the slope of the demand function. Equation (2.5) indicates that it is the slope coefficient of the demand function. In price elasticity, this formula (2.5) would be a... middle of paper ......and plausible modelIn general, this report uses OLS linear regression to estimate two models: a demand function and a multivariate demand function of "Supa-clean". In addition to this, several weaknesses of two models and this methodology are also indicated, such as: the problem of omitted variables or the problem of multicollinearity. Finally, the plausibility of the multivariate demand function model was demonstrated to be better than that of the demand function. Works Cited by A Sykes, 1993, An introduction to regression analysis BR Beattie, CR Taylor, MJ Watts – 1985, The economics of production DR Anderson, DJ Sweeney, TA Williams, 2011, Statistics for business and economicsSN Goodman,1999 , Towards evidence-based medical statisticsI Dobbs, 2000, Managerial economicsM Shalev, 2007, Limits and alternatives to multiple regression in comparative research