SOCOL CRISTIAN| MARINAS MARIUS MINIMUM WAGE AS A PUBLIC POLICY INSTRUMENT – PROS AND CONS We also applied the CUSUM test to identify the stability of the estimated coefficients. This test considers the cumulative sum of recursive errors obtained by regression, which, in order to satisfy the stability condition, should be within the interval between two critical lines. In table 6, we included the results obtained by estimating the five equations by the OLS method, the probabilities associated to the coefficients of the exogenous variables, the values for adjusted R2(the extent to which the variation of the dependent variable is explained by the exogenous variables with standard adjustment to avoid random influences), the probability associated to the F test, whose null hypothesis is that all the parameters of the model are zero, as well as the probabilities associated to the conditions of distribution normalization, of presence of the homoscedasticity condition and of absence of autocorrelation in errors, for residues. Note that these hypotheses necessary for the validity of residues are accepted with a probability of at least 14.31%, i.e. above the established thresholds of 5% or 10%. Table 6. Estimation of the minimum wage impact in Romania Endogenous variables Coefficients of exogenous variables; [probability associated to the t-statistic test] Adjusted R² 1. 2. demployment.rate dyouth.employment.rate +0. 04* constant [0. 1330] +0. 98* dactivity.rate [0. 0000] +1. 87* dlnminimum.wage [0. 0000] -0. 03* constant [0. 5886] -0. 12* dyouth.employment.rate (-1) [0. 0144] +2. 27* dlnminimum.wage [0. 0274] -2. 18* dlnminimum.wage (-4)[0. 0000] -2. 10* dlnminimum.wage (-4)[0. 0177] +0. 78* dyouth.activity.rate [0. 0000] 0. 955 0. 865 3. dInaverage.wage +0. 29* constant [0. 0002] 4. InCPI +0. 00* constant [0. 3772] 5. lnIPP +0. 31* constant [0. 0000] -0. 52* dlnaverage.wage (-1)[0. 0000] +0. 04* dlnminimum.wage (-3)[0. 0039] -0. 03* Lnproductivity [0,0000] +0. 15* dlnminimum.wage (-1)[0. 0034] +0. 31* lnIPP [0. 0000] +0. 05* dlnminimum.wage [0. 0111] -0. 02* dunemployment.rate [0. 0091] +0. 28* lnIPP (-3) [0. 0000] -0. 02* dlnminimum.wage (-3)[0. 3011] +0. 40* lnproductivity [0. 0000] -0. 43* lnproductivity (-1) [0. 0000] -0. 00* dunemployment.rate [0. 0926] 0. 590 0. 753 0. 701 F statistic probability 0. 0000 0. 0000 0. 0000 0. 0000 0. 0000 H0 probability Normalization of 0. 186 0. 171 distribution 0. 854 0. 480 0. 153 H0 probability Absence of autocorrelation in errors H0 probability Homoscedasticity CUSUM test 0. 2839 0. 3427 Satisfied 0. 5983 0. 1431 Satisfied 0,. 6197 0. 2423 Satisfied 0. 7613 0. 5381 Satisfied 0. 2266 0. 3777 Satisfied 34