I have a dataset made of more than 10K observations. For each of them I know the value of a continuous variable (C1), and the value of three nominal variables: N1, which can take three different values (let's say "A", "B" and "C", corresponding to three different groups of observations), N2 and N3, which can take thirty and twenty different values, respectively. What I need to know is if the value of C1 is somehow affected by the value of N1, accounting for N2 and N3. I thought that multiple regression might help. Now I'll explain how I proceeded:
I've dummy-coded my three nominal variables (N1, N2, N3), i.e. in my dataset I have replaced the N1 variable with two dummy variables (N1_dummyB and N1_dummyC, with "A" as the reference level), the N2 variable with twenty-nine dummy variables, and the N3 variable with nineteen dummy variables.
Since the continuous variable (C1) was not normal-distributed, I've log-transformed it.
I used the software JASP to carry out the regression analysis, using log-transformed C1 as the dependent variable, and all the other variables (two + twenty-nine + nineteen dummy variables) as covariates.
These are the results of the analysis on JASP (I put only the first seven lines of the coefficients table):
Based on this, is it correct to say that the C1 variable is on average 0.244 higher in group B than in group A, and that the same variable is on average 0.128 higher in group C than in group A, and that this difference is significant even when "controlling" for the other two nominal variables (N2 and N3)?