Dear researchers,

I have two questions, please.

I have unbalanced panel data for a set of firms. In 2002 a new standard has been issued, and accordingly, firms started to adopt the standard, but the adoption process is not simultaneous. I mean a group of firms adopted in 2005, other groups adopted in 2003, and so on (i.e., the adoption is in different years). I want to examine the relationship between growth and leverage, and the impact of standards on this relationship.

The previous literature suggested that the relationship between growth and leverage could be simultaneously determined, and they suggest performing a bi-directional model when examining the relationship between growth and leverage.

At first, prior studies have examined the relationship between growth and leverage, but because my contribution will be examining the impact of the standards on this relationship, so at first, since my sample is new, I will conduct the analysis between growth and leverage for the whole sample without considering the impact of the standards, to see if my results will be consistent with the previous studies or not. In other words, to see if I could benchmark my sample or not, or to see if my sample could be a good base to examine the impact of the standards or not. Accordingly, I have used the following bi-directional model:

Code:


    

  1. Leverage = growth + control variable 1 + control variable 2 + control variable 3.
    2. 

  2. growth= Leverage + control variable 1 + control variable 2 + control variable 3.
    3. 




I have found that in both models, leverage and growth have a positive relationship at a significance level of 5% at CI 95%. That means there is reverse causality. This in line with the previous studies.

My first question, if one of the above-mentioned control variables has no significant relationship with the dependent variable, is it okay to examine that control variable in the DID model that will be mentioned below.



Then, I have applied the following models to examine the impact of the standards on the relationship between leverage and growth.






Code:




    

  1. Leverage = growth + control variable 1 + control variable 2 + control variable 3 + Standards + growth× Standards+ control variable 1× Standard + control variable 2× Standards + control variable 3× Standards.
    2. 

  2. growth = leverage + control variable 1 + control variable 2 + control variable 3 + Standards + leverage× Standards+ control variable 1× Standard + control variable 2× Standards + control variable 3× Standards.
    3. 




My second question, the coefficient of growth× Standards in model 3 is significant and negative, while the coefficient of leverage× Standards is not significant and it is positive. Is there any explanation for this thing, or that what I am doing is not correct?



Your answers will be highly appreciated.



Many thanks in advance.