Sign differences in coefficients arising from using ordinal vs continuous data

I run a simple OLS regression: y=a +bx+.....+e,

I obtain an estimate of b<0.

Prior researchers running the a similar regression obtain an estimate of b>0: I'm trying to reconcile this difference.

The only methodological difference driving our results is the following:

In my study, both y and x are continous variables.

The prior researcher uses ranked data: y ={1,2,3,4,5} and x={1st,2nd,..... nth}.

My question is: can the difference in methodology explain the difference in estimates for b (sign change)? If so, how?

Many thanks to anybody who comments


Less is more. Stay pure. Stay poor.
Please better describe what was done in the past (e.g., rank?). Also, were samples comparable and models contained the same covariates? Lastly, are you finding a significant negative coefficient and they all had a positive significant coefficient. Are there any other model parameters available? Are sample sizes comparable.

Finally, given everything is comparable, it could also be an example of replicability or researcher degree of freedom.