cenuno
commented
3 years ago Hi Marah,
This is to be expected. You should compare your individual lab 04 and lab 05 source files and ask yourself a series of questions:
- What are my sources of data? What stays the same and which sources are found in one but not the other?
- How are you filtering in one versus the other? Why are you filtering one way in one file but not in another?
- What data manipulation are you doing in one versus the other? Why are you manipulating it in one file but not in another?
These questions build up your awareness so that when you do detect a difference in your unified file, you know enough about the "upstream" logic that it is easy for to point to one decision that accounts for the change. This is why in practice you always start with one file rather than take pieces of two files and unify them into one.
When scaling your analyses in the future, you may want to start considering implementing unit tests: a series of checks that test your data based on a variety of rules that you set. That is beyond the scope of this course but is good for you to be aware of conceptually.
Cheers, Cristian
Hello,
I am combining my. R files of both labs 4 &5, but I am getting slightly different values for lab 04 regression tables. The difference in values is minimal. Should I be getting the exact same values I was getting when I did lab04? I believe it is because of some dropped observations, but I am not sure. Thanks!