0

I'm new to MLM both in R and in general. I have a dataset of Building permits for a couple of cities and I have created a variable counting the number of parcels with a permit. Now, I want to perform a MLM to see if there is a census tract (a geographic level) effect going on. Here's where I hit a problem. When writing this line:

lmer(PERMITS ~ 1 + howeownership + (1 | CITY), data = dt2, REML = FALSE)

Do I need to also include census tract variable? If not, how would R know that my levels are CITY>>CT>>PERMITS (which is really the outcome)?

MrFlick
  • 195,160
  • 17
  • 277
  • 295
Kawi
  • 19
  • 5
  • Presumably the "howeownership" (Chgeck your spleding) is something you are measuring at a census tract level of detail. That would be interpreted as a fixed effect in the ME framework you are setting up. If that doesn't make sense then any followups should go first to your TA or professor and failing that to the CrossValidated.com portion of the SE universe. – IRTFM Feb 19 '20 at 19:47
  • Yeah homeownership is a variable of the census tracts. I get that but wouldn't it need me to add census tract itself in the model? Will ask my prof as well. Thanks! – Kawi Feb 19 '20 at 20:10
  • I'm guessing homeownership is a ratio or proportion. So the census tract effect would be expressed as the increase in the PERMITS value per unit increase in homeownership. – IRTFM Feb 19 '20 at 20:16

0 Answers0