Message/Author 


In doing some multilevel modeling, my ICC appears to be quite low (barely .01). My thought is that it would be foolish to run a multilevel model with such a low ICC. To still acccount for this very slight effect of clusters, I was thinking I should run the analysis in TYPE=Complex as conceptually and by design there are in fact clusters. Please tell me if that's logical enough. 


It is not the size of the intraclass correlation alone that determines whether nonindpendence of observations needs to be accounted for. It is the design effect which is a function of the size of the intraclass correlation and average cluster size. TYPE=TWOLEVEL and TYPE=COMPLEX are two different ways to take nonindependence of observations into account. With TWOLEVEL, nonindependence of observations is modeled. With COMPLEX, it is taken into account. The choice depends on whether you want to know something about the clusterlevel parameters or just control for nonindependence of observations. 


Thanks Linda! 


Hi Lucy, I would also calculate the Design Effect which is based on the ICC and the average cluster size, where DEFF = 1 + (Average cluster size  1)*ICC. If you find that DEFF >= 2, then you should address the clustering. 


Note that this formula holds for means with equal cluster sizes. It is probably a decent approximation in other cases though. 

Lucy Morgan posted on Tuesday, February 03, 2015  3:44 am



Hi I hope this hasn't been answered elsewhere (I did have a good search first!). My study was designed to be multilevel, measuring care assistant variables (Level 1) within nursing homes (manager variables  level 2). The ICCs for dependent variables are very low (.062 and .086), both DEFF values are < 2 and all manager (L2) variables are nonsignificant predictors so I have decided that multilevel analysis is not suitable. I have then run the analyses with TYPE = COMPLEX to account for the clustered data but this in fact makes the overall model fit worse. My questions are 1) am i correct to get rid of multilevel modelling given the low ICC AND low DEFF? And would it be better NOT using the TYPE = COMPLEX analysis since it makes model fit worse? (In another post you state that TYPE = COMPLEX is the right analysis to use with clustered data but in that instance the person posting found that model fit improved using TYPE = COMPLEX) Many thanks for your help Lucy 


I think you should use Type=Complex if you have at least 20 clusters. 

Lucy Morgan posted on Wednesday, February 04, 2015  1:27 am



Hi, thanks so much. I have 38 clusters so will go ahead with Type = complex analyses. And thanks so much for this forum and your speedy and helpful responses, this is an invaluable resource! 


Hi, is there a citation for the need to address clustering when DEFF >=2 but ICCs are low? What about the reverse: high ICCs and low DEFF? Also, does nonindependence mean that there is sufficient between group variation to say that the measure distinguishes among clusters? 


Q1: Not that I know of. Q2: With DEFF = V_C/V_SRS = 1+(s1)*rho, a high ICC (rho) and a low DEFF can happen for a low cluster size, say s = 2. Q3: A high ICC says that the measure has a relatively large variation across clusters, so yes, that can perhaps be seen as distinguishing between clusters. I think the important aspect is how different the SEs are when assuming independent clusters (Type=General) versus when allowing for cluster variation using Type=Twolevel or Type=Complex. 


Thanks so much, Dr. Muthen! 

Back to top 