Hello All,
I ran a mixed-effects model using country (50 countries) as a random intercept. The random intercept for country was statistically significant, and model fit improved significantly(as indicated by a lower -2 Log Likelihood).
The concern is 22 countries have only one respondent and 10 countries have 2 respondent, I was thinking to say: Even though the model looks better, but I will go with simple linear regression not mixed model due to sparse data (low sample size in lots of clusters)
As a note, I also grouped countries into 5 clusters to increase the sample size within each group. In this version, the random intercept was not significant, and the change in -2 Log Likelihood was not statistically meaningful.
Below is the frequency of each cluster/country:
country_1
1
country_2
1
country_3
1
country_4
24
country_5
1
country_6
2
country_7
1
country_8
5
country_9
22
country_10
2
country_11
1
country_12
1
country_13
20
country_14
12
country_15
1
country_16
1
country_17
1
country_18
1
country_19
1
country_20
2
country_21
2
country_22
1
country_23
2
country_24
1
country_25
6
country_26
1
country_27
3
country_28
4
country_29
32
country_30
5
country_31
1
country_32
6
country_33
15
country_34
10
country_35
1
country_36
1
country_37
18
country_38
2
country_39
3
country_40
2
country_41
1
country_42
3
country_43
6
country_44
8
country_45
1
country_46
2
country_47
2
country_48
7
country_49
6
country_50
18
country_51
5
country_52
1
country_53
1
country_54
9
country_55
3
total
290
Any input appreciated,
Thank you!
Bahar