New answers tagged survey
2
votes
Different AIC in R survey package vs. R stats package
You should not use $aic -- as @BenBolker says, you shouldn't even know it's there. It's a byproduct of using glm to fit the ...
- 43.8k
5
votes
Accepted
Different AIC in R survey package vs. R stats package
The short answer is that you should always* use accessor methods such as AIC() rather than extracting elements from objects using ...
- 45.3k
4
votes
Accepted
Can regression coefficients be bootstrapped when sampling weights must be used?
Short Answer
The standard approach is to create bootstrap replicate samples for your data, using a bootstrap method appropriate to your survey design. Then you estimate the coefficients separately ...
- 506
0
votes
Mixed model vs. imputation for questionnaire scale score?
Assuming that imputation is performed well, you are better off performing imputation. Thus, you will not have to drop either the samples with any missing values, or the features (ie question answers) ...
- 233
Top 50 recent answers are included