This information is for reference purposes only. It was current when produced and may now be outdated. Archive material is no longer maintained, and some links may not work. Persons with disabilities having difficulty accessing this information should contact us at: https://info.ahrq.gov. Let us know the nature of the problem, the Web address of what you want, and your contact information.
Please go to www.ahrq.gov for current information.
Table 3: Imputations and Coding for Modeling
Variable
|
Imputation of Missing Data
|
Coding of Variable for Modeling Purposes
|
All continuous variables (age, BMI, length of procedure, uterine volume,
fibroid size)
|
Imputed as medians of the variable
|
Value of the variable itself
|
|
|
Number of fibroids
|
Imputed to 5
|
Value of the variable itself
|
Race
|
Imputed as Caucasian/other
|
2 groups for race: Caucasians or others vs. African Americans (reference group)
|
History of pregnancy
|
Used data from variables—gravida, para, spontaneous abortion, ectopic—to
define variable. If still missing imputed to "nulligravid"
|
Nulliparous or nulligravid vs. parous
|
Smoking
|
Imputed as "non smoker"
|
|
Previous procedures
|
Imputed to "none"
|
Any vs. none (ref.)
|
Previous medical therapy
|
Imputed to "none"
|
Any vs. none (ref.)
|
Fibroid morphology
|
Lumped missing with subserosal & intra/trans mural
|
Submucosal vs. others (ref.)
|
Symptoms
|
Missing lumped with other symptoms
|
Heavy bleeding, pelvic pain, bulk vs. others (ref)
|
DVT prop.
|
Imputed to "no"
|
yes vs. no (ref)
|
Prophylactic antibiotics
|
Imputed to "no"
|
yes vs. no (ref)
|
Vessel embolized
|
Excluded patients missing or with no vessel embolized
|
UA bilateral vs. UA single (ref.)
|
Core site
|
No requirement
|
yes vs. no (ref)
|
Practice type
|
No requirement
|
academic vs. other (ref)
|
Site experience
|
Initial no. of cases imputed as 0
|
|
Return to Document