Hello, I found that the 1950 Full Count Census data has missing values in several variables for too many observations, such as wkswok (weeks worked last year) and incwage (wage and salary income).
For example, more than 90% of observations in 1950 only had a missing value for the variable “wkswork2”.
Since the 1950 Full Count Census data is just a preliminary release, are you going to fix it in the future? Do you have an estimated date of when to fix it?
Also, is it reasonable to say that observations had the missing value or valid values randomly? In other words, we can still use observations with valid values to conduct analyses.
The 1950 full count release is a preliminary release; there are a number of known issues and limitations of the data. IPUMS continues to work with Ancestry to refine these data, identify and remove duplicate records, and fix transcription errors. Users should consider the status of this work while using these data, and be cognizant that this is a preliminary release only. We are uncertain of the exact timing of the next release; we expect to have more details on the timing and contents in January 2025.
Specifically addressing the variable WKSWORK1, the universe of the variable in the 1950 full count data is sample-line persons age 14+ who worked last year. Many census questions in 1950 were asked only of sample-line persons: every fifth person on the census form (20% of the population). Sample-line persons are identified in SLREC. The restriction of the universe to sample-line persons explains the large share of missing values you see.
Please submit any feedback you have about the 1950 full count data using this form, which is monitored by the historical data team (and continue to reach out via the user forum or email at ipums@umn.edu with questions).
As you can see in the universe section of INCWAGE, the universe in the 1950 full count is sample-line persons age 14+; all persons age 14+ in Alaska. All variables’ universes are listed in their universe tab once you click on the variable.