For a majority of items, nonresponses and Inconsistencies were eliminated by using the computer to assign entries and correct inconsistencies. In general, few assignments or corrections were required, although the amount varied by subject and by enumerator.
The assignment of an acceptable entry by machine was based on related information reported for the person or on information reported for a similar person in the immediate neighborhood. For example, in the assignment of age in the complete-count tabulations, the computer stored reported ages of persons by sex, color or race, household relationship, and marital status; each stored age was retained in the computer only until a succeeding person having the same characteristics and having age reported was processed through the computer; this stored age was assigned to the next person whose age was unknown and who otherwise had the same characteristics. This procedure insured that the distribution of ages assigned by the computer for persons of a given set of characteristics would correspond closely to the reported age distribution of such persons as obtained in the current census.
Specific tolerances were established for the number of computer allocations acceptable for a given area. If the number was beyond tolerance, the data were rejected and the original schedules were reexamined to determine the source of the error. Correction and reprocessing were undertaken as necessary and feasible.
Marital Status and Whether Married More Than Once
The computer Editing and allocation procedure for marital status from the sample FOSDIC schedule was designed so that the sample marital status entry would be consistent with the entries for whether married more than once, date of first marriage, and detailed family status. Household heads with wives present and wives of household head were treated as married regardless of their original entries. Similarly, if the head or the wife of a husband-wife subfamily or of a husband-wife secondary family was reported in a marital status category other than married, the computer changed the classification to married. Heads of a parent-child subfamily or of a parent-child secondary family with a blank in marital status were edited as separated. If the marital status of a child-in-law, parent, or parent-in-law was reported as never married, this entry was changed to a blank (and then a code was assigned from the matrix described below).
After these edits were performed, all remaining persons with blanks in marital status were assigned a marital status from values stored in a 64-cell matrix in which the variables were type of living quarters, relationship to head of household, presence of children (for household heads only), sex, evidence that the person had ever married (defined as an entry in either of the questions on whether married more than once or date of first marriage, or a relationship entry of child-in-law, parent, or parent-in-law), and age (only for those persons with evidence of ever having married). The Editing and allocation of the sample data on marital status occurred after the Editing and allocation of type of living quarters, relationship, and sex, and before the Editing and allocation of color, age, and all items collected on a sample basis only.
The data on whether married more than once were transferred from the microfilmed stage II FOSDIC schedule to the computer tape without prior manual Editing. No manual coding was necessary because the item was precoded on the schedules. A computer edit was used to eliminate inconsistencies and to allocate blanks. Blanks on whether married more than once were allocated as follows. If the person was married, spouse present, and the person's date of first marriage was the same as or later than that of the spouse, the person was recorded as married once. If the person was married, spouse present, and the person's date of first marriage was earlier than that of the spouse the person was coded as married more than once. For all other persons, blanks for whether married more than once were allocated from the value stored in a 28-cell matrix in which the variables were age, sex, and color.
The extent of allocation for nonresponse on marital status is described in the section, on "Quality of the Data," above. Certain types of response assignment (or allocation), however, are not shown in these tables. The following are the chief examples for marital status: Allocations of marital status and sex were automatically made for persons identified as wives of household heads or as heads of households with wife present; all persons coded as wives were automatically classified as female and married, and all heads with wife present as male and married. These automatic classifications occurred regardless of the original entries in sex or marital status, and assignments in sex or marital status resulting from these allocations were not recorded. Furthermore, the data shown above on allocations for nonresponse do not include the 0.2 percent of the population for whom data were replicated because there were no sample data for them; for these persons, the characteristics shown are those for persons in the substitute households.