Statistical processing

Source data

The primary source to produce the The Attainment Register is the Student Register. The Student Register is supplemented with additional data from Statistics Denmark's Qualification Register that collects data from multiple sources of different nature.

When the Attainment Register is produced, the source of the information is taken into account and categorized according to how reliable the information is assumed to be, and given a priority (1 to 4). Information coming from the source of highest priority will always be used in the attainment register, even if there is information about a higher qualification coming from a source of lower priority.

Sources with priority 1:

• Examinations achieved through adult education (HF_KILDE = 1) Qualification from the adult education system are updated annually.

• IDA Engineering association (HF_KILDE = 5) Statistics Denmark received in 2005 the members of the engineering association.

• Ministry of Health (HF_KILDE = 8) Since 1980, The Authorisation Register from Sundhedsdatastyrelsen have been used as a source to The Attainment Register.

• Danish Agency for International Education (HF_KILDE = 11) Since 2007 Statistic Denmark have received information about education that has been assessed by the Agency for international Education.

• Educational Information from Greenland (HF_KILDE = 12) Once a year, Statistic Denmark receive information about people who have completed a education and received grants from Greenland under their education. The information from Greenland is not ready for the last year when the register of highest completed education is formed and the information from this source is therefore missing in the last year.

• Maritime Agency (HF_KILDE = 13) In 2010 Statistic Denmark received information from the Maritime Agency's administrative system about completed maritime education.

• Ph.d. (HF_KILDE = 14) Statistics Denmark's Ph.D. register contains information about the admission course to the PhD. education. The information from Greenland is not ready for the past year when the register of highest completed education is formed and the information from this source is therefore missing in the past year.

• The Student Register (HF_KILDE = 15)

Sources with priority 2:

• Population & Housing Census 1970 (HF_KILDE = 2). Population & Housing Census 1970 consist of self reported education information and the quality is considered to by less good. The date of completion on the educations from the Population & Housing Census 1970 is all set to 1-1-1970.

• Immigrants education (IVU) (HF_KILDE = 3, 17) Self reported education information for people who have immigrated to Denmark before 2007 have source = 3, from 2007. The completion date is set to the date of first immigration to Denmark (added 1-1-1600 if date is missing).

Sources with priority 3: - The admission education (HF_KILDE = 19) People that Statistics Denmark don't have a educational information about that have immigrated to Denmark and subsequently have started on a education in the student register, receive the admission education for this education, as their highest completed education.

Sources with priority 4: - Immigrants education (IVU) (HF_KILDE = 9, 18) Information on immigrants' education is imputed when it hasn't been possible to obtain educational information in another way Imputed values is information that replace unstated values based on experience from similar people. . The imputed data is useful in overall statistical statements, but cannot be considered as valid information on individuals' educational attainment. The imputed educational information from immigrants is coded with broad educational codes, ie codes that simply indicate a certain level of education

The completion date is set to the date of first immigration to Denmark (added 1-1-1600 if date is missing).

With the inclusion of new sources, the highest level of completed education is also influenced back in time, depending on how far back the new data covers. This is important when compared to older versions of the attainment register (PSD_HFUDD) and causes data breaches in the status register (PSD_Udd_STATUS), which are not changed in previous years' versions.

When the register of highest completed education is updated, there are two sources that are not ready with data for the last year, Ph.D. (HF_KILDE = 14) and Greenland (HF_KILDE = 12). Information from these two sources is therefore not included in the last year of the register.

Frequency of data collection

The register is based on information that are gathered once a year.

Data collection

The register is based on information from Statistic Denmark's two register, The Student Register and The Qualification Register

Data validation

Data editing is minimal since the register is based on information from other registries, that already has been true a comprehensive error control.

There is a check fore: - The development of the main groups for the highest attainted education over time. - The development of the use of sources over time.

• if there is a record that is temporarily followed by a new record with lower priority.
• if there are two records with the same priority, where the temporal first record has a higher level than the next record.
• if there are two records with the same priority and the same main group level, where the temporal first record has a higher PRIA than the next record.
• if there are two records with the same AUDD, where the temporary first record has the student register as source and the next not have the student register as source.

Data compilation

Based on The Student Register and The Qualification Register, an assessment is made of each person's educational career in order to determine the person's highest completed education.

Higher education is chosen according to the following principle: 1. Highest priority 2. If there are several AUDD here, highest main group, with main groups 20 and 35 being equated 3. If there are several AUDD here, highest PRIA 4. If there are several AUDD here, the recently completed. 5. If there are 2 records with the same AUDD, the register is only updated if no HF_KILDE = 15 already exists.

When the register of highest completed education is produced, only completed qualifying courses are included with KOMP = 1 (qualifying general education), 3 (vocational qualifying education) or 7 (secondary education in higher education). The exception to this is education / grade level at the primary school level, where completed grades from grade 6 and up are all included regardless of the value of the variable KOMP and AUDD = 0001, which means that you have never gone to school.

Similarly, a dataset with the highest completed general education (main areas 10, 20 and 35) and a dataset with the highest completed professional qualifying education (main areas 30, 40, 50, 60, 70 and 80) i produced.

Finally, a data set with the latest competency-giving education that a person has completed at a given time is produced. Latest completed education is chosen according to the following principle:

1. Recent completed education.
2. If two completed education have the same time of departure, the first priority sources are selected
3. If two completed education have the same departure time and the same source priority, the highest DISCED level is selected.
4. If two completed education have the same departure time, same source priority and same DISCED level, the highest PRIA is selected.

Adjustment

There is no correction of the data beyond what has already been described under data validation and data processing.