There are three main sources of statistical data

There are three main sources of statistical data. These include:

a) Statistical surveys

Statistical survey is an investigation about the characteristic of phenomenon by means of collecting data from a sample of the population and estimating their characteristics through systematic use of statistical methodology. Survey mainly uses interview to collect data; this can either be direct interview, telephone interview, email interview or online survey.

Surveys are advantageous source of data as the researcher has direct control over the data and there is possibility of asking data according to statistical definitions during the collection.

The disadvantages of surveys are high cost, especially in conducting direct interviews. Quality of the feedback can also be compromised, for instance, non-response and errors.

b) Census

This is a complete enumeration of a population at a point in time with respect to well-defined characteristics, for example, population, production, etc. For instance, Kenya has been taking census from 1948, when the first census was taken. The last four censuses after the independence (1969, 1979, 1999 and 2009) have been conducted in a span of ten years.

In census, the data is mostly collected through questionnaires.

Census provides better data compared to surveys as it target the entire population of either a country or region. It also provides a basis for sampling frames which may be used in subsequent surveys. On the other hand, it is expensive to plan, conduct and to process the resulting data.

c) Registers

Register is a database that is updated continuously for a specific purpose and from which statistics can be collected and produced. Examples include: administrative registers (e.g. government departments), private registers (such as those from insurance companies among other private entities).

Registers as a source of statistical data has the cost advantage, that is, there is low cost in collecting and processing the data from this source. However, possible under-coverage in terms of information may render it disadvantages to some users.