CH 8
CH 8
• Survey secondary data refers to existing data originally collected for some other purpose using a survey
strategy, usually questionnaires.
• They are made available either as compiled data tables or, increasingly frequently, in structured form as a
downloadable matrix of data.
• Survey secondary data may be available in sufficient detail to provide the main data set from which to answer
your research question(s) and to meet your objectives. They may be the only way in which you can obtain the
required data.
• Censuses are usually carried out by governments and are unique because, unlike other surveys,
participation is obligatory, They include censuses of populations
• they are usually clearly defined, well documented and of a high quality. Such data are easily
accessible in compiled form, are available via the Internet and are widely used by other organisations
and individual researchers.
• Continuous and regular surveys are those, excluding censuses, which are repeated over time as
repeated at regular intervals,
• Such as the UK’s Living Costs and Food Survey, although access to these data is limited by European
and individual countries.
• Non-governmental bodies also carry out regular surveys. These include general-purpose market
research surveys, Because of the commercial nature of such market research surveys, the data are
likely to be costly to obtain.
• Many large organisations also undertake regular surveys, a common example being the employee
attitude survey. However, because of the sensitive nature of such information, it is often difficult to
gain access to such survey data, especially in its raw form.
• Ad hoc surveys are usually one-off surveys and are far more specific in their subject matter.
• They include data from questionnaires that have been undertaken by independent researchers as
well as interviews undertaken by organisations and governments.
• Because of their ad hoc nature, you will probably find it more difficult to discover relevant
surveys.
• you may be able to gain access to and use raw data from an ad hoc survey that has been deposited
in a data archive .
DOCUMENT SECONDARY DATA
• Document secondary data are defined as data that, unlike the spoken word, endure physically
(including digitally) as evidence, allowing data to be transposed across both time and space and
reanalysed for a purpose different to that for which they were originally collected.
• For your research project, the document sources you have available can depend on whether you
have been granted access to an organisation’s records as well as on your success in locating data
archives, and other Internet, commercial and library sources.
• Text media include notices, correspondence (including emails), minutes of meetings, reports to
shareholders, diaries, transcripts of speeches and conversations, administrative and public records
as well as text of web pages.
• Text media can also include books, journal and magazine articles and newspapers.
• Audio media, such as archived recordings of radio programmes, speeches, audio blogs and
podcasts.
• Can be analysed both quantitatively and qualitatively by transcribing the spoken words and
treating them as text.
• Business and management researchers are making greater use of visual and to a lesser extent audio documents
as data. Much of these are web-based materials generated by organisations and online communities.
MULTIPLE-SOURCE SECONDARY DATA
• Multiple-source secondary data can be compiled entirely from document or survey secondary data,
or can be an amalgam of the two.
• It can include data that are being added to continually such as records of transactions, as well as
data that are added to less frequently on an ad-hoc basis or collected only once.
• often for a specified date to provide a ‘snapshot’. Other multiple-source secondary data snapshots
include the various share price listings for different stock markets reported in the financial pages
of quality newspapers.
• One method of compilation is for you to extract and combine one or more comparable variables
from a number of surveys or from the same snapshot survey that has been repeated over time to
provide longitudinal data, in which you will be able to obtain data over a long period.
Evaluating secondary data sources
Secondary sources may not always be suitable for your research question or
objectives, so it is crucial to evaluate their suitability. Researchers can save time
by rejecting unsuitable data earlier, especially when there are multiple possible
secondary data sources.
Validity and reliability criteria can be used to evaluate potential secondary data,
which can be incorporated into a three-stage process. However, this process is
not always straightforward, as sources may not always contain all the necessary
information
Evaluating secondary data sources
Measurement validity is a crucial factor in determining the suitability of any data set.
Secondary data that fails to provide the necessary information for research questions or
objectives can result in invalid answers
For instance, a manufacturing organization may record monthly sales instead of orders,
making the measure invalid. This can cause issues when analyzing relationships between
sales and orders.
There are no clear solutions to measurement invalidity problems. To evaluate the validity
of data, one can examine how other researchers have dealt with this issue in a similar
context. If they found the measures suitable, it can be more certain that the data will be
suitable for the research questions and objectives. If they had problems, they can provide
suggestions on how to overcome them.
Evaluating secondary data sources
The other important overall suitability criterion is coverage. You need to be sure
that the secondary data cover the population about which you need data, for the
time period you need, and contain data variables that will enable you to answer
your research questions and to meet your objectives. For all secondary data sets
coverage will be concerned with two issues:
•ensuring that unwanted data are or can be excluded
•ensuring that sufficient data remain for analyses to be undertaken once
unwanted data have been excluded.
Evaluating secondary data sources
When analyzing secondary survey data, you will need to exclude those data that
are not relevant to your research questions or objectives. Service companies, for
example, need to be excluded if you are concerned only with manufacturing
companies.
For document sources, you will need to ensure that the data contained in them
relate to the population identified in your research. For example, check that the
social media content on an organization's social media pages actually relate to
the organization. Where you are intending to undertake a longitudinal study, you
also need to ensure that the data are available for the entire period in which you
are interested.
Assessing Reliability and Validity of
Secondary Data