RESEACH DESIGNS
MODULE 3
INTRODUCTIONTO POPULATION
Upon completion of the Research Areas topic, you will
be able to:
• Understand representativeness, probability sampling and
sampling-error
❖ Population is the potential respondents of interest
oExample: adults aged 18 or above, resident in Manila
oExample: air temperatures at the FEU Institute Manila
❖ A sample is the respondents selected from population for
study
oExample: 500 mobile phone users in Manila, selected randomly
using their phone number
oExample: 1000 average daily ozone levels recorded
sequentially at the street level monitoring station in Recto station
❖ Units of analysis are usually the sampling elements, often
people or households (need to be clear which), but can be
rats, words, and songs – any countable objects (although
sometimes we can analyse at multiple levels, e.g. students
and schools).
❖ Representativeness is the extent to which sample that is
like the population on characteristics of interest for
research. This is essential if we wish to draw conclusions
about the population based on a sample.
❖ A probability sample is a sample where all sampling units
have a known non-zero probability of selection. Probability
samples are a requirement for all hypothesis testing and
statistical models. Below we discuss different mechanisms
of probability sample.
❖ A simple random sample means that all combinations of
sampling units with the specified sample size have an
equal chance of selection. This also means that all
sampling units have an equal chance of selection.
oA simple random sample of size 2 of students in a class with 10
students means that all 45 (10x9÷2) possible pairs are equally
likely to be selected.
❖ Cluster sampling means sampling at two or more levels
(e.g. school, class, student), usually require that each
individual has the same chance of selection overall.
oExample: a sample of 500 secondary students is hard to draw
without a list of all students.
❖ Stratified sampling means sampling within subgroups of
known size that are relatively homogenous, to yield more
precise results than a simple random sample.
oExample: Sample children separately in year groups because we usually
know the number of children in each year group and children within year
group are often quite homogeneous (as opposed to across year groups).
❖ When the population can be placed in an ordered list, a
systematic sample involves selecting a random start point
and then selecting every kth individual where k=population
size/sample size.
❖ Network sampling is a sampling strategy that draws a sample
through a random selection of links in a network.
❖ It makes assumptions about how people are linked in
networks, which may not be valid, but has the advantage of
sometimes being feasible when a simple random sample is
impossible.
❖ It is important as it yields representative samples of difficult to
sample populations, if the assumptions are valid.
❖ It is important as it yields representative samples of
difficult to sample populations, if the assumptions are valid.
oExample: it is very hard to sample drug addicts in general because
they are not all easily identifiable, but they are usually connected
in drug supply networks.
oA network sample can be drawn by asking an initial set of drug
addicts for introductions to their drug-using friends and then
asking a sample of those friends, etc.
❖ Distance sampling involves randomly placing points or
lines (transects) on a map and then measuring distances
to objects. There are two main approaches – point
transects and line transects.
oExamples would be estimating the number of people
marching along Lacson Avenue or the number of people in
Morayta (usually look at density in random sample of
small areas).
❖ Sampling errors relate to the use of a sample rather than
the whole population.
❖ Sampling errors relate to the use of a sample rather than
the whole population.
❖ The non-sampling errors include non-contacts, refusals,
misunderstandings, lies, mistakes, coding errors etc.
oExample: any household survey that fails to make
repeated (at least 5) attempts to contact households will
under-represent poor and single working households
(who are often out at work) and young households
without children (out at work or play).
oExample: a self-selected Internet survey omits most of the
population who are not interested in the topic, do not see
the survey or do not trust the website, so is likely to be of
very limited research value.
❖ Most interviews now use telephone or face-to-face. Telephone
loses visual contact, gains on lower cost, better supervision,
faster collection, ease of computer assistance (CATI stands for
Computer Aided Telephone Interviewing, which automates
question display, telephone number selection etc.).
❖ Mobiles provide an alternative to fixed lines as coverage of
fixed lines is starting to drop and be replaced by mobile.
❖ However mobile is linked to individuals, while fixed is
linked to households, so the sampling unit is different.
❖ Secondary data analysis means using data previously
collected.
❖ Data collection is very expensive and usually not
repeatable for social science data, so use of previously
collected data or materials is a good idea, if feasible (e.g.
use data archive).
❖ When choosing the sample size for a study, we need to
consider sampling error, non-sampling error and power.
❖ The dividing line is sometimes not clear, but one distinction
sometimes made is the type of data collected - directly
measurable (quantitative) vs. recordable (text, audio, video
etc.) (qualitative).
Journals:
EBSCO
IntechOpen
IntechOpen website link: [Link]
Taylor and Francis
T&F website link: [Link]/
Springer
Springer website link: [Link]/SpringerCS
JSTOR
JSTOR website link: [Link]
Books:
• Forsyth, D. (2018). Probability and Statistics for Computer Science. IL, USA: Springer.
• Frank E. Harrell, J. (2015). Regression Modeling Strategies. Switzerland: Springer
International Publishing
• Gorvine, B. (2018). Research methods. Oxford University Press.
• Grigoryev, I. (2017). AnyLogic 7 in three days a quick coursein simulation modeling.
• McCroskey, J. (2016). Quantitative research methods for communication. OXFORD
university Press.
• Matera, M. (2015). Explore like a pirare : gamification and game inspired course design
to engage, enrich and elevate your learners. Dave BurgessConsulting, Inc.
• Pajo, B. (2018). Introduction to research methods. Sage Publising.
• Viswanathan, M. (2019). Digital modulations using Matlab : build simulation models from
scratch.
External Resources:
• [Link] (CANVAS)
• Bacon-Shone, J. (2015). Introduction to Quantitative Research Method. Hong Kong: Research Gate
• Nathan, Peter (2013). The Oxford Handbook of Quantitative Methods Vol 2: Oxford University Press.
• Teo, Timothy (2013). Handbook on Quantitative Methods for Educational Research: Sense Publisher.
• Zeigler, Bernard P. et al. (2019). Theory of Modeling and Simulation 3 ed.: Academic Press.
• Arias-Rodil, M., Diéguez-Aranda, U., & Burkhart, H. E. (2017). Effects of Measurement Error in Total Tree Height and Upper-
Stem Diameter on Stem Volume Prediction. Copyright Society of American Foresters Jun 2017, 250-260.
• Domanski, C., & Jedrzjezak, A. (2015). Statistical Computing in Information Society. Folia Oeconomica Stetiensia, 144-152.
• Ibrahim, K. (2019). Foreign language practice in simulation video games: An analysis of game-based FL use
dynamics. American Council on the Teaching of Foreign Languages, 335-357.
• Kirkpatrick, E., Gaisford, W., Williams, E., Brindley, E., Tembo, D., & Wright, D. (2017). Understanding Plain English summaries.
A comparison of two approaches to improve the quality of Plain English summaries in research reports. Research Involvement
and Engagement , 1-14.
• Sato, K. (2004). Perspective of Research Design in Design. Visible Language, 218.
• Shu, K., Kozak, M., Fradj, N. B., Zylowski, T., & Rozakis, S. (2020). Simulation of sorghum introduction and its impacts on land
use change—A case study on Lubelski region of Eastern Poland. John Wiley & Sons, Inc., 252-274.
• Trochim, P. M. (2020, March 10). Retrieved from Research Method Knowledge Base: [Link]
sample/paper/
• University of Minnesota. (2020, April 20). Driven to Discover. Retrieved from Heart Attack Prevention:
[Link]