Professional Documents
Culture Documents
Course Coordinator
Professor Ann Williamson
School of Aviation
Tel: (02) 9385 4599
Mob: 0414 772 114
a.williamson@unsw.edu.au
Room #215 Old Main Building
Week 6
Week 6
Ann Banks
Undergraduate Studies
School of Aviation
Week 6
AVIA3710 Reminder
How are you going with the Research Proposal?
Remember Assignment is due before:
23:59hrs Friday 23rd September (Wk 9)!!
MUST submit assignment via Printed hard copy (to me in
class or the Aviation office on that day) AND Moodle
or will not be accepted.
If you cant bring hard copy on that day:
Submit it earlier OR get someone to bring it for you.
Week 6
Week 6
In Week 5 we covered.
Select a method of data collection
Differentiate primary and secondary data and sources
Describe the characteristics of questionnaires,
interviews and observation
Evaluate the advantages and disadvantages of
questionnaires, interviews and observation
Understand the considerations to be made when
developing a research instrument and collecting data
using the instrument
Any questions?
Week 6
Week 6
Week 6
Population Studies
Population studies - obtain relevant information from
the entire population eg academics, voters, pilots,
drivers, census..
In most cases its impossible to test/survey/interview
entire population
Advantages
Accurate information
Detailed information
Minimisation of errors
Disadvantages
Time consuming
Resource intensive
Kumar, 2014
Sampling Studies
Sampling studies obtains information about a population
based on a small sample of the population
Achieved by inferring characteristics of sample on entire
population
Advantages
saves time
saves money
Disadvantages
Can only estimate or predict information about the
population (eg average hrs of sleep of UNSW academics)
potential errors you only end up with an estimate of the
information you want
potentially miss information about population characteristics
Kumar, 2014
Study
population
Sample
Week 6
Week 6
Principles of Sampling
Principle 1
sampling error is the difference between the sample statistic
and the true population mean (attributable to success (or not)
of selection of sampling units)
Principle 2
the greater the sample size, the more accurate will be the
estimate of the true population mean
Principle 3
the greater the difference in the variable under study in a
population for a given sample size (the range), the greater will
be the difference between the sample statistics and the true
population mean
(Kumar, 2014)
Population Mean
(2)
1 (A+B)
19.0
21.5
-2.5
2 (A+C)
20.5
21.5
-1.5
3 (A+D)
21.5
21.5
0.0
4 (B+C)
21.5
21.5
0.0
5 (B+D)
22.5
21.5
1.0
6 (C+D)
24.0
21.5
2.5
Sample
Sampling Error
= Difference
between (1) &
(2)
Sample
Average (1)
Population
Mean (2)
Sampling error =
Difference
between (1) & (2)
20.33
21.5
-1.17
21.0
21.5
-0.5
22.0
21.5
0.5
22.67
21.5
1.17
Week 6
Selecting a Sample
The aim in selecting a sample is to:
achieve maximum accuracy or precision in your
estimate,
avoid bias in the selection of your sample
Kumar, 2014
Principle 2
the greater the sample size, the more accurate will be the
estimate of the true population mean
Principle 3
the greater the difference in the variable under study in a
population for a given sample size, the greater will be the
difference between the sample statistics and the true
population mean
(Kumar, 2014)
Week 6
Non-random
you target participants with the particular characteristics you
are interested in
sample is biased
cannot infer findings from the sample to the population
Kumar, 2014
Week 6
Week 6
Week 6
Week 6
Non-Random Sampling
Quota sampling eg want to select a sample of males to
find out which brand of cigarettes they smoke, and why.
Stand by supermarket entrance, and ask each male who
enters.
Accidental sampling you want the same information,
but you sample any males who happen to walk past you,
anywhere.
Judgemental sampling you want the same information,
but you go to people who in your opinion are likely to
have the required information eg people you see
smoking
Non-Random Sampling
Expert sampling you sample people with known
expertise in an area of interest to you. Eg A380 captains.
Snowball sampling you ask some of the males you
sampled to nominate friends of theirs who smoke that
can become part of your sample.
Kumar, 2011
Sample Size
How big should a sample be?
Generally, the larger the sample size, the more accurate
are your estimates for the population
For qualitative research, sample size is less important than
for quantitative research
For qualitative research (eg using focus groups) you
collect data until you think you are not getting much new
data from your participants. 6 partcipants might be
enough.
For quantitative research, especially cause-and-effect
studies (ie experiments), calculating the sample size
needed for your research is critical to ensure your sample
is representative of the population you are attempting to
study
Week 6
Week 6
Week 6
Ethics
All professions are guided by a Code of Ethics
Many research bodies have evolved a Code of Ethics
separately to govern the way they carry out research.
Eg medicine, psychology, education, business, etc
Definition: in accordance with principles of conduct
that are considered correct, especially those of a
given profession or group (Collins Dictionary 1979, p.
502; cited in Kumar, 2014).
Week 6
Week 6
Week 6