Readings
The study guide I have was prepared in Feb 2010. It may very well be the first version of the text, as there are no acknowledgements to other contributors / authors or to earlier versions. I'm surprised the primary reference and supplementary readings are so old:
- Primary reference 2002
- Supplementary readings
o 1989
o 2003
o 1993
o 1985
o 1979
o 1998
o 1993
The most recent book is from 2003 – 7 years old. Surely technological development and resulting methodological advancement means that survey design has changed considerably.
Exam
Is the exam open book?
When will second module be available.
Australian Social Science Data Archive website
Fee of $1,000 per data set applies.
VicRoads
http://www.vicroads.vic.gov.au/Home/SearchResults/default.aspx?qt=statistics
Databases
- What's the difference between online database and online journal access (Swin Library website)
- Why no subject guide for Applied Statistics
Statistics Databases
http://www.swinburne.edu.au/lib/database/abs.htm
Online Journals
Too many to go through
See following list of statistics journals
http://www.statsci.org/journals.html
http://www.stata.com/links/journals4.html
http://www.inrialpes.fr/is2/pub/liens-an.html
http://en.wikipedia.org/wiki/List_of_statistics_journals
Which journals are available full text via Swinburne.
Also, many subject specific journals have articles about statistical methodology, etc.
Reading: De Vaus, p 25 – 30: Using the Internet to Review Existing Information and Research
- Seven main ways of obtaining information to assist in reviewing a research field
o Information freely available
§ Search engines
§ Follow links
§ Use gateways
o Free access to online catalogues
o Free access to publications and full text articles
o Restricted access to resources such as online publications
o Restricted access to lists of articles in academic journals
§ Notification services
· Now done via RSS
o Restricted access to searchable database
o Newsgroups, listservs and chatgroups
§ Are these used nowadays
§ Social media: eg twitter / blogs
· http://www.researchrockstar.com/free-market-research-training-twitterversity-results/
· See separate list of statistics and market research blogs
http://statisticsandastudent.blogspot.com/2011/02/statistics-and-market-research-blogs.html
Real World Example
De Vaus, D. and McAllister, I (1987) ' Gender Differences in Religion: A Test of Structural Location Theory' American Sociological Review 52: 472-81
Google scholar search:
137 citations
See Web of Knowledge to list citations.
Copy of original article saved.
Reading: Evaluating Indicators : p52 – 55
- Develop indicators à have to make sure they measure the concept we thaink they are measuring à validity
- Consistent responses à Reliable
- Pilot testing
- Reliability
o Obtain same result on repeated occasions
o Sources of unreliability
§ Question may be badly worded
§ Characteristics of interviewer
§ Coding
o Testing reliability
§ Scales
§ Test / re test
· Confounding – memory
§ What does inconsistency of measures really mean
· Unreliable test measure
· Change in attitudes
· Unstable attitude
o Increasing reliability
§ Use multiple item indicators
§ Likert scales
§ Careful wording
§ Interviewer training
§ Clear coding methods
§ Don't ask questions on which respondents unlikely to have a view
§ Provide don't know / cannot decide options
- Validity
o Measures what it is intended to measure
o Use to which measure put to makes it valid / invalid
o Criterion validity
§ Compare how people answer our new measure of a concept with exiting well accepted measures of the concept.
· Assumes validity of existing measure
· No well established measure to compare against
o Content validity
§ Extent to which indicator measures the different aspects of content
o Construct validity
o How well measure conforms with theoretical expectations
- Problem of meaning
o Interpreting meaning of people's responses
o Help to make intelligent interpretations of patterns in data
§ Variety of methods of data collection
· Observation & in depth interviewing
- Developing indicators – a checklist.
- Translation of concept into indicator
Exercises from De Vaus: Chapter 4
Question Bank
http://surveynet.ac.uk/sqb/introduction.asp
http://webapps.ropercenter.uconn.edu/CFIDE/cf/action/home/index.cfm?CFID=1224444&CFTOKEN=82785847
http://www.icpsr.umich.edu/icpsrweb/ICPSR/index.jsp
http://hdr.undp.org/en/ (changed url
The education component of the HDI is now measured by mean of years of schooling for adults aged 25 years and expected years of schooling for children of school going age. Mean years of schooling is estimated based on duration of schooling at each level of education (for details see Barro and Lee, 2010). Expected years of schooling estimates are based on enrolment by age at all levels of education and population of official school age for each level of education. The indicators are normalized using a minimum value of zero and maximum values are set to the actual observed maximum values of the indicators from the countries in the time series, that is, 1980–2010. The education index is the geometric of two indices.
The life expectancy at birth component of the HDI is calculated using a minimum value of 20 years and maximum value of 83.2 years. These are the observed maximum value of the indicators from the countries in the time series, 1980–2010. Thus, the longevity component for a country where life expectancy birth is 55 years would be 0.554.
For the wealth component, the goalpost for minimum income is $163 (PPP) and the maximum is $108,211 (PPP), both observed minimum observed during the same time series.
The decent standard of living component is measured by GNI per capita (PPP US$) instead of GDP per capita (PPP US$) The HDI uses the logarithm of income, to reflect the diminishing importance of income with increasing GNI. The scores for the three HDI dimension indices are then aggregated into a composite index using geometric mean. Refer to the Human Development Report 2010 
Technical notes [388 KB] for more details.
The HDI facilitates instructive comparisons of the experiences within and between different countries.
)
Australian Market Research Society
http://www.mrsa.com.au/index.cfm
What Is Qualitative Research
De Vaus p 5 – 7
- Participant observation
- Unstructured interviewing
- Case studies
- Focus groups
- Rich data about real life people à stereotype
- Distinguish between 2 stages of research process
o Collecting data
§ Structured vs un structured data sets
o Analyzing data
§ Logic of analysis
· Variations in one variable matched with variations in another variable
· Co variation
- Survey research
- Research question
o Case study
o Survey
o experiment
No comments:
Post a Comment