Please enable JavaScript.
Coggle requires JavaScript to display documents.
Pre-lecture 1 (Correlation: relationship between variables, but does not…
Pre-lecture 1
Correlation: relationship between variables, but does not mean the an event is guaranteed of another event.
Causation: an effect is due to cause of another event.
-
Pre-intensive Leacture 2
1.1 Research: collection and analysis of information to increase understanding in an interested field.
1.2 Social Research: use of scientific approach to find explain social problems.
1.3 Research Process: use of data to explain research questions.
1.4 Scientific Process: systematic collection of methods to produce knowledge.
1.5 Forms of Social Research
- Pure research: research to develop general knowledge on human behaviour;
- Applied research: provide information and knowledge that can influence social policy;
1.6 Three components of research:
- Theory;
- Method;
- Epistemplogy: the study of the nature of knowledge, justification, and the rationality of belief;
-
-
-
1.10 Three Main Epistemological Perspectives
- Positivism:
- Phenomenology:
- Critical:
-
-
-
-
-
-
-
Pre-intensive Lecture 3
2.1 What do we strive for social science research?
- Regularity and generalisation;
- Reliability and replicability;
- Validity;
- Prognostication (预测) or prediction;
- Parsimony (简约);
2.2 Hypotheses: Dependent, Independent and Control Variables
- Dependent variable: is what you measure in an experiment, and affected during experiment.
- Independent variable: is the variable changed or controlled in experiment, in order to measure the effects on dependent variables.
- Control variable: is an element stays constant and unchanged in an experiment.
2.3 Falsifiability (可证伪性)
- If an hypothesis can be proved to be true or false. If it is not testable, then it is not scientific.
2.4 Hypothesis Testing: H0 and HA
- It is to use sample data to test an assumption of a population is equal or not equal to a number.
2.5 Errors: Type I and Type II
- Type I Error: reject H0 when H0 is true;
- Type II Error: not reject H0 when H0 is false;
2.4.1 Six Steps of Hypothesis Testing:
- Formulate H0 and HA.
- Determine test criteria.
- Collect data.
- Compute likelihood (p-value).
- Interprete findings and make decision.
- Quantify significant findings: power analysis, effect size and confidence intervals.
Pre-intensive Lecture 5
5.1 Central Tendency
- Mean: average value of a set of data. Sum of values for population divided by value;
- Median: middle value of a set of data ordered from highest to lowest;
- Mode: the most common value amongst a set of observations.
5.2 Dispersion
- Percentile: The value of a variable below whihch a certain per cent of observation fall.
- Inter-quantile range: the range between 25 % and 75 % (percentile):
- Standard deviation: the distance or dispersion between each sample value and sample mean.
5.3 In equality
- Inequality: disparities in the distribution of economic assets/income.
- Lorenz curve: horizontal = cumulative share of population from lowest to highest income; vertical = cumulative share of income earned
- Gini coefficient = ratio of area A over area (A+B)
5.4 Probability
- Probability: likelihood for an event to occur;
- Independent probability: probability of an event to occur that is independent of another event;
- Conditional probability: probability of an event to occur, given another event has occured.
5.5 Analysis
- Correlation: a measure of relationship between two variables.
- Dependent variable: is what get measured.
- Independent variable: is controlled and to measure the dependent variable.
- Regression: analysis of relationship between dependent and one or more independent variable.
- Multiple regress: regression analysis with more than one independent variable.
- Linear regression: there is a constant relationship between dependent and independent variable.
- Non-linear regression: 1) dependent variable is binary/categorical.
2) there is more complicated relationships between dependent and independent variable.
5.6 Inference
- Hypothesis test: a procedure to test if a null hypothesis should be accepted or rejected in favor of an alternate hypothesis.
- Statistical significance: a result has statistical significance when it is very unlikely to have occurred given the null hypothesis
-
Pre-intensive Lecture 4
4.1 Definition:
- Data: information usually numerical and collected through observation.
- Survey: investigation about of characteristics by collecting data through a given population.
- Variable: characteristic of a unit that can have more than one set of values.
- Parameter:
4.2 Dimension 1 - Coverage and Representativeness
- Population: the complete collection of unit that one is interested;
- Sample: a subset of population that is observed by data collectors;
- Sampling frame: the set of target population selected into survey sample;
- Probability sampling: each unit of population has a chance of being selected in the sample;
- Census: when the sample is the same as population;
4.3 Dimension 2 - Collection Methodology
- Primary data collection: face to face interview, focus groups, mail, telephone, online interview;
- Textual data;
- Administrative records;
4.5 Dimension 4: Repetition
- Cross-sectional survey: sample survey at one point in time only;
- Repeated cross-sectional survey: same question is asked more than once of the same population, but popuation is selected afresh each time;
- Longitudinal survey: a sample survey is vurved more than once through time;
- Quantitative and qualitative and admin data can be cross-sectional or longitudinal.
4.4 Dimension 3: Measurement
- Data type: binary, categorical, continous, count, duration.
- All of the above data types can be objective, subjective and attitudinal.
Pre-intensive Lecture 6
6.1 The Census - Scope and Methodology
- Scope: all people in Australia, excl. foreign diplomats and families;
Vistors counted but separately identified;
Residents outside not counted;
- Methodology: self enumerated; 43,000 census collectors; non-private dwellings...
6.2 The Census - From Count to Population Estimate
- Census counts differ from census year population estimates;
- Correlations also need to be made for partial response;
- Post-enumeration survey (PES) to calculate the net undercount;
6.3 From Census to Sample
- A breakthroughs in 20th century social science research is precise estimates from a fraction of a population;
- Make inference abou the population;
6.4 Key Cross-sectional Survey in Australia
- Labour force survey;
- Australian health survey;
- Australian early development census;
- Programme of international student assessment;
- Quality indicators for learnning and teaching
-
-
Pre-intensive Lecture 7
7.1 Longitudinal Surveys
- Individual, households, business, etc. surveyed more than once through time.
- Three types: 1. cohort studies, study a group experiencing same event in a selected time period. 2. panel studies, selected a representative sample of individuals at a time and following them through time. 3. Administralive collections, track individuals through time based on administrative data.
7.2 Household Income and Labour Dynamics in Australia (HILDA)
- Household-based panel study, collects information about economic and subjective well-being, labour market dynamics and family dynamics.
-
Pre-intensive Lecture 8
8.1 Longitudinal Surveys of Australian Youth (LSAY)
- Focuses on youth outcomes and transitions, following successive cohorts of 15 year olds.
8.2 Longitudinal Study of Australia Children (LSAC)
- Aims ot provide a database for a comprehensive understanding of children's development in Australia's current social, economic and cultural environment.
8.3 Longitudinal Study of Indigenous Children (LSIC)
- The LSIC is the first large-scale longitudinal survey in Australia to focus on the development of indigenous children