BUSS1020 Flashcards
DCOVA
Define problem Collect required data Organise data Visualise data Analyse data
Three branches of Stats
- Descriptive
- Predictive
- Inferential
Descriptive Stats
Collecting (surveys), summarizing (means), presenting (graphs) and organising data
Predictive Stats
Using a model and data to make forecasts of outcomes
Inferential Stats
Estimation and hypothesis based on a small group
Categorical Variables (qualitative)
- Nominal e.g. car colours (red, blue black)
2. Ordinal e.g. shirt sizes (small, medium, large)
Numerical Variables (quantitative)
- Discrete - counting process (e.g. Number of Children)
2. Continuous - measuring process (e.g. cost)
Levels of data measurement
- Nominal (data cannot be agreed on order)
- Ordinal ( has an agreed progression but gaps are not equal)
- Interval (numerical data where differences between values are consistent and no meaning of zero e.g. temp)
- Ratio (zero has a true meaning, e.g. height, weight)
Non- probability Sampling
- Convenience Sample
- Judgement Sample
- Self selected
- Quota Sample
Probability Sampling
- simple random sample
- Systematic
- Stratified
- Cluster
Advantage and Disadvantage of SRS and Systematic Sampling
+ simple, cheap to use, effective against bias
- not great representation
Advantage and Disadvantage of Stratified Sampling
+ ensures representation of individuals across entire population
- Costly
Advantage and Disadvantage of Cluster Sampling
+ Cost effective
- less efficient, does not have perfectly represented clusters
Four types of Survey errors
- Coverage error (exclusion of groups)
- Non-response error (people who chose not to respond may respond different).
- Sampling error (variation from sample to sample)
- Measurement error (weakness in question design).
Four components of Time series trends
- Trend
- Seasonal Variation
- Cyclical Variation
- Random Variation
