AS 2.9 Inference Checklist
General introduction statement - what the report is about
- Variables defined with units
- Groups are defined.
- Population defined (and any assumptions)
- Formed a Comparative Research Question (Variable, groups, 'median', direction, population)
- A prediction is make: ‘I think that...’
- Reason why making your prediction: Why ‘I think that...’
Use iNZight to:
Take a random sample,
Analyse the sample
- Make a box & dot plot
- Display the informal confidence interval bars (save the display image)
Data / Display
- Did you have to ‘clean’ the data’ (discuss)
- Comment on the sampling method,
- Comment on the appropriateness of the sample size.
Analysis / Discussion
Discussion of the SAMPLE:
Sample statistics comparing two groups.
- Distribution (dot plots) of the two groups symmetry, skew, outliers, gaps, clusters
- Box plots (Initial interpretation, Shape, Centre (middle 50%), Unusual aspects, Spread, Shift / Overlap)
The discussion needs be in context at all levels.
Also consider possible reasons or causes of these features (in the context)
‘I notice ... I expected ... I was surprised that...’
Discussing of sampling variability, including the variability of estimates (ESSENTIAL for Achieve)
Informal Confidence Intervals
- Discussion of what each informal confidence interval means
- Discussion of informal confidence interval overlap / or not
(in context & referring back to the population and how sure you are)
'I can be reasonably sure that...'
- Answer your research question by referring to your graphs, analysis and informal confidence interval.
- Make a conclusion about the population medians based on their samples taken from the population.
- Discuss errors, bias, omissions, improvements, further research...
- Discuss sampling variability, including the variability of the population estimates.
- An understanding relating to sampling variability and variability of estimates must be evident.
- Discuss the effect of different sample sizes
- Be sure to be clear when you are discussing the sample and when you are discussing the population estimate.