Used Augmented Reality (AR) to make an engaging video to introduce sampling from a seven hundred Kiwi Population. This is the starting point of Statistical Inference. Particular Kiwi selected is shown with its related variables e.g species, gender, height and weight. Thus we may begin our discussion of context and variables for this topic. In this video various issues with this internal assessment are highlighted. The Island Project is briefly introduced to demonstrate some ethical and other issues associated with the surveys and questionnaires.
This is the presentation prepared for the HOD Day_2017.
Discussions and resources will be on Level 3 Statistical Inference topic.
My intention is to discuss:
The framework for thinking about informal statistical inference with the main emphasis on three layered assessment structure. Time permits, I will discuss how Google Classroom, Doctopus and Goobric can be integrated to facilitate the teaching/learning and assessment processes.
In the presentation, I will use video, Peardeck (a presentation tool) and other electronic files. All files will be shared. Therefore, note taking is not required.
The video shows how to create a Google Sheet as a grading rubric. Finally, this rubric can be attached to the Doctopus file created earlier for our marking process.
'Looking through the dirty window': effect of sampling!
Grading with the Goobric-Doctopus
Organisation of portfolio using Gmail (label) and feedback/feedforward using Google Doc's comment feature.
An example of a bootstrap sampling: the sample size stays same, and it is done with replacement. Therefore, we might see the same item twice or more in the re-sampled group.
To address all the elements of the PPDAC Cycle of statistical investigation, we tend to forget the ethical matters during the investigative process is very important. The Island project demonstrates some of it.
In statistics books, it is frequently suggested that we have to be careful using the word 'significant'. My experience is quite different with the students -they 'love' to use that word to signify some large difference of data etc. Any thought?
How important is p-value in relation to statistical inference? Is it only relevant for experimental data? Can it be used for double checking the inference (call) obtained from Confidence Interval analysis?
The difference of median months for baby's walk is the ESTIMATE (Fathom calls it a Measure) which changes (variability due to sampling). In the stop motion video there are two arrows or sticks. The longer one shows the difference of medians between the control and treatment groups. The shorter stick shows the difference of medians after one of the randomisations. Just imagine if we had 1000 of these differences (converted to numerical figures) and plotted them into a distribution, that will give us the final answer: 'is chance alone playing a role?'. That's how I see it, is it only a 'gamble' or is there a real difference?. Then only we will be able to say if the experimentation is effective or not.