Timeline Graphic Confusion

[ERWoodhead]

Hihi, i'm trying to write up the script for the presentation and on the timeline slide i've run into some issues.

If you look at the timeline graphic under the "Testing of Hypotheses" section there is a line which says "prepare data for testing", but isn't the data prepared during the preparing the data stage? I could assume it means selecting which data we're testing, but it comes after we've already tested the data to find correlations and differences.

Also I think the "Identify Bias" section should come under the "Validation and Interpretation of Results" section, since by saying something is biased we are in fact interpreting that our results say that.

I'm also slightly confused by what "Test Hypothesis with relevant factors" means, since isn't that what was done in the "Identify Factors that Correlate" section? If the "Identify Factors that Correlate" section does not actually involve any statistical analysis and is just saying what we're going to test it should be in the "Defining Hypothesis" section.

[Rawaida]

I've added George, Jagoda & Gloria on your comments, so that everyone's aware on this

[glorwlin]

I think you have given a very good explanation in the slides you uploaded - we need to continuously work on the data and 'prepare' them for different hypotheses. I guess you can use a more appropriate word than 'prepare' just to prevent confusion.

'Identify bias' means initial guesses for potential bias in the data, which require further testing/confirmation at later stage - again you may choose another way to describe it other than 'identify' if it seems confusing - now you mentioned it I do think it is a bit misleading.

This is again the choice of wording - I think what 'identify' means is simply listing all the possibilities based on our initial understanding of the data or intuition, 'list' might be a better word.

In addition to above, I have also gone through the slides you uploaded and they look very good! Here is just some minor points that I picked up in the script which might need to be twisted a bit:

1. Slide 2: a. Research funding are allocated to a range of universities, not only the ones with the highest quality of research b. The year of next REF is uncertain yet - 2021 is an assumption made based on REF 2014
2. Slide 3: a. 'A higher grade means more funding' → 'a higher grade can potentially lead to more research funding'

Overall that is great work - thank you Eleanor:)

[ERWoodhead]

1a. But the funding is allocated to the universities who display the higher quality of research, i.e. the ones who score better on the REF are said to have a higher quality of research and therefore get more money, therefore the REF is a system designed to allocate more funding to universities that produce a higher quality of research. 1b. The Assumption of the next REF being in 2021 was made because the REF website says REF 2021, it was because of this I had to edit the boundaries of years the REF occurs in earlier on. I didn't base it on when REF 2014 occurred because there seems to be little to no pattern as to when these things occur. 2a. If the university gets a higher REF grade they get more funding from them than a university with a lower grade, I don't think there's anything potential about it, but i'll rewrite it just in case.