Wonderful, thanks.

So good.

I'm assuming you see my shared screen in which basically just the title slide is shown.

This is the tutorial for lecture number eight in the series of empirical research methods

for medical engineering.

And yeah, it is a series of three that I'm going to hold.

So number eight, number nine, and number ten.

And they will be directly linked to the stuff that you just saw, although seeing from a

different point of view.

So my understanding here is then I'll try to give you a practical grip on the, well,

the tools that you just watched, right?

So we'll try to see why we need them and how to reasonably use them.

I need to make a premise here.

I'm not theoretician of statistics.

So if you got some theoretical questions about these tools, you should drag them to Birgit

or to Dharina.

I don't really, so I use these as tools and I know some of the maths behind it, but not

down to the last detail.

So it might be the case that you ask me something.

And at some point I say, I don't really know.

She should ask someone else.

Never mind that.

And hope that this doesn't happen.

So what is the structure going to be for my exercises?

I have quite a few things open, so I need to be careful about them.

So basically, well, not basically, this is going to be the case.

So I'll first show you a few slides.

And then I'll switch to Colab, the Google Collaborative Laboratory, and work out one specific

topic of this lecture.

And show you a few related things.

So for those of you who are not familiar with it, Colab is this cool online tool by Google

in which you can interest purse, text, and code.

Now the text can be formatted in a quite good way, so you can have italics, bold, bold,

and especially, so headings, which is also very important, and especially you can have

late-tech maths.

So it really looks like a paper.

And I can put my maths there so I can illustrate what I mean by the concepts and then formula.

And I can also place images in it, which is almost never the case, but sometimes there

are.

And then I can open a section of code, and that code will be Python.

And so since everyone, more or less, is familiar with Python, probably here I'm the one

who knows less about it.

I can run the Python code and show you graphs and change the parameters and then show you

how the graph changes or how the results change.

And this is exactly the way I'm trying to, I'll be trying to convey to you some of the

gist of the set of tools and statistics that we use.

And then, and then, in the Colab, I have a few tasks for you to work out.

And I'll just, so after every Colab file, which I will comment, I will stop and give you

some 15 minutes to try and do it yourself.

This is not mandatory, of course.