Are you saying that the mean is the middle? I find that a little confusing because of median.

I really like this module. I like the flow of topics and organization. Some more detail is needed in some places and I am curious about what will be in 1.7.2, but really interesting so far.

I am curious about how you will use the Bayes theorem here.

We can just get that from the table, right? You don't really need the Bayes theorem. I think.

I like this exercise but it's not actually related to the topic of the module.

These are great questions

Capitalize

To me, these are two separate questions.

Are you only looking at traffic stope here or are you looking at other things? How do we decide if there is bias? That might be the first question to ask.

It might be worthwhile to also ask about the limitations in how the data is collected in the first place.

I think that this can work since you explained the math topics. One thing you can do is have them analyze the Philadelphia data from 1.6 in this section, asking additional questions. I imagine that there the disproportionality is more stark and we can make a stronger case for police bias. I would also move the 1.7.2 activity into Solving for change. I am not sure what is going to be in this activity, but I am sure that a lot of different questions can be asked about the dataset to get at police bias, which I think is what you are trying to do here.

Still needs to be added

I think you don't actually need this sentence. You set up the numbers so that the positivity rate follows from them -- you have 1000 out of the 100000 who are infected. That way the example shows how to find all the probabilities in the problem from the numbers given, not needing additional outside information. But I may be misunderstanding what you are trying to do.

positive

I believe it will actually be ten times as much.

I wonder if it would be helpful to illustrate the theorem and this example using a table too. It may make more sense than just the formula.

0.01?

Related to what I wrote above: I think that students would need help understanding what it means to be infected if negative and what it means to be negative if infected.

Need a period here

Can you say more about this? How is it used?

I think that some straightforward examples would be really useful here.

I am not familiar with this notation. I am used to P(AB) or P(A /cap B).

Should we assume that students know this already? I guess it will depend on whether the topic comes up in previous modules. But if this is the first module with probability, I think that some more discussion of probability may be needed before getting into conditional probabilities.

A very important point

I think it would be useful to share the results here, i.e., the table and graph.

Will there be a tutorial for how to get started with R? Will it be possible to embed it in the module somehow?

Great explanations in this section.

Maybe make a note of limitations of sex as a binary category.

Technically, column headings are variables, I think

These are the big questions, I agree. I just think that the section can be expanded upon a little. Maybe just with an intro sentence along the lines of "The questions this module addresses are..."

These are both primarily financial gains. What other gains are there?

Indeed. But you may have to explain this a little more. Not everyone will know these groups (I actually am only aware of GEO Group).

I imagine not everyone will agree with or appreciate item 1. I guess police also gain because if they do nothing then they don't have to do any extra work. Though they also lose through engaging in dehumanizing practices. But that's beyond the scope of this module.

What happened in Ferguson? And why just Ferguson?

the language here is a little clunky

What do you think about adding a footnote explaining why you use the term minoritized and maybe what it means, since not all students will be familiar with it?

Can you elaborate on this a little?

I think this section could be longer. What is the issue? It seems like you are jumping in the middle when you start with California. Before we get to policing data, why is policing an issue? Why do we need policing data?

Which calculations?

the Bayes Theorem?

which concepts?

This hasn't come up yet in the module, but I assume it will when you add more content.

Which is related to Cui Bono, right?

I think it's really neat that you developed a mathematical model that actually predicts temperature increase. I do think this section is much more equation heavy than any of the previous ones, so as I mentioned above, I think you should prepare the reader gradually for the section. Having a short section about ratios and proportions for example, as well as just dealing with algebraic equations might be helpful.

Explain what this means. I think you are using this word with a few different meanings.

I don't think that students will know the proportionality symbol. You may want to explain what that means.

These may also need defining in the prerequisites section? Especially dimensionless.

Example? This is a little abstract,

It seems to me that this section jumped suddenly in the level of mathematical and science sophistication. I am wondering if some things from this section (e.g., proportionality) should be foreshadowed in the mathematical prerequisites, or in the understanding the issue section.

Check for typos in this section

Greenhouse

I am pretty sure it's greenhouse as one word.

It's really neat that you added this section.

I don't know if the logarithmic scale is necessarily hiding anything; it seems necessary to graph all the countries in the same graph. But I would agree that people looking at the graph would need to understand what a logarithmic scale means.

If students will have to make their graphs, you may want to show them where and how to make them.

This is only allowed if the parts add up to 100% of the same whole.

Great examples! I think that the section gets a little long though.

What do you mean by repeated values? :Like two values for the same year?

Line graphs are only used for change over time.

It would ne nice if some of the countries could be labeled.

This is not a technical definition of an outlier.

I don't quite understand what you mean here.

They don't have to be continuous. Discrete would also be possible.

You should not really use a pie chart in this situation. You can, I guess, but it's weird.

You calculate the angle so you don't have to estimate.

Note that pie charts can only be used with categorical data and only when the categories add up to 100% of the same whole. Statisticians generally discourage the use of pie charts.

Only for categorical data.

Are you really sure there are two types of data here? Isn't this only categorical data? There is always a count or measurement associated with a categorical variable.

In a histogram, the bars need to touch, since it's a continuous range.

Do you think students will need a reminder of what [ vs ( means with number intervals?

A bar graph and histogram are two different types of graphs.

Histograms can also be used for discrete data, for example test scores. But they can only be used with numerical data.

My understanding is that this is still categorical data because you could reorder the numbers of vehicles and it would be weird but not incorrect.

Can you please consult some statistics books on this? I have been reading a lot of statistics in the past year but am not a statistician, so I may not be correct.

Bar graphs are only used for categorical data.

I don't understand why days of the year are continuous.

These both look discrete to me.

Does this have to be true?

Examples?

It doesn't have to be small.

Can you give 1-2 examples?

This is vague. Also, can you give 1-2 examples?

This is a negative definition. Can you provide a positive definition of what is meant by categorical?

I think you should give a definition of data.

I like that you are providing this information.

This is a little weird. Maybe with an example it would make more sense.

Maybe have this as a separate definition?

I would recommend having one or two examples of numbers written in scientific notation before the examples below.

The notation A.XXXX may be confusing. I could see students thinking that the X's all stand for the same number.

It seems to me that those who want to maintain the status quo benefit. Eventually we all lose, but in the meantime, oil producers and big industry benefit.

Why is this significant? It may seem to someone that 1% is not very much.

Isn't this also just hypothesized? It's not 100% certain that this is what caused the extinction, right?

I think Earth should be capitalized everywhere.