Teaching research methods - tips and pitfalls

[Hibush]

Good suggestions! Keep them coming.

Here are some fun spurious correlations that students get a kick out of: https://www.tylervigen.com/spurious-correlations

So...by producing too many PhDs in mathematics we're increasing the amount of nuclear waste stored at nuclear plants?  Looks like the recommended course of action is clear!

Likewise, our space program is critically dependent on vigorous sociology-PhD production.

[FishProf]

If they've never seen THIS, it is a great intro to context.  Every claim in the website is TRUE.

[Hibush]

If they've never seen THIS, it is a great intro to context.  Every claim in the website is TRUE.

Appropriately sponsored by a Klein-bottle vendor. A nice touch. You can store an infinite amount of DHMO vapor in it.

[OneMoreYear]

Thanks for starting this thread, Sun_Worshiper and for all the suggestions so far from those who have posted.  According to my Fall evals for Research Methods, you should do everything the opposite of how I am teaching it (evals amounted to--instructor tried really hard, but the class is awful).  Eh, I'm not all that pleased with the class structure myself, so it's time for a revamp.   So, I'm taking notes on this thread! 

[ergative]

One gets a spurious correlation between any two variables that exhibit a time trend. Unless the examples are used to motivate time-series analysis, they are not helpful.

I mean, that's the point of the website. It's showing that any two things can be correlated if you look hard enough, even if the correlation is absurd.

I use it to illustrate the dangers of multiple comparisons, and the need for theoretically motivated planned comparisons.

[spork]

I can recommend Charles Wheelan's Naked Statistics for explanations of which basic statistical methods are appropriate for which purposes.

[apl68]

Good suggestions! Keep them coming.

Here are some fun spurious correlations that students get a kick out of: https://www.tylervigen.com/spurious-correlations

So...by producing too many PhDs in mathematics we're increasing the amount of nuclear waste stored at nuclear plants?  Looks like the recommended course of action is clear!

Likewise, our space program is critically dependent on vigorous sociology-PhD production.

And people say that social sciences PhDs aren't good for anything!

[polly_mer]

Good suggestions! Keep them coming.

Here are some fun spurious correlations that students get a kick out of: https://www.tylervigen.com/spurious-correlations

So...by producing too many PhDs in mathematics we're increasing the amount of nuclear waste stored at nuclear plants?  Looks like the recommended course of action is clear!

Likewise, our space program is critically dependent on vigorous sociology-PhD production.

And people say that social sciences PhDs aren't good for anything!

Who says that?!

I have been in meetings of engineers and physical scientists where we realized we needed a social science PhD and had to figure out how to get access to one.

[Parasaurolophus]

Talk to them about how to properly cite other researchers' work (no kidding).

omg yes.

This week of helping my partner edit a collection has been horrific. Like, PhD-revoking stuff, IMO.

[ergative]

Talk to them about how to properly cite other researchers' work (no kidding).

omg yes.

This week of helping my partner edit a collection has been horrific. Like, PhD-revoking stuff, IMO.

Yes, I devoted a section of one of my lectures to that.

Sidenote: I was teaching a first-year seminar about how to write an essay, and we went through examples of good and bad essays. The first-year students chose one of the A-quality essays, gave it a C, and said that the referencing was problematic, because sometimes the author and year were both in parentheses together, and other times only the year was in parentheses. Argh. We had a chat about that.

(They also didn't like the transitions in the A-level essay. That's because they were good transitions, rather than 'Next, this essay will discuss . . . ' at the start of each paragraph. Argh.)

(Yes, I wrote the sample essays myself.)

[Parasaurolophus]

Talk to them about how to properly cite other researchers' work (no kidding).

omg yes.

This week of helping my partner edit a collection has been horrific. Like, PhD-revoking stuff, IMO.

Yes, I devoted a section of one of my lectures to that.

Sidenote: I was teaching a first-year seminar about how to write an essay, and we went through examples of good and bad essays. The first-year students chose one of the A-quality essays, gave it a C, and said that the referencing was problematic, because sometimes the author and year were both in parentheses together, and other times only the year was in parentheses. Argh. We had a chat about that.

(They also didn't like the transitions in the A-level essay. That's because they were good transitions, rather than 'Next, this essay will discuss . . . ' at the start of each paragraph. Argh.)

(Yes, I wrote the sample essays myself.)

I've had similar experiences when I show them sample papers, actually. I was pretty surprised by how much backtracking to the basics I had to do.

[Sun_Worshiper]

I can recommend Charles Wheelan's Naked Statistics for explanations of which basic statistical methods are appropriate for which purposes.

I use this too! Great book and fun read.

Wheelan should write an international edition that relies less on references to US sports. My international students always complain about this (they still like the book overall though).