Suggestions for constructing a valid Survey on fighting

[lklawson]

OK, my recent article deconstructing the "90% of all fights go to the ground" myth got me thinking. Because none of the existing data sources pass research muster, it'd be really, really nice to have one that does. The problem is, I'm not going to shell out that thousands of dollars (hundreds of thousands?) to have a Research Group run a national poll.

So, failing that, I'm soliciting ideas for actually getting the necessary data in such a way that actually will pass muster.

Suggestions?

Peace favor your sword,
Kirk

 

[punisher73]

I almost think that there are too many variables to get reliable data. For example, the flawed data for the 90% statistic was for LEO that wanted to take it to the ground for arrest. So you would need to differentiate fights that went to the ground by design (ie: wrestler takedown), fights that went to the ground after someone was knocked down, fights that went to the ground due to slippage or just falling. Then you would have, did both people stay on the ground or did one stay standing and strike/kick from there.

As to data sources, maybe design a website and pass it word of mouth to sites like this and MA schools to have them go to. Maybe entice them with a free ebook for participating or something or for referring so many people.

 

[lklawson]

I agree that there's a LOT of data that should be collected, ideally. Everything from "multiple opponents" to "weapons or barehanded" permutations.

The issues, as I see them, related to that sort of on-line survey are "sample bias." The sample would be skewed by the fact of being "martial artists" or, at the very least, "self defense minded." I suppose that it might be possible to, in part, control for that by including a question "are you a martial artist or do you have martial arts/combative training?" However, the advertising would still seem to me to appeal more to martial artists and draw them more heavily, particularly if the incentive was an ebook related to martial arts.

I suppose that I might be able to reach a broader audience by using a Social Media that extends beyond that, such as Facebook, but, again, there is a slight sample bias in that the responders would all be "internet active."

I'm not saying that it's not do-able, of course, just looking to make the survey as statistically solid and valid as possible.

Peace favor your sword,
Kirk

 

[Jason Striker II]

I agree that far too many variables are involved to do anything that would be statistically accurate.

I'm content with "ground-fighting happens a lot" so deal with it!

 

[lklawson]

I'm content with "ground-fighting happens a lot" so deal with it!

Peace favor your sword,
Kirk