h2g2 The Hitchhiker's Guide to the Galaxy: Earth Edition

Entry: How To Understand Statistics - A1054117
Author: Atlantic_Cable - U196159

I've already had this in the Writing workshop and would like to thank everyone who helped me with it.

There's got to be an easier way to move etries between review forums, surely?

Like it A_C

I think in the work force sickness example you should explain that 40% represents 2 days, and therefore is normal.

I think your little chart showing the mean mode and average of a set of numbers would be clearer if you included a second set of numbers with a really high number in it - say 4, 5, 5, 5, 8, 12, 86.

Very nice entry!

Have you considered using the clever George Carlin quotation:
"Think about how stupid teh average person is;

now realise half of them are dumber than that."

I liked the entry a lot. Easy to read, factually sound (in my cursory first glance).

I'll have another look soon.

Friar

Ooooh very nice.

There were a couple of crossovers with A852761 (things to consider when reading medical research) so a link might be worthwhile. They were crossovers not duplications though



"Women are better drivers than men
This is not the same thing as saying that all women are better drivers than men"

Should that be "than *all* men" or is that labouring the point?

"Toddler who attend pre-school exhibit agressive behaviour"

Should be either toddlers or attends.

"beccause their behaviour was abnormal."

typo

"the number of injuries due to the head"

Don't think the due should be in there

"However the chart showed that the chewing would have to go on for 30 mins to raise the line above the "danger" line."

Does this mean the eating prior to chewing the gum? Raising the line above the "danger" line sounds like it takes 30 minutes to enter the danger "zone"...might be better to reword it like "chewing would have to go on for 30 mins to take the line *out of* the danger zone".



as a stats bod (or a Management Information Officer) I would prefer it if noone ever read this...I get enough of people picking holes in my data as it is...and no matter how many times I tell them about GIGO it's always my fault

Hi,

Looks very good.

I think there is an entry here somewhere on Average, Mean, Mode, etc. I'll try to find it (it may not be in the EG yet, but if it is you could link to it).

Steven Wright said "47.3% of all statistics are made up on the spot".

Awu.

There are some terms that are probably worth using here. You kind of glass over their meanings in some way, but you don't use the terms themselves -- Type I Error, Type II Error, Type III Error.

If you're going to be recommending books, the one I would recommend is actually the Cartoon Guide to Statistics, by Larry Gonick -- even for people with absolutely no grasp of mathematics whatsoever, it manages to convey a decent sense of university level introductory statistics.

I think you would also need to go into the problem that many of the statistics people try to present are not actually statistically significant -- i.e., people will go on and on about how 95% of children passed their exams at this school, and 92% of children passed their exams at this school, but the sample sizes aren't actually big enough for the difference to be statistically significant. Many people don't understand how important sample size is to interpreting statistics. You have a little paragraph on this, but I don't think it explains it very well to the average lay person.

Also, in your "no average" section, you seem to imply that distributions are always normal, which we all know isn't the case. It would make our lives easier if they were, but sadly, it's not reality. Clearly, this entry is too basic to go into the statistics of non-normal distributions, but it's worth mentioning that there *are* non-normal distributions, and that the statistics you use for normal distributions are often inappropriate when the distribution is patently non-normal.

Another thing for the deceptive use of statistics is the selective presentation of statistics -- so often a company will collect statistics on hundreds of variables, and perhaps calculate a thousand more from those original hundreds, and then present only the 2 or 3 most positive to the public. Again, this gets back to the issue of "who paid for the study".


Mikey

Thanks everyone. I've made a few more changes to the entry.

I suggested this was ready, and I know my statistics, but didn't spot a lot of these errors.

by the way, although you have updated the entry, you have not fixed all the points mentioned.

Just a little thing - in the 'No average' section, can you change the order of the list, so it reads Mean, Median, Mode? Then it will match the order used in the two examples - caught me out the first time I read it through.

I like this entry. Nice and easy to understand.

There are a couple of typos to be fixed - small issues - however;

revelaed that the ealrier records > revealed that the earlier record

fatalies > fatalities

asnwer > answer

There may be more - I wasn't deliberately looking for them.

I'm a bit unhappy with the normal/abnormal behaviour descriptions in the bit about the toddlers. 'the children who stayed at home and did not attend pre-school were less aggressive, because their behaviour was abnormal.' This kind of definition of 'normality' is a minefield that I think you should avoid.

A quote you might like for the averages section:
'Most people have more than the average number of legs'
of course it only applies to the mean!


Azara

"of course it only applies to the mean"... which is why you should try and avoud using the term average and use median, mean or mode instead when talking about the specific data involved.

As a relative PR newbie, I'm not too sure of the logisitcs/niceities here, so please bear with me.

I really liked this entry. It is informative and illuminating, without becoming patronising in any way. Nice one AC!

One minor point, in the quotation from the legal case;

"Assuming that the defendant did not commit this crime, what is the probability that the defendant and the culprit having identical fingerprints?"

Should the second "that" perhaps read "of"? I realise this is a quotation, but it doesn't read quite correctly to me.

Slàinte
Perseus

Your Guide Entry has just been picked from Peer Review by one of our Scouts, and is now heading off into the Editorial Process, which ends with publication in the Edited Guide. We've therefore moved this Review Conversation out of Peer Review and to the entry itself.

If you'd like to know what happens now, check out the page on 'What Happens after your Entry has been Recommended?' at EditedGuide-Process. We hope this explains everything.

Thanks for contributing to the Edited Guide!

Congratulations Atlantic Cable!

spelugx

Thanks. And thank you to everyone who helped me with this entry. I've really enjoyed writing it.

Yes, an entry on stats that I understand. Congratulations!

well, i have had a number of stylistic and grammatical points to change. in parts i have clarified the language, and in others i have changed, deleted or added sentences in order to increase clarity. I have also tried to make it more formal and less chatty. i hope thats ok.

tell us where it is, and we will look and see.

well done AC.