Welcome to European Tribune. It's gone a bit quiet around here these days, but it's still going.
Display:
I think there are two types of graphs.. those used for mathematical analysis and those used to plot pure data.

If you take any table of numbers and you intrduce in excel or anyother tabel environment (take the data form the CIA worldbook or wiki .. but you have to make soem changes in format) ,there is for sure an option to choose the x-axis and the y-ayis.. and then plot one in frotn of the other where each data is a point.

Once you have mastered this aspect of choosing the axis and plotting discrete data, I rec you the book Migeru mentions about how to plot this data in a truthfull way.. it is a very good start.

Once you knwo how to plot discrete data properly in an axis vs axis scheme  then you can explore the help of the excel program regardign different ways of plotting the same thing.

I am afraid there is no book I know with indication about which graph-method is better depending on the type of data and future analysis you want to make... but there are a few guidlines.

If you want to plot a year after year comparison trasnforming the data point into a bar-graph is normally helpful.. drawing different years one beside the other.

If it is a set of percentages which add up to 100% a cake-plot with different portions is mormally the rule.

If your data comes from measuring the same thing over and over and over and you are interesting in the small differences you find, then the best is to plot all the point in a single column as small dots to see the cloud of points around a number...

And once you have mastered the different graphs.... then you can proceed witht he continuous, mathematical graphs.. and start an internet course on basic analysis of functions....but this will take more time...

A pleasure

I therefore claim to show, not how men think in myths, but how myths operate in men's minds without their being aware of the fact. Levi-Strauss, Claude

by kcurie on Sat Jun 21st, 2008 at 07:47:48 AM EST
If it is a set of percentages which add up to 100% a cake-plot with different portions is mormally the rule.
I'm afraid pie charts are deprecated:
Statisticians tend to regard pie charts as a poor method of displaying information. While pie charts are common in business and journalism, they are uncommon in scientific literature. One reason for this is that it is more difficult for comparisons to be made between the size of items in a chart when area is used instead of length. In Stevens' power law, visual area is perceived with a power of 0.7, compared to a power of 1.0 for length. This suggests that length is a better scale to use, since perceived differences would be linearly related to actual differences.

... Most subjects have difficulty ordering the slices in the pie chart by size; when the bar chart is used the comparison is much easier.

If you have numbers adding up to 100%, plot them on the same bar, one on top of the other.

When the capital development of a country becomes a by-product of the activities of a casino, the job is likely to be ill-done. — John M. Keynes
by Migeru (migeru at eurotrib dot com) on Sat Jun 21st, 2008 at 11:14:19 AM EST
[ Parent ]
J ejeje.. it is all about teaching how to read graphs in media... in physics or any other field they are never used, of course... but I understood he was talking about graphs used in media, finance and in some cases general reader science publications.

A pleasure

I therefore claim to show, not how men think in myths, but how myths operate in men's minds without their being aware of the fact. Levi-Strauss, Claude

by kcurie on Sat Jun 21st, 2008 at 02:21:09 PM EST
[ Parent ]
He's teaching young kids to make graphs - if he can vaccinate them against pie charts...

When the capital development of a country becomes a by-product of the activities of a casino, the job is likely to be ill-done. — John M. Keynes
by Migeru (migeru at eurotrib dot com) on Sat Jun 21st, 2008 at 02:22:53 PM EST
[ Parent ]
 .. wouldn't that be nice? :)

A pleasure

I therefore claim to show, not how men think in myths, but how myths operate in men's minds without their being aware of the fact. Levi-Strauss, Claude

by kcurie on Sun Jun 22nd, 2008 at 07:51:57 AM EST
[ Parent ]
Graphs and statistical analysis are used a lot in the life sciences. One common example: experiments are run several times to confirm that the outcome is reproducible and because of experiment-to-experiment variability. The results may be summarized in a column graph, with error bars proportional to the standard deviation in the set of replicate experiments.

Having said that, incompetent usage of graphs and statistical analysis in scientific papers is one of the major complaints of journal editors.

Double check casts doubt on statistics in published papers

A study highlighting statistical gaffes in scientific literature has brought renewed calls for vigilance among mathematically challenged researchers and journal editors.Statistical tests are sometimes seen as a necessary evil by researchers, who fear their complexity but know that they are needed to test hypotheses.



You're clearly a dangerous pinko commie pragmatist.
by Vagulus on Sat Jun 21st, 2008 at 04:08:09 PM EST
[ Parent ]
Precisely, the exmaple you put is the example I put for graphs in broad audience scienteific journals..

but again.. it seems that the teaching goes to show them how to do the graphs trhemselves, not about how to read them...

then of course.. i would go from basic graphs to mathematical analysis (up to limits, growth, areas and so on). Probably statistical analysis with visual cues is a bit too far for them :)

A pleasure

I therefore claim to show, not how men think in myths, but how myths operate in men's minds without their being aware of the fact. Levi-Strauss, Claude

by kcurie on Sun Jun 22nd, 2008 at 07:54:17 AM EST
[ Parent ]
... in three or four words of English.


I've been accused of being a Marxist, yet while Harpo's my favourite, it's Groucho I'm always quoting. Odd, that.
by BruceMcF (agila61 at netscape dot net) on Sun Jun 22nd, 2008 at 09:03:38 AM EST
[ Parent ]

Display:

Occasional Series