Statistics Help Please

sarahbarron · 05-01-2009 06:05PM #1

Hi, I'm in urgent need of some help, the guys over in the mathematics forum told me to come here for a step by step walkthrough of how to do my statistics. I'm doing an undergraduate course in radiography but for some crazy reason I have to do statistical analysis as part of my dissertation. I did an experiment where I took a number of x-rays on a phantom in two different postions.

My dissertation supervisor told me that I have to do the anova test and the wilcoxen test. The poor man spent over two hours explaining how to do it but I came out and still hadn't a clue. My dissertation is due in a couple of weeks and I cant finish it unless I get some help.

The data I have is the dose recieved by four sensitive organs- the testes, the ovaries, the eyes and the thyroid gland. I have data for both positons.

If someone could possibly walk me through how to do this step by step I would be very grateful. I have very little experience in statistics and computers in general so if it could be explained simply that would be great. I have both Minitab 15 and Excel to do the statistics in by the way.

Sarah

2Scoops · 05-01-2009 08:55PM

Hi sarahbarron, it should be easy to sort this one out but probably a bit more information on your dataset is needed first. I've never used Minitab but I can help with Excel (and R or SPSS, if you need a more complex analysis!).

I've followed you over from the maths forum so I know the basic gist of what you want to analyze, but first you should clarify what exactly you want to test:do you simply want to compare the two body positions for each organ or do you also need to compare organs?

Also, what are you comparing - what are the units? Or is it some kind of ratio or percentage?

sarahbarron · 06-01-2009 01:47PM

Excel is fine thanks, whatever suits you.

The data I have consists of five exposures in position one for the ovaries, testes, thyroid and eyes, giving the dose received for each. I have the same data except for position two.

I want to compare the positions, identifying which one gives the least dose to the sensitive organs- I think this what I need to use the ANOVA for.

I'm not exactly sure why I need to use the Wilcoxen test, but I'll have more information tomorrow when I get back home.

Sarah

2Scoops · 16-01-2009 07:31PM

To analyze this dataset, a 2-way repeated measures ANOVA would work - except that, technically, your sample size is actually 1 and not 5, since these are all remeasures of the same thing. The technically correct way to analyze it then, would be a 2 way ANOVA with organ and position as group variables.

I ran it both ways quickly - the good news is that they both have more or the less the same results! This analysis is straight forward but can't be done in Excel. I can run you through how to do it in SPSS or R.

sarahbarron · 16-01-2009 07:34PM

Hi thank you so much for replying so quick. Thats brilliant news that i can do the anova as i was starting to panic. i can download which ever software you think is appropriate. just let me know what you need etc.

2Scoops · 16-01-2009 07:44PM

I would say SPSS is the quickest. If it is on your school computers, then great. Otherwise, you can download a trial here:

http://www.spss.com/downloads/Papers.cfm?ProductID=00035&Name=SPSS_Base&DLType=Demo

Statistics Help Please

Comments