# Thread: Treatment for Table Results - Help

1. ## Treatment for Table Results - Help

Hello everyone! I just joined, as you can see by my bare naked account.

I am here because I am quite desperate. I have this wonderful Epidemiology work to deliver tomorrow. Epidemiology has to do with statistics and logic and they both have to do with maths so hopefully I'm at the right place (and posting this on the right location, sorry if not).

So, I have a table. In this table I have inputted all the results for the surveys I made. 5 people answered and each positive answer to each topic is marked with an X or with a quality defined by the survey's options. Now, what I need to do and don't know how, is how to relate those answers with each other.

Let's suppose I want to see if getting sick is a direct consequence of not washing your hands, based of the answers of the survey. Some answered they did not wash their hands and got sick, some washed hands and did not get sick, some did not get sick and never washed their hands and some got sick even though they washed their hands. How do I conclude mathematically that you get sick if you don't wash your hands?

I am pretty sure my epidemiology teacher gave me a complicated formula for this, but she did not tell us how to use it (just "you have to know this exists"). I've read some similar scientific articles and they used SPSS to treat their data. I own that program but don't know how to use it so...

I really hope you guys here can help me! I'll even put an aknowledgement in the article! (If needed I can screenshot the table) Thanks!

Edit: Just in case I'm having trouble explaining myself is a quote from the methods of an article where they did something like I want to do
Data were analysed using Statistical Package for the Social Sciences (SPSS) 16.0 and Microsoft Office Excel 2003 for Windows. Data on the eight variables on victims, injuries and circumstances were organised in cross-tabulations and association between variables was tested with Pearson’s Chi square test. Data on breeds were presented in contingency tables with the variables breed (breedx or nonbreedx) and population (biting population or canine population). To test for statistical significance of differences between the two fractions, we used Fisher’s Exact test for breeds and Pearson’s Chi square test (without Yates’ correction) for breed groups. Responses in the category ‘unknown’ were considered as missing data in statistical analyses. Tests were two tailed, and significance was accepted if P < 0.05.
I understand what is written there but I don't know how to do it...

2. Originally Posted by ladyxzeus
Hello everyone! I just joined, as you can see by my bare naked account.

I am here because I am quite desperate. I have this wonderful Epidemiology work to deliver tomorrow. Epidemiology has to do with statistics and logic and they both have to do with maths so hopefully I'm at the right place (and posting this on the right location, sorry if not).

So, I have a table. In this table I have inputted all the results for the surveys I made. 5 people answered and each positive answer to each topic is marked with an X or with a quality defined by the survey's options. Now, what I need to do and don't know how, is how to relate those answers with each other.

Let's suppose I want to see if getting sick is a direct consequence of not washing your hands, based of the answers of the survey. Some answered they did not wash their hands and got sick, some washed hands and did not get sick, some did not get sick and never washed their hands and some got sick even though they washed their hands. How do I conclude mathematically that you get sick if you don't wash your hands?

I am pretty sure my epidemiology teacher gave me a complicated formula for this, but she did not tell us how to use it (just "you have to know this exists"). I've read some similar scientific articles and they used SPSS to treat their data. I own that program but don't know how to use it so...

I really hope you guys here can help me! I'll even put an aknowledgement in the article! (If needed I can screenshot the table) Thanks!
You make a table like this:

$\begin{array}{ccc}\ &\mbox{sick}&\mbox{not sick}\\
\mbox{wash hands}& N_1&N_2\\
\mbox{no wash}&N_3&N_4\end{array}$

$N_1, N_2, N_3, N_4$ denote the number of people in each category.

You can do this using Variance Analysis. You can use F-distribution to determine whether there is any significant difference between washing hands and not washing hands. You also can determine whether the number of peeple getting sick and not getting sick in relation to washing and not washing hands.

3. Thank you! I searched a bit more and found application with chi-square, but the f-distribution is easier... Though I haven't looked at it since high school! Thank you so much for the quick answer!

4. Originally Posted by ladyxzeus
Thank you! I searched a bit more and found application with chi-square, but the f-distribution is easier... Though I haven't looked at it since high school! Thank you so much for the quick answer!
You are welcome.