I am having a lot of trouble figuring out the runs for a 2*3 4*4 survey design. From the following site, it is orthogonal at 16 runs, so I don't think I am trying to do something impossible.

http://neilsloane.com/doc/cent4.html

But for the life of me I can't figure out what the runs are. I've tried a bunch of different iterations but resultant regressions won't run properly because the parameters aren't set up properly. Any idea what I am doing wrong?

Below Brand/Price/HP and MPG have 4 possible values. Var1, Var2, and Var have 2.

Run Brand Price HP MPG Var1 Var2 Var3

1 Brand1 Price1 HP1 MPG1 Var1Off Var2Off Var3Off

2 Brand1 Price2 HP2 MPG2 Var1On Var2On Var3On

3 Brand1 Price3 HP3 MPG3 Var1Off Var2On Var3On

4 Brand1 Price4 HP4 MPG4 Var1On Var2Off Var3On

5 Brand2 Price1 HP2 MPG3 Var1On Var2On Var3Off

6 Brand2 Price2 HP1 MPG4 Var1Off Var2On Var3Off

7 Brand2 Price3 HP4 MPG1 Var1On Var2Off Var3On

8 Brand2 Price4 HP3 MPG2 Var1Off Var2Off Var3Off

9 Brand3 Price1 HP3 MPG4 Var1Off Var2On Var3On

10 Brand3 Price2 HP4 MPG3 Var1On Var2Off Var3Off

11 Brand3 Price3 HP1 MPG2 Var1Off Var2Off Var3Off

12 Brand3 Price4 HP2 MPG1 Var1On Var2On Var3Off

13 Brand4 Price1 HP4 MPG2 Var1On Var2Off Var3On

14 Brand4 Price2 HP3 MPG1 Var1Off Var2Off Var3On

15 Brand4 Price3 HP2 MPG4 Var1On Var2On Var3Off

16 Brand4 Price4 HP1 MPG3 Var1Off Var2On Var3On

I would greatly appreciate any help, I am going crazy trying to figure this out! ]]>

I need some help and input on my analysis for a research. My aim is to determine any statistically significant difference in the noise levels between 5 genres of movies:

Action (n=18)

Comedy (n=6)

Drama (n=6)

Horror (n=4)

Musical (n=2)

My independent variable is nominal. My dependent variable is continuous/interval. Usually I would use ANOVA, but my problem now is the number of data points in each "genre" group is unequal.

To get around this problem, I grouped Comedy, Drama, Horror and Musical into one group: "Non-Action". This way, I have two groups with equal number of data points: Action (n=18) and Non-Action (n=18). After checking the normality with Shapiro-Wilk (p>0.05), I run the two groups through independent t-test. Equal variances assumed, p=0.002.

I wanted to try analysing all 5 genres separately. I looked for a test to use: 5 groups, equal variances but unequal sample size. In the end, I tried using Kruskal-Wallis. I know this test is not ideal, because I have groups that have less than 5 data points, but I run it through anyway and got the following results:

Chi-Square 18.686

df 4

Asymp. Sig. 0.001

Then I did a post hoc test using Kruskal Wallis. I got p-values <0.05 with Action vs Drama and Comedy vs Drama. Action vs Comedy is not significant. I did not analyse Horror and Musical because the sample sizes are <5.

This is what I've attempted so far.

Is my method acceptable?

Is there a better test or a better way for me to analyse this data?

Any input and advice will be appreciated. Thank you in advance.

ps1: I also run Shapiro-Wilk test on all 5 genre groups. All had p>0.05 except Musical, which was too small to be analysed.

(By the way, I use SPSS Version 20. I am an undergraduate student.) ]]>

Thanks

sample size 28350

Of the whole population 10.4% have the outcome, 89.6% don't.

Of those with the main exposure, 12% have the outcome of those without the main exposure 10%. ]]>