Which statistical test should I perform?

[d6k5d3]

I have 2 datasets. Dataset X looks like this:

Jmp_o   Nws_r
1       0
0       1
1       1
0       1
0       1
1       0
1       0
...    ...

 I calculate the conditional probability P(jmp_o=1|nws_r=1). There is another dataset Y which is like:

Jmp_o   Nws_r
1       0
0       0
1       0
0       0
0       0
1       0
1       0
...    ...

From dataset Y I calculate unconditional probability P(jmp_o=1).

I want to test whether these 2 probabilities are statistically different (by means of p-value).

What test should I perform?

Much thanks.

[PaigeMiller]

This isn't a case where statistical testing is appropriate. The formulas used are different, so the results are mathematically different.

Statistics would be used only if sampling differences caused different results.

[d6k5d3]

Yes, the two datasets are 2 different samples.

[d6k5d3]

And they are independent.

[PaigeMiller]

---

@d6k5d3 wrote:

Yes, the two datasets are 2 different samples.

---

This is not clear to me based upon your original explanation.

Please explain further.

[d6k5d3]

First I have dataset X from where I calculate the conditional probability. Then from dataset X I create a subsample which has Nws_r=0. After creating dataset Y, I calculate the unconditional probability. Now I need to check whether they are different.

[PaigeMiller]

I stick with my previous statement that this is not a case where statistical testing is appropriate.

If you have a sample of people, and you measure their heights in inches, and then you take an independent sample and measure their height in centimeters, you would not do a statistical test to determine if the average height in inches differ from the average height in centimeters. You would just assume they are different because a different measurement was used.

[PGStats · Accepted solution]

So, all you need is dataset X. Run a Fisher test (proc freq) between jmp_o and nws_r. This will tell you wether the two vars are related in your sample.