0

I am a medical student and new to this site so please be patient with me.

I am doing a study on effect of zinc on bronchiolitis in children,taking clinical findings over time period in patients given zinc and patients not given zinc (control) for example: I have taken 50 subjects with zinc(group A) and 50 without (group B); all have bronchiolitis, and this is the results regarding wheeze in the first 24 hour

 group A 31/50 developed wheeze
 group B 33/50 developed wheeze

and I got the results in a similar manner for all other clinical symptom or sign for each interval 24-, 48-, and 72-hr.

what is the next step how to calculate the p-value for each symptom at each interval to see if the zinc is significant or not in relieving a clinical sign or symptom for each interval?!

Carl
  • 13,084
Maysan Student
  • 3

1 Answers1

1

Ideally, this can be looked at with a survival analysis, where wheezing is the event (instead of death). You can do this in SPSS or stata, for example. In this case, you get a significance level (p value) from Cox regression (usually in the same program dialog).

An easier approach is a t Test, where you compare the numbers at one of these time points. Your data has to be organized in columns, like "groupA24h" "groupB24h" and so on; the single patients would be the rows.

You can get a statistically significant result, which is not the same as a clinically relevant difference. Although I doubt that 31 vs. 33 would be significant (at alpha=.05).

Ma Di
  • 26