Timeline for Testing for similarity on count data
Current License: CC BY-SA 3.0
24 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 9, 2017 at 13:06 | history | edited | kjetil b halvorsen♦ |
edited tags
|
|
| Apr 13, 2015 at 20:47 | history | tweeted | twitter.com/#!/StackStats/status/587718831453384704 | ||
| Apr 13, 2015 at 18:34 | vote | accept | afreen sahiri | ||
| Apr 13, 2015 at 18:33 | history | edited | gung - Reinstate Monica |
added tag
|
|
| Apr 13, 2015 at 18:27 | answer | added | gung - Reinstate Monica | timeline score: 5 | |
| Apr 13, 2015 at 18:13 | comment | added | gung - Reinstate Monica | For me to be notified that you left a comment, you need to ping me like so: @afreensahiri. (You are always notified, because this is your Q.) Your 2nd table is the correct format here; the 1st table is incorrect. | |
| Apr 13, 2015 at 17:59 | comment | added | afreen sahiri | Gung, I have arranged the table in Dr1 Vs Dr 2 format so that the contingency table shows plant A Vs Plant B. I am testing if the same genes are similarly upregulated or similarly downregulated in plant A and B. | |
| Apr 13, 2015 at 17:57 | history | edited | afreen sahiri | CC BY-SA 3.0 |
added 142 characters in body
|
| Apr 13, 2015 at 17:31 | comment | added | afreen sahiri | In my case I am asking if the same genes in two different plants (A and B) respond similarly. It is similar if out of 15 genes upregulated (increased) in plant A, 13 (same) genes are also upregulated in plant B. if out of 10 genes downregulated (decreased) in plant A, 8 are also downregulated in plant B. | |
| Apr 13, 2015 at 17:31 | comment | added | afreen sahiri | it’s more like they have the same patients, and you are wondering if the 2 doctors think they will recover. or does one doctor say they will recover and the other does not? there is similarity if both the doctors say the patients will recover. There is difference if one doctor says the patients will recover and the other says they will not. | |
| Apr 13, 2015 at 17:20 | comment | added | gung - Reinstate Monica | Thanks, now what do you mean by similarity in this context? For instance, one situation is where you have 2 doctors say who they think will recover & you wonder if they select the same patients, but that doesn't seem to apply in your case, as you have plants vs genes, not dr1 vs dr2. | |
| Apr 13, 2015 at 17:19 | comment | added | afreen sahiri | Rover eye is right. I have edited my post and added the tables with my actual data gung. Thank you | |
| Apr 13, 2015 at 17:18 | history | edited | afreen sahiri | CC BY-SA 3.0 |
added 206 characters in body
|
| Apr 13, 2015 at 16:37 | comment | added | gung - Reinstate Monica | Can you post an example of your data? What are your variables? Do you have a contingency table? | |
| Apr 13, 2015 at 16:29 | comment | added | Rover Eye | I think the OP is asking for a null hypothesis of data having a difference, and alternate of they being the same..something along the lines of equivalence testing if I am not wrong? but for count data, and not population distributions. | |
| Apr 13, 2015 at 16:03 | comment | added | Glen_b | No, sorry, it isn't. How are you going to get an alpha of 0.05 or lower? What rejection rule can achieve it? | |
| Apr 13, 2015 at 15:57 | comment | added | afreen sahiri | alpha value has to be below 0.05 and beta value 0.2. these are the standards we use in our field. is that what you are asking? | |
| Apr 13, 2015 at 15:18 | comment | added | Glen_b | To do a hypothesis test you need to work out the probability of rejection when $H_0$ is true (or more generally, the largest probability for composite hypotheses). How are you going to do that? | |
| Apr 13, 2015 at 14:11 | comment | added | afreen sahiri | I have done fishers exact test on treatment a and treatment b and the P value I got was 1. This is representing that there is no difference between the two treatments. However, It is not valid for me to say that as the P value is 1 the two treatments are similiar. Therefore I am trying to establish if there is a statistical test that I can use on a count data that measures for similarity rather than differences. | |
| Apr 13, 2015 at 14:09 | comment | added | afreen sahiri | Aletrnative hypothesis: Response in treatment A is similiar to response in treatment b. so response Yes in treatment A is likely to be response yes in treatment B. | |
| Apr 13, 2015 at 14:07 | comment | added | afreen sahiri | Null Hypothesis: treatment A bears no similarity to treatment b. Response yes in treatment A can equally be response yes or response no in treatment b. | |
| Apr 13, 2015 at 14:01 | comment | added | Glen_b | What's a 'p-value for similarity'? What test statistic? What's the null, and what's the alternative? | |
| Apr 13, 2015 at 12:10 | review | First posts | |||
| Apr 13, 2015 at 12:12 | |||||
| Apr 13, 2015 at 12:09 | history | asked | afreen sahiri | CC BY-SA 3.0 |