What does P value means and from what range to what is it significant?
I have read a lot of web pages but haven't understood. Please immediate help is required.
I need to interpret Hartigan dip.test results on the basis of P value which is 1 and 0.9 , 0.2,0.7
Please guide me how to interpret these p values for bimodality and unimodality
The American Statistical Association (ASA) published these recommendations on the proper use of the p value:
1.) p-values can indicate how incompatible the data are with a specified statistical model.
2.) p-values do not measure the probability that the studied hypothesis is true, or the probability that the data were produced by random chance alone.
3.) Scientific conclusions and business or policy decisions should not be based only on whether a p-value passes a specific threshold.
4.) Proper inference requires full reporting and transparency.
5.) A p-value, or statistical significance, does not measure the size of an effect or the importance of a result.
6.) By itself, a p-value does not provide a good measure of evidence regarding a model or hypothesis.
I would like to recommend reading the paper in the attachment.
Regards, Christian
Simply put, P value is the calculated probability of rejecting the Null Hypothesis, that is, the probability of findind similar results as a 'positive' or 'negative' effect in an experimental study if you were to repeat it with the whole population. In other words P determines the probability of being wrong and that the results of the experment are not random. The Significance (or alpha level) referes to a pre-chosen probability. It usually depends on the fiels of study. In the social sciences 0.5 is significant, whether in the medical sciences 0.001 is the minimum required.
Jorge
No, Jorge, that is definitively wrong.
The p-value is not about the probability of rejecting the null hypothesis (in a whole population or wherever). Further, the p-value has nothing to do with the "alpha level". The p-value is a "benchmark measure" used in significance tests, whereas the alpha level is an error rate defined in hypothesis tests - something very different! For a short intro you may read Perezgonzalez JD (2015) Front. Psychol. 6:223.
The p-value is the probability of a more extreme test statistic (a convenient summary of the data) than the one observed, and this probability is evaluated under a given statistical model. The null hypothesis is a particular restriction in the model. A small p-value indicates that we wouldn't expect such data (that is at least as "extreme" [w.r.t. the restricted statistical model] as the data that were actually observed):
p = Pr( t ≥ tobserved | H0 in M)
where t is the (absolute) test statistic, H0 is the null hypothesis as a restriction in the statistical model M.
If you believe that the restricted model is in principle a sensible model to describe your data, then the p-value tells you how much you should bet on observing more extreme test statistics than the one calculated from your data. There is nothing more that would follow from a p-value. However, since you believe that the model is principially sensible, a low probability of the data under the restriction may incline you to believe that the restriction (the null hypothesis) is inadequate. This is your decision: how high are you willing to bet that the more complex model will serve the purpose better than the simpler (restricted) model? This depends on the purpose of the model, and it is a subjective judgement call. There is no logical rule. Most people feel a 20:1 bet as good enough to decide for the more complex model (i.e. to "reject the null hypothesis"), but most do it just because others do it and not because they would think that this is a sensible choice in light of the specific context.
Instead of investigating p-values I suggest to look at more direct measures of what you are interested in. It can be helpful to simulate data and see what consequences the simulated features will actually have in the specific context of your research.
The American Statistical Association (ASA) published these recommendations on the proper use of the p value:
1.) p-values can indicate how incompatible the data are with a specified statistical model.
2.) p-values do not measure the probability that the studied hypothesis is true, or the probability that the data were produced by random chance alone.
3.) Scientific conclusions and business or policy decisions should not be based only on whether a p-value passes a specific threshold.
4.) Proper inference requires full reporting and transparency.
5.) A p-value, or statistical significance, does not measure the size of an effect or the importance of a result.
6.) By itself, a p-value does not provide a good measure of evidence regarding a model or hypothesis.
I would like to recommend reading the paper in the attachment.
Regards, Christian
From Jochen's and Christian's responses, one question that you need to answer is whether p is providing the information that you want to answer your question.
Statistics is sometimes taught as a way to find p values as if these are answering any question that researcher might be interested in. If not, then don't worry about trying to interpret their complex meaning (and with 4 p values, the meaning is even more complex), and concentrate on other summaries of the data.
Ahsan, are these p values addressing your research question(s)?
Hello there,
When you perform a hypothesis test in statistics, a p-value helps you determine the significance of your results. Hypothesis tests are used to test the validity of a claim that is made about a population. This claim that’s on trial, in essence, is called the null hypothesis.
The alternative hypothesis is the one you would believe if the null hypothesis is concluded to be untrue. The evidence in the trial is your data and the statistics that go along with it. All hypothesis tests ultimately use a p-value to weigh the strength of the evidence (what the data are telling you about the population). The p-value is a number between 0 and 1 and interpreted in the following way:
A small p-value (typically ≤ 0.05) indicates strong evidence against the null hypothesis, so you reject the null hypothesis.
A large p-value (> 0.05) indicates weak evidence against the null hypothesis, so you fail to reject the null hypothesis.
p-values very close to the cutoff (0.05) are considered to be marginal (could go either way). Always report the p-value so your readers can draw their own conclusions.
Regards
Hi!
Previously somebody asked the same kind of question reg. P value see the following "If you did a research, analyzed the results, and got a p-value of less than 0.05 what can you really claim?" (you can see my answer at page 3)(https://www.researchgate.net/post/If_you_did_a_research_analyzed_the_results_and_got_a_p-value_of_less_than_005_what_can_you_really_claim/3)
P tells about statistical significance. You just cannot blindly reject and accept by seeing 0.05. Thorough knowledge is needed to accept and reject the values of P.
"P-value Interpretation
P< 0.01 very strong evidence against H0
0.01< = P < 0.05 moderate evidence against H0
0.05< = P < 0.10 suggestive evidence against H0
0.10< = P little or no real evidence against H0
This interpretation is widely accepted, and many scientific journals routinely publish papers using such an interpretation for the result of test of hypothesis."
A p-value tells you the probability of having a result that is equal to or greater than the result you achieved under your specific hypothesis.
It is a probability and, as a probability, it ranges from 0-1.0 and cannot exceed one. A p-value higher than one would mean a probability greater than 100% and this can't occur.
- Badges
- Science topic