shirley.ha
Mind Map by , created about 6 years ago

HBS108 (Topic 8.4 Statistical inference and hypothesis testing: Conf) Mind Map on P-values, created by shirley.ha on 09/16/2013.

42
1
0
shirley.ha
Created by shirley.ha about 6 years ago
Casuality aka causation & association
shirley.ha
Measures of central tendency
shirley.ha
Measures of dispersion
shirley.ha
OCR AS Biology - Enzymes
Chris Osmundse
Joomla Extension
Santi Sounsri
Topic 8.4 Statistical Inference, Statistical Significance and Hypothesis Testing
shirley.ha
Null hypoth, chi-squares, p-values, CI
shirley.ha
P-values, Generalisability, Study Limits
shirley.ha
P-values e.g
shirley.ha
P-values
1 used for hypothesis testing and is critical in the interpretation of results from quantitative research studies.
1.1 used to see if an association between two (or more) variables is statistically significant.
1.1.1 determines the probability of obtaining the same or more extreme result that the one actually observed from chance alone (i.e. assuming the null hypothesis is true);
1.1.1.1 generally (but arbitrarily) considered significant if p ≤ 0.05 (i.e. the p-value is less than or equal, to 0.05).
2 routinely report the results of studies with p-values.
3 If they do not have some test of significance
3.1 you cannot really interpret whether or not the results are actually “true” or of any use at all.
4 results are commonly summarized by a statistical test
4.1 and associated p-values or confidence intervals, and a decision about the significance of the result is based on either one of them (they provide similar information)
5 reader decides if evidence is strong enough to believe.
6 study was designed according to good scientific practice, the strength of the evidence is contained in the p-value.
7 important for the reader to know what the p-value is saying.
8 If not due to chance, the association is likely to be real and the results can be generalised to the whole population.
8.1 the conclusion drawn about the hypothesis
9 The process of applying a test of significance is also called HYPOTHESIS TESTING
9.1 this results in a decision to reject, or not, the NULL HYPOTHESIS.
10 GOLDEN RULES
10.1 p ≤ 0.05
10.1.1 the result is statistically significant
10.2 p > 0.05
10.2.1 the result is NOT statistically different