PAS 4 Flashcards
Questions to ask when looking at data…
is there an effect size?
is the effect size large enough to be biologically significant?
is the result a real effect or due to random variation in the data?
How do we judge whether the result is a real effect oR not?
by looking at raw data
by plotting sem error bars
by calculating a confidence interval
by calculating a p-value
What does a confidence interval tell you?
What is the most likely value for the effect size?
How large or small might the effect size be?
Is zero possible answer for the real effect size?
Could the effect be negative?
Gives a visual representation
Biological Significance
Statistical significance
sufficiently great or important to be worthy of attention
having a particular meaning and signifying something (indicative of something) as the result is not due to random variation
p=0.05 is a ….level of evidence
weak level of evidence
Type 1 Error
Type 2 Error
rejecting the null hypothesis when in fact it is true and there is no real effect (FALSE POSITIVE)
accepting null hypothesis when in fact it is false and there is a real effect (FALSE NEGATIVE)
What is the p value now seen as the alpha to be used when declaring something statistically significant?
p<0.005
Why is null hypothesis significance testing so popular?
People don’t like uncertainty and the NHST appears to give a definite answer (however often wrong due to type 1 and 2 errors)
People don’t like making decisions, therefore the computer makes the decisions for them based on the p-value (however only makes decision off one piece of evidence, the p-value, when really you should make the decision based on all the evidence)
People are often lazy:
- tells you a result is significant, implying that you don’t need to do more experiments (when there is still only weak evidence)
- tells you result is not significant implying that you don’t need to do more experiments (when really the p-value by itself gives no direct evidence that the null hypothesis is true)
- possible to use it without really understanding it
People are ambitious, and the NHST allows you to publish more papers for the minimum work (even if some of the conclusions are actually wrong)
critical value
the point along the x-axis, at which you decide to reject the null hypothesis
What are the two types of tailed t-tests and how does it affect the probability and rejection?
- one-tailed test = 0.05 probability level = a region of rejection of 0.05. only a sample mean much lower (or higher but not both) would have led to the rejection of the null hypothesis.
- Two-tailed test. the rejection region must be split between both tails of the distribution—0.025 in the upper tail and 0.025 in the lower tail
You will reject the null hypotheses of no difference if sample mean is either much higher or much lower.
compare a one-tailed test and two-tailed test?
- A one-tailed test allows for only one possibility – a directional choice. e.g. are females shorter than men/are males taller than women
- A two-tailed test allows for the possibility that the test statistic is either very large or very small e.g. is there a height difference between the genders?
The p-value in hypothesis testing represents?
In NHST (null hypothesis significance testing) the p value is the probability of observing results as extreme or more extreme than currently observed, given that the null hypothesis is true.
do we reject or accept the null hypothesis if the t statistic is larger than the critical value?
reject
