Introductory Statistics Flashcards
null hypothesis
prediction that the observed difference is due to chance alone and not due to a systematic cause
null hypothesis is the statement of
no difference
statistics provide the evidence to
reject or fail to reject the null
alternative hypothesis
prediction that some observed difference is significant and due to some knowable cause
alternative hypothesis is the statement that
there is a difference between groups not attributable to chance alone
what does statistic testing test?
the likelihood of differences occurring by chance alone
p level
the predetermined probability researcher is willing to make a type 1 error
p level is also referred to as the
alpha level
p
“Only 5% of the time, this difference will be observed due to chance alone”
5% chance observed difference was due to chance
95% confident that results were due to independent variable(s)
p<0.001
.1% chance observed difference was due to chance
99.9% confident that results were due to independent variable(s)
nominal
label or category without rank
ordinal
label or category with some meaningful order or sequence
interval
scaled measure with an arbitrary zero point
ratio
scaled measure with an absolute zero point
inferential statistics don’ts (3)
◦Prove cause and effect
◦Estimate clinical effectiveness
◦Estimate risk/benefit
inferential statistics do’s (2)
◦Estimate the probability of getting results due to chance
◦Suggest numerical differences
Statistical significance (p-value) indicates
difference between two groups
Effect size describes the
magnitude of difference
◦How much more effective?
We can standardize difference and compare it to
0
effect size
standard measure, can be calculated from various statistical outputs
Standardized mean effect, expresses the mean difference between
two groups in standard deviation units (Cohen’s d)
◦Need mean and standard deviation for each group
values for effect size range from
-3 to 3
same as standard dev
standard interpretation of effect size
.8=
.5=
.2=
◦.8 = large (8/10 of a standard deviation unit) ◦.5 = moderate (1/2 of a standard deviation) ◦.2 = small (1/5 of a standard deviation)
relative risk
A measure of risk based on a comparison of disease (or other health outcome) incidence in two distinct groups
what is relative risk the ratio of?
the probability of the event occurring in the exposed group versus a non-exposed group
odds ratio
Comparing the odds of an event in one group to the odds of an event in some comparison group
odds ratio estimates
association
Both the odds ratio and relative risk compare the
likelihood of an event occurring between two distinct groups
are relative risk or odds ratio easier to interpret?
RR is easier to interpret and consistent with the general intuition◦comparison between subgroup and entire population, rather than subgroup and remainder of population
Case-control designs limit
RR calculation
cases selected on basis of disease rather than exposure (RR compares exposed to unexposed)
OR and RR are comparable when the disease studied is
rare
OR overestimates RR, when the disease is more
ccommon
◦should be avoided if RR can be used
sensitivity vs specificity
Sensitivity is the proportion of patients with the disease who test positive
Specificity is the proportion of patients withoutthe disease who test negative
confidence interval tells you
the most likely range of the unknown population average
what three things impact the width of a confidence interval
◦Confidence level: typically 95%
◦Variability: standard deviation
◦Sample Size: Smaller sample sizes generate wider intervals