Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
60 Cards in this Set
- Front
- Back
|
What does the NULL hypothesis MEAN
|
NO difference is PRESENT
|
|
|
What is FAILS to reject NULL hypothesis MEAN
|
THE STUDY FOUND NO DIFFERENCE BETWEEN 2 groups
|
|
|
A study that has SIGNIFIGANCE, does what is the NULL hypothesis
|
REJECTS the NULL Hypothesis
|
|
|
What is a TYPE II EROR
|
IS A DIFFERENCE
|
|
|
WHat is a TYPE 1 ERROR (alpha)
|
THE RESULTS SAY there is A DIFFERENCE
And there is NO DIFFERENCE |
|
|
What are types of Descriptive Studies
|
Case reports
|
|
|
Can Case reports explain cause or effect
|
NO
|
|
|
Explanatory studies can explain cause or effect, what type of studies
|
Experimental (Clinical Trial)
Observational Case control, Cohort) |
|
|
What type of studies are case controls
|
OBSERVATIONAL retrospective studies that LOOKED at people with or without and ENDPOINT, and SEE if EXPOSED
|
|
|
What type of studies are COHORT
|
PROSPECTIVE studies LOOK at PEOPLE EXPOSED and SEE if DEVELOP OUTCOME
|
|
|
What is unique about Cross-over studies
|
people serve as own controls
|
|
|
What is Selection Bias
|
subject are NOT randomly assigned
|
|
|
What is Recall Bias
|
subject who have disease may have better memory than those who dont
|
|
|
What are ways to reduce biase
|
Multicenter trial
randomization using double dummy cross overs |
|
|
Parametric data is continuous data, that follow what type of distribution
|
NORMAL distribtion
|
|
|
What is a NORMAL distribution
|
mean, median, mode are all equal
|
|
|
What are COMMON statistical tests for NORMAL distribution
|
T-test and ANOVA
|
|
|
What is NONparametic data
|
population being studied does NOT follow a normal distribution
|
|
|
Parametics is accociated with what type of data
|
CONTINOUS (any number--weight height)
|
|
|
What is nonparametic data assoicated with
|
NOMINAL data
ORDINAL data |
|
|
NON-parametic dats (NOT normal distribution, what is POSITIVELY SKEWED DATA) for distribution (DRAW)
|
Mean > Median > Mode
|
|
|
What is Negatively skewed data
|
Mean < Median < Mode
|
|
|
What is NOMINAL DATA
|
categoies have no sense of ranking
YES OR NO GENDER MORALITY |
|
|
With NOMINAL DATA can you get a mean, median and mode
|
NO only MODE
|
|
|
What is ORDINAL data
|
used to rank order but NOT the same maginitude between them
PAIN Scale |
|
|
What is CONTINOUS DATA (can get a mean, median and mode
|
ranked but equal magnituted (HR, WEIGHT, HEIGHT)
|
|
|
The mean is average, what is the median
|
MIDDLE NUMBER
|
|
|
What is the MODE
|
most frequently occuring number
|
|
|
What is the RANGRE
|
highest and lower number
|
|
|
What is the standard deviation
|
is the degree of scatter from the MEAN
|
|
|
What type of standard deviation do you want
|
SMALL number
|
|
|
What power equation
|
1-BETA
Type II error |
|
|
What does the POWER equation TELL US
|
the probability of making a type II error
|
|
|
What TWO variables have an effect on POWER of study
|
SAMPLE SIZE and alpha value
|
|
|
What is the MAXIMUM alpha value someone may accept
|
0.05
|
|
|
A P value does NOT tell you the degree of clinical signifigant
|
TRUE
|
|
|
What does a P value tell you (i.e. P <0.01
|
MEANS there is A 1% chance that yours results are either due to chance or random ERROR
|
|
|
What does a P value of <0.0001 mean
|
MEANS there is A 0.01% change that your results are either due to CHANCE OR RANDOM error
|
|
|
A Confidence Interval (CI) if it CROSS ONE what does that mean
|
NOT statistically signifigant!!!
|
|
|
ODDS ratios are done what type of studes
|
CASE control
Retrospective studies |
|
|
What is Relative RISK is done for what type of STUDIES
|
PROSECTIVE studies
|
|
|
What is the relative risk
|
incidence rate in exposed /
incidence rate in NON-exposed) |
|
|
What does a RR of 1 mean
|
incidence is SAME
|
|
|
What does a RR of >1 mean
|
increase is exposed group is HIGHER
|
|
|
What does RR <1 mean
|
incidecne is EXPOSED group is LESS
|
|
|
How do you calculate relative risk
|
SEE BOOK
|
|
|
What is the formula for ARR (absolute risk reduction)
|
RRcontrol-RRtreatment
|
|
|
What is NNT
|
1 / ARR
|
|
|
The ODD ratio is used for what type of STUDES
|
retrospective studies (CASE CONTROLS)
|
|
|
How do you calculate ODDs ratios
|
AxD/BxC
|
|
|
What does SENSITIVITY DO
|
SeNsitivty rules OUT
SNOUT |
|
|
SENSTIVITY does what
|
RULES OUT disease
|
|
|
What does SPECFICITY do
|
SPecficity rules IN
SPIN S |
|
|
SPEICIFICITY DOES what
|
RULES IN DISEASE
SPIN |
|
|
IF you have 100% specificity (+) results what does THAT MEAN
|
RULEs IN DISEASE since no FALSE +
|
|
|
If you have 100% senstivity (+) result what does that MEAN
|
RULES OUT DISEASE, no false negatives
|
|
|
What is indicence verus prevalence
|
INCIDENCE is the number of NEW cases during a time period
|
|
|
What is META-ANALYSIS
|
reivew MULTIPLE studies
|
|
|
What is COST minimiization
|
ALL MEDS are equal so pick the cheapst MED
|
|
|
What is COST-effectiveness
|
MEDS are NOT equal (may pay more and get better results)
|
