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;
35 Cards in this Set
- Front
- Back
OR formula |
ad/bc |
|
RR formula |
[a/a+b] / [c/c+d] |
|
Attributable risk formula |
[a/a+b] - [c/c+d] |
|
Random error reduces ______ of a test. Systematic error reduces _______ of a test. |
precision (reliability); accuracy (validity) |
|
Selection bias |
non random assignment to study group |
|
Recall bias |
knowledge of presence of a disorder affects recall by subjects |
|
Sampling bias |
results not generalizable b/c subjects are not representative of generable population |
|
Late-look bias |
information gathered at inappropriate time |
|
Procedure bias |
more attention paid to treatment group stimulating greater compliance |
|
Lead-time bias |
Early detection confused with increased survival |
|
Pygmalion effect |
researchers belief in a treatment changes the outcome of the treatment |
|
Hawthorne effect |
study group changes behavior to meet the expectation of the researcher |
|
Positive skew. Tail on the ______. Mean ___ Median ____ Mode |
Right. Mean > Median > Mode |
|
Negative skew. Tail on the ______. Mean ___ Median ____ Mode |
Left. Mean < Median < Mode |
|
Null hypothesis (Ho) definition? |
No association between disease and risk factor |
|
Alternative hypothesis (HI) definition? |
There IS an association between disease and risk factor |
|
Type 1 error definition (and greek letter)? |
Alpha. Stating association exists when none exists. Mistakenly reject null hypothesis. |
|
Type 2 error definition (and greek letter)? |
Beta. Stating that no association exists when one actually does exist. Mistakenly accept null hypothesis. |
|
Power. Definition and formula. |
1-Beta. Probability of rejecting the null hypothesis when it is in fact false (likelihood of finding a difference when one exists) |
|
SEM ___ SD. SEM __________ as n increases. |
<, decreases |
|
Simple confidence interval formula? |
[mean + Z(SEM)] to [mean - Z(SEM)] |
|
For CI at 95%, Z = ? |
1.96 |
|
Mnemonic for mandatory reportable diseases (nationwide)? |
Hep, Hep, Hep, Hooray, the SSSMMART Chick is Gone! HepA, HepB, HepC, HIV, Salmonella, Shigella, Syphilus, Measels, Mumps, AIDS, Rubella, Tuberculosis, Chickenpox, Gonorrhea |
|
Four ethical principles and definitions? |
1. Autonomy = honor patient preference 2. Beneficence = Physician acts in pt best interest 3. Non-maleficence = Do no harm 4. Justice = treat all persons fairly |
|
Sensitivity formula |
a/a+c Proportion of people with disease who test positive |
|
Specificity formula |
d/d+b Proportion of people without the disease who test negative |
|
PPV formula |
a/a+b (proportion of positive tests that are truly positive) |
|
NPV formula |
d/c+d (proportion of negative tests that are truly negative) |
|
Case control study asks _____ |
What happened (compares those with disease to those without, can calculate OR) |
|
Cohort study asks ______ |
What will happen (Compares those with a risk factor to those without and sees who gets disease; can calculate RR) |
|
Cross sectional study asks ________ |
What is happening (collects data from a group of people to assess disease frequency; beware ecologic fallacy, also can't establish temporality) |
|
Paired T-test is best for (give study scenario) |
Same subject with pre-post measurement of a variable (Bobby's LDL pre statin, Bobbys LDL post statin) |
|
Student T-test is best for (give study scenario) |
Compare the means of two independent groups with normal distribution pre-post measurement (lactate levels in 500 males and 500 females before and after a marathon) |
|
Chi squared-test is best for (give study scenario) |
Both variables are dichotomous (med students and dental students ordering coffee or tea...common in 2x2 tables; i.e.: effect of treatment on disease) |
|
ANOVA-test is best for (give study scenario) |
Compares the means of 3 or more groups on a continuous variable (Effect of drugs A, B, and C on males and females) |