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;
41 Cards in this Set
- Front
- Back
|
What is a cross sectional study measuring and what does it use to measure? |
It is asking what is happening study that collect data from a group of people to measure frequency of disease Measure is disease prevalence |
|
|
What is a Case control study measuring and what unit of measure is it using? |
studies what has happened THose who have the disease vs those who dont Odds ratio is used: AD/BC |
|
|
What is a Cohort study measuring and what is its tool? |
Measures exposed vs unexposed and ask who will develop the disease (prospective) or who has developed the disease ( retrospective) uses risk Ratio |
|
|
What is sensitivity? What is the equation? Characteristics? |
proportion of all the people with the disease who test positive (rules out disease with a negative test) Tp/(TP+FN) or A/(A+C) values approaching 100% indicate low FN rate high sensitivity test used for screening with low prevalence disease if sensitivity=1 then FN must be zero and all negatives are true negatives |
|
|
What is specificity? |
Proportion of all the people without disease who test negative (rules in disease with a positive test) TN/(TN+FP) or D/D+B vales appraoching 100% indicates low false positive rate Used for confirmation after a screening test |
|
|
what is PPV? Equation? |
PPV is the proportion of positive results that true positive the probability that a person actually has the disease given a positve test result TP/(TP+FP) or A/(A+B) varies irectly with prevalence |
|
|
what is NPV and equation? |
Proportion of people without disease who test true negative probability that a person actually is disease free when they test negative TN/(TN+FN) or D/(D+C) varies inversly with prevalence |
|
|
Incidence vs prevalence? |
Incidence is number of new cases/existing pop as risk DURING SAME TIME PERIOD prevalence= existing cases/existing pop at risk Prevalence=incidence rate x average disease duration Prevalence> incidence for chronic diseases |
|
|
Odds ratio? |
AD/BC odds that group with disease was exposed to risk factor vs groups without disease was exposed |
|
|
Relative Risk |
Risk of developing diseease in exposed group vs risk in unexposed group RR=A/(A+B)/ C/(C+D) |
|
|
Relative risk reduction |
proportion of risk reduction attributable to the intervention as compared to control RRR=1-RR |
|
|
Attributable risk? |
difference in risk between exposed and unexposed groups AR= A/(A+B) - C/(C+D) |
|
|
absolute risk reduction |
difference in risk( not proportion) attributable to intervention vs control |
|
|
Number needed to treat? |
1-ARR |
|
|
Number needed to harm |
Nmber of patients who need to be exposed to risk factor for 1 patient to be harmed 1-AR |
|
|
Precision vs Accuracy? |
Precision is the consistency and reproductability of a test (random error). Increase precision decreases standard deviation? Accuracy is the trueness of test measurements |
|
|
Non random assignment to participate in a study group. Bias? |
Selection Bias |
|
|
How to reduce selection Bias? |
randomization |
|
|
What is Berkson Bias and what type of Bias is it? |
Berkson Bias is a selection bias and looks at- outpatient study |
|
|
If the awareness of a disorder alters recall by subject, what kind of Bias is that? and how to reduce? |
Recall Bias and you need to decrease time from exposure to follow up |
|
|
If groups who know theyre being studied behave differently than they would otherwise. what is the name of this, the type of Bias and the way to reduce it? |
Hawthorne effect and it is a measurement Bias FIx with use of Placebo control groups with blinding |
|
|
Loss of follow up is which type of Bias? |
selection bias |
|
|
If the subject in different group are treated differently, what is this bias? |
procedure Bias |
|
|
If a researcher believes int he efficacy of a treatment therefore changing the outcome of that treatment which effect and Bias is this? |
Pygmalion effect( self fulfilling prophecy) Observer expectancy Bias |
|
|
When a factor is related to both the exposure and outcome but NOT on the casual PAthway, this factor distorts or confuses effect of exposure on outcome. what Bias is this? how to reduce? |
confounding Bias Multiple/repeated studies crossover studies |
|
|
What is lead time Bias? |
early detection is confused with increased survival. |
|
|
What is the equation for SEM? |
SEM=SD(square root N) SEM decreases as N increases |
|
|
For SD what is the 68/95/99 rule? |
68% within 1 SD 95 within 2 SD 99 within 3 SD |
|
|
What does a positive skew vs negative skew look like? |
positive= mean>median>mode and tail to right negative= mode>median>mean and tail to LEFT |
|
|
Null hypothesis vs alternative? |
NUll is of no difference alternative is of some difference Low P is not compatible with null hyp |
|
|
When do reject the null hypo? When do you accept the null? |
when P<0.5 when P>0.5 therefore results not significant |
|
|
Explain a type 1 error and how it relates to the null hypothesis and P? |
a type one error is stating an effect when there isnt one. (trying to get over) The null hypothesis is incorrecly rejected in favor of the alternative |
|
|
Explain a type II error, how it relates to the null hypothesis? |
stating that there was no difference when there was (trying to hide your ****) |
|
|
Explain B and how it relates to power |
B is the probability of making a type two error |
|
|
What is power? |
power=1-B increase power by increased sample size increased expected effect size increased precision of measurement |
|
|
What is a meta analysis? |
pools data and integrates results from several similar studies |
|
|
What is the Confidence interval equation? |
CI= range from [mean-Z(sem)] to [mean-Zsem] 90% CI and z=1.6 95% CI and z=1.96 99% CI and z=2.58 |
|
|
What does the confidence interval mean? |
range of values which a specified probability of means of repeated samples would fall. |
|
|
1.T-test? 2.anova? 3. chi-square |
1. t-test compares two means 2. anova is 3 or more means 3. chisquare- checks diff bw two or more percentages |
|
|
Exceptions to informed consent? |
-Patient lacks decision making capacity or is legally incompetent - Implied consent in emergency -theraputic privalege -waiver |
|
|
developmental milestones 0-12 yr 12-36 yr 3-5 yr |
0-12: |
