Flashcards in First Aid: Behavioral Science Deck (16):

1

## What is the difference between a case-control and cohort study?

###
Case-control is only retrospective (What happened)

Cohort can be retro or prospective (Who will develop disease or Who developed disease comparing exposed vs. nonexposed)

2

## What does sensitivity tell you? Specificity?

###
Sensitivity = Rate of TRUE POSITIVES

SNNOUT - When a test is highly sensitive it has a high likelihood of ruling OUT disease in those who are negative.

Specificity = Rate of TRUE NEGATIVES

SPPIN - When a test is highly specific, it has a high likelihood of ruing IN disease in those who are positive

3

## What does sensitivity tell you? Specificity?

###
Sensitivity = Rate of TRUE POSITIVES

SNNOUT - When a test is highly sensitive it has a high likelihood of ruling OUT disease in those who are negative.

Specificity = Rate of TRUE NEGATIVES

SPPIN - When a test is highly specific, it has a high likelihood of ruing IN disease in those who are positive

4

## What is the difference between standard deviation and standard error of the mean?

###
SD = variability from the mean

SEM = sample mean vs. population mean variability

5

## What do bimodal distributions suggest?

### Two different populations (e.g. suicide rate by age)

6

## What is the difference between Type 1 and Type II error (alpha vs. beta)? How can either be avoided?

###
Alpha = false positive; you saw an association when one really wasn't there

-avoid by using p value 5% chance of error

Beta = false negative; you missed an association that is there

-avoid by increasing the power of your study (increase sample size); increasing precision of measurement; increasing expected effect size

7

## What is the difference between Type 1 and Type II error (alpha vs. beta)? How can either be avoided?

###
Alpha = false positive; you saw an association when one really wasn't there

-avoid by using p value 5% chance of error

Beta = false negative; you missed an association that is there

-avoid by increasing the power of your study (increase sample size); increasing precision of measurement; increasing expected effect size

8

## What is the purpose of the Confidence Interval? How do you calculate?

###
to determine if significant difference exists between two groups. If CI between 2 groups overlap, there is no significant difference.

CI = [mean - Z(SEM)] to [mean + Z(SEM)]

Z = 1.96 for 95%, Z=2.58 for 99%

9

## What is the purpose of the Confidence Interval? How do you calculate?

###
to determine if significant difference exists between two groups. If CI between 2 groups overlap, there is no significant difference.

CI = [mean - Z(SEM)] to [mean + Z(SEM)]

Z = 1.96 for 95%, Z=2.58 for 99%

10

## What does the t-test check for? ANOVA? Chi-square?

###
t-test - check difference between means of 2 groups

ANOVA - check difference between means of 3 or more groups

Chi-square - Chi-tegorical - checks difference between 2 or more percentages or proportions of categorical outcomes (not mean values)

11

## What does the Pearson coefficient (r) measure?

###
Measures the level of correlation between 2 variables. the closer the absolute value of r is to one, the greater the correlation.

r can range from -1 (negative correlation) to +1 (positive correlation)

12

## What does the Pearson coefficient (r) measure?

###
Measures the level of correlation between 2 variables. the closer the absolute value of r is to one, the greater the correlation.

r can range from -1 (negative correlation) to +1 (positive correlation)

13

## What is a key difference between a living will and medical power of attorney?

### Medical power of attorney is more flexible and can be revoked at anytime the patient wishes (regardless of competence).

14

## What is the priority of surrogates?

### Spouse > adult children > parents > adult siblings > other relatives

15

## What is the priority of surrogates?

### Spouse > adult children > parents > adult siblings > other relatives

16