Stats

Question 1

T Test

Answer 1

-used to compare the difference between the means of two groups

Question 2

Analysis of Variance

Answer 2

• ANOVA

- compares the difference between the means of two or more groups

Question 3

Chi Square Test

Answer 3

• used to check for an association between 2 categorical variables (ie. gender and smoking status random vs. correlation)
• given as number of people for example, not mean number

Question 4

Normal Distribution Rule

Answer 4

68/95/99

68% within -1 and +1 standard deviations, etc.

Question 5

Hawthorne Effect

Answer 5

Subjects change their behavior once they realize they are being studied.

Question 6

Alpha

Answer 6

• probability of rejecting null hypothesis when null hypothesis is true
• related to type 1 error (you are pregnant to a dude)

Question 7

Beta

Answer 7

• probability of failing to reject null hypothesis when null hypothesis is false
• type 2 error (you are not pregnant to pregnant lady)
• 1-B = power (how many people needed to find significant difference)

Question 8

Case Series

Answer 8

• medical research that tracks subjects with known exposure

- no control necessarily

Question 9

How to Find Number Needed to Harm/Treat

Answer 9

• calculate absolute risk difference between treatment and placebo
• NNH or T = 1/absolute risk difference

Question 10

Effect Modification

Answer 10

• when the effect of the main exposure on the outcome is modified by another variable
• not bias or confounding
• significant difference with stratification (not so with confounding)