2 - Biostatistics 1 - Basic Principles

Question 1

Statistics

Answer 1

Encompasses methods of collecting, summarizing, analyzing & drawing conclusions from data

Question 2

Biostatistics

Answer 2

The application of statistics to medical, biological and public health data

Question 3

Descriptive Statistics

Answer 3

A means of organizing and summarizing observations

Question 4

Statistical Inference

Answer 4

A process of drawing conclusions about a population from a sample

Question 5

Population

Answer 5

A collection of all subjects of interest

Question 6

Sample

Answer 6

A representative subset of the population that can be studied

Question 7

Types of Sample

Answer 7

Random (every 10th person)

Convenient (this cluster all together)

Question 8

Parameter

Answer 8

Rule (applicable to population)

Question 9

Statistic

Answer 9

Value (measured from sample)

Question 10

Variable

Answer 10

A characteristic or condition of an observation that can take on different values

Question 11

Dependent Variable

Answer 11

Outcome, variable of interest

Question 12

Independent Variable

Answer 12

Exposure, predictor variables

Question 13

Types of Categorical (Qualitative) Data

Answer 13

Nominal

Ordinal

Question 14

Nominal Data

Answer 14

Values fall into categories of classes that are mutually exclusive and are not ordered
Dichotomous/Binary - Only Two Possible Categories (Dead/Alive)
Multiple Categories - (Race, Blood Type)

Question 15

Ordinal Data

Answer 15

Values fall into categories or classes where order matters (Disease stage, satisfaction level)

Question 16

2 Types of Numerical (Quantitative) Data

Answer 16

Discrete

Continuous

Question 17

Discrete Data

Answer 17

Data has a numerical value that takes only certain whole number values (# of kids in a family)

Question 18

Continuous

Answer 18

Data has a numerical value that can have any value in a continuum (height, weight, time)

Question 19

Frequency Distributions - Data Representations

Answer 19

Categorical Data - Pie Charts, Bar Charts
Continuous Data - Histogram
Continuous Data - Box Plot

Question 20

Unimodal Frequency Distribution

Answer 20

One Peak

Question 21

Bimodal Frequency Distribution

Answer 21

Two Peaks

Question 22

Right Skew Frequency Distribution

Answer 22

Tail to the right (more low values than high values)

Question 23

Left Skew Frequency Distribution

Answer 23

Tail to the left (more high values than low values)

Question 24

Central Tendency Descriptors

Answer 24

Mean
Median
Mode

Question 25

Mean

Answer 25

Average Pro - Uses all Data Values Con - Distorted by outliers and skewed data

Question 26

Median

Answer 26

Middle value of the ordered data set Pro - Not distorted by outliers or skewed data Con - Ignores most of the information

Question 27

Mode

Answer 27

Most frequently occurring value Pro - Easily determined for categorical data Con - Ignores most of the information

Question 28

Spread

Answer 28

``` Measures to describe the variability of dispersion Range IQR Variance Standard Deviation ```

Question 29

Range

Answer 29

Difference between largest and smallest values Pro - Easily Determined Con - Distorted by Outliers

Question 30

IQR (Inter-Quartile Range)

Answer 30

Difference between the 25th and 75th percentiles Pro - Unaffected by outliers Con - Appropriate for skewed data

Question 31

Variance

Answer 31

Each deviation is squared

Question 32

Standard Deviation

Answer 32

Square root of variance, an average of deviations from the observations from the mean

Question 33

Inferential Statistics

Answer 33

The process of drawing conclusions about a population from a sample. Starts with a Null Hypothesis and an Alternative Hypothesis

Question 34

Null Hypothesis (H0)

Answer 34

Assumes no effect in the population

Question 35

Alternative Hypothesis (H1)

Answer 35

Assumes effect in the population

Question 36

Steps for Hypothesis Testing in Inferential Statistics

Answer 36

Assume Null Hypothesis to be true Collect data from the sample to disprove Null Hypothesis Either reject H0 (if there is convincing/strong evidence against it) or fail to reject H0

Question 37

Type 1 Error

Answer 37

Reject the null when the null is actually true | Probability - α

Question 38

Type 2 Error

Answer 38

Fail to reject the null when the null is false | Probability - β

Question 39

Power

Answer 39

The probability of rejecting H0 when it is false (Not committing a Type 2 error) = 1 - β Aim for 100%, settle for 80 - 90%

Question 40

Factors influencing power

Answer 40

Sample Size Variability Effect of Interest Significance Level

Question 41

How does Sample Size influence Power?

Answer 41

Power increases with larger samples

Question 42

How does Variability influence Power?

Answer 42

Power increases as variability decreases

Question 43

How does Effect of Interest influence Power?

Answer 43

Power increases with larger effect size

Question 44

How does Significance Level influence Power?

Answer 44

Power increases with larger α

Question 45

α

Answer 45

The chance of Type 1 Error we are willing to accept, decided prior to collecting data Typically α = 0.05 Using a smaller α will increase your β

Question 46

P-Value

Answer 46

The probability of obtaining our results or something more extreme given that the null hypothesis is true

Question 47

P

Answer 47

Reject H0 and conclude that results are significant at the α% level

Question 48

Confidence Interval

Answer 48

Estimated range of values likely to include the population parameter. Point estimate, 95% CI (upper limit, lower limit)

Question 49

What do P-Values tell you about?

Answer 49

Statistical Significance

Question 50

What do Confidence Intervals tell you?

Answer 50

Statistical Significance + Information about Size and Direction of the effect.

Question 51

Statistical Significance

Answer 51

90% Confidence Interval does not include the null A very small difference that is not clinically meaningful can reach statistical significance if the sample size is large enough

Question 52

Clinical Significance

Answer 52

Effect Estimate is above the threshold for clinical relevance