Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Biostatistics > Biostatistics > Flashcards

Biostatistics Flashcards

1
Q

What is the mode?

A

The number which occurs most often

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is the mean?

A

The average of the values

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is the median?

A

The value in the middle of the ranking when in order

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

How can you determine if the CI (Confidence Interval) is Statistically Significant by comparing Difference data (mean)?

(without p-value)

A
  • CI (Confidence Interval) would be based on Subtraction
  • If the interval crosses 0, than it is Not statistically significant
    e. g. (-0.26 - 0.98)
  • If the interval does not cross 0, than it is Statistically significant
    e. g. (18 - 58)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

If alpha is 0.05, what is the CI (Confidence Interval) and the p-value?

If alpha is 0.01, what is the CI (Confidence Interval) and the p-value?

A

CI: 95% (1 - 0.05 = 0.95 * 100 = 95%)
p-value: 0.05

CI: 99%
p-value: 0.01

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

How can you determine if the CI (Confidence Interval) is Statistically Significant by comparing Ratio data (Relative Risk, Odds Ratio, and Hazardous Ratio)?

(without p-value)

A
  • CI (Confidence Interval) would be based on Division
  • If the interval crosses 1, than it is not statistically significant
    e. g. (0.61 - 1.29)
  • If the interval does not cross 1, than it is Statistically significant
    e. g. (0.72 - 0.99)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Type I error is denoted by …?

A

Alpha

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Type II error is denoted by …?

A

Beta

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Type I error is when…?

A

The Null hypothesis was rejected in error

So, saying there is statistical significance when there wasn’t

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Type II error is when…?

A

The Null hypothesis was accepted when it should have been rejected

So, saying there is no statistical significance when there was

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Null hypothesis definition?

A

A Null hypothesis states that there is no statistically significant difference between the groups

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is the power of a study?

A

The Power of a study is the probability that the test weill reject the null hypothesis correctly

i.e. It is the power to avoid a type II error

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

If the power is set to Beta 0.2, what is the power of the study?

What does this mean?

A

80%

There is a 20% chance of missing a true difference and making a type II error
(saying there is no statistical significance when there really was)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

If the power is set to Beta 0.1, what is the power of the study?

What does this mean?

A

90%

There is a 10% chance of missing a true difference and making a type II error

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What dose a Relative Risk (RR) aka Risk Ratio of 1 mean?

A

Equal risk b/w the interventions and the control group

aka. Intervention had no effect

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What dose a Relative Risk (RR) aka Risk Ratio of > 1 mean?`

A

The treatment INCREASED, GREATER the risk of the outcome or endpoint

aka. Intervention is no good

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What dose a Relative Risk (RR) aka Risk Ratio of < 1 mean?

A

The treatment DECREASED, LOWERED the risk of the outcome or endpoint

aka. Intervention had a positive outcome

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What does RRR stand for?

What is it measuring?

A

Relative Risk Reduction

  • Calculated after the Relative Risk (RR) and indicated how much the risk is reduced in the treatment group compared to the control group
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What does ARR stand for and Why is it better than RRR?

A

Absolute Risk Reduction

  • It is more useful than RRR b/c it includes the reduction in risk and the incidence rate
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What is NNT?

A

Number Needed to Treat

  • It is the number of patients who need to be treated for a certain period of time in order for 1 patient to benefit.
    e. g. if the NNT is 9, it means that for every 9 patients to get the intervention, 1 patient benefited

Note: The lower the better

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

How do you calculate NNT?

A

NNT = 1 / (Risk in control group - risk in treatment group)

OR

NNT = 1 / ARR

Note: Use 1 if data is presented in decimal, Use 100 if in percentage form

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What is NNH?

A

Number Needed to Harm

  • It is the number of patients who need to be treated for a certain period of time in order for 1 patient to experience harm.

Note: The higher the better

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

How do you calculate NNH?

A

NNH = 1 / (Risk in control group - risk in treatment group)

OR

NNT = 1 / ARR

Note: Use 1 if data is presented in decimal, Use 100 if in percentage form

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

In terms of calculating NNT and NNH, what is the main difference?

A

In NNT you round up.
e.g. NNT is 52.1 —> 53 patients

In NNH you round down.
e.g. NNH is 52.1 —-> 52 patients

  • Depends on whether the outcome is looking at harm or a positive outcome.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

When is Odds Ratio used? In what type of study styles?

A

Odds Ratio is used with Case-Control studies because these types of studies are done retrospectively.

Note: In contrast, relative risk is a prospective

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

What does Odds Ratio look at?

A

The probability that an event will occur or not occur

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

What does Hazard Ratio look at?

A

Look at the rate at which an unfavorable event occurs within a shor period of time

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

What dose an Odds Ratio (OR) or Hazard Ratio (HR) of < 1 mean?

A

The event rate in the treatment group is LOWER, REDUCED than the event rate in the control group

e.g. A HR of 0.5 for an outcome of death indicated that there are half as many deaths in the treatment group.

NOTE: when interpreting, make sure you subtract from 1. i.e. if RR is 0.77 then interpretation is 23% decreased in risk.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

What dose an Odds Ratio (OR) or Hazard Ratio (HR) of > 1 mean?

A

The event rate in the treatment group is HIGHER, GREATER than the event rate in the control group

e.g. A HR of 2 for an outcome of death indicates that there are twice as many deaths in the treatment group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

What dose an Odds Ratio (OR) or Hazard Ratio (HR) of = 1 mean?

A

The event rate is the same in the treatment and control arms.
i.e. There is no advantage to the treatment

31
Q

For a Discrete or Categorical Data , what type of statistical test should be performed?

A

One arm: Chi-square test

Two arms: Chi-square test OR Fisher’s exact test

32
Q

For a Numerical or Continuous Data, what type of statistical test should be performed?

A

One arm: One-sample T-test

Two arms: Independent or Unpaired student T-test

Three or more arms: ANOVA or F-test

33
Q

Correlation is a statistical technique that is used to…?

A

Determine if one variable changes is related to another variable.

NOTE: correlation doe NOT prove causal relationship

34
Q

Regression is a statistical technique that is used to…?

A

Describe the relationship b/w a dependent variable and one or more independent variable

Note: Most commonly used when researches need to assess multiple independent variables or need to control for many confounding factors

35
Q

Sensitivity describes ….?

A

How effective a test is at identifying patients with the condition

i.e. The True Positive

36
Q

Specificity describes ….?

A

How effective a test is at identifying patients withOUT the condition
So, ‘specific’ to that condition

i.e. The True Negative

37
Q

What is the difference b/w Intention To Treat (ITT) and Per Protocol (PP) analysis?

A

Intention To Treat (ITT) includes all patient originally allocated to each arm even if the didn’t complete the study

while

Per Protocol (PP) includes only those who completed the full study according to the protocol

38
Q

Forest Plots: definitions and steps to interpret info …

A

Horizontal line: The length of the CI (Confidence Interval)

Vertical line: The line of no effect, where you can interpret significance

Box on horizontal line: Effect estimate

Diamonds on horizontal line: Pooled results

Step 1:

  • Is it a Difference Data or a Ratio Data?
  • Difference Data: the vertical line should be set at 0.
  • Ratio Data: the vertical line should be set at 1.

Step 2:

  • For each variable, if the horizontal line crosses the vertical line, the data is Statistically Insignificant
  • For each variable, if the horizontal line Does Not cross the vertical line, the data is Statistically Significant
39
Q

Retrospective OR Prospective study?

Case-control studies

A

Retrospective

40
Q

Retrospective OR Prospective study?

Cohort studies

A

Retrospective

OR

Prospective

41
Q

Retrospective OR Prospective study?

Randomized controlled trials

A

Prospective

42
Q

Meta-analyses definition

A

Analyzes the results of multiple studies in order to develop a conclusion that has greater statistical power

43
Q

Case-control studies definition

A

Compares cases (patients with disease) to controls (patients without disease)

44
Q

Cohort studies definition

A

Compares patients with an exposure to those without an exposure

45
Q

Case Report vs Case Series difference

A

Case Reports: single patient

Case Series: few/multiple patients

46
Q

Rank type of studies from MOST to LEAST Reliable

A

****Systematic Reviews and Meta-Analyses

*****Randomized Controlled Trials

**Cohort Studies

***Case-Controlled Studies

**Case Series and Case Reports

*Expert Opinion

47
Q

Continuous data definition….

A

Data is provided by some type of measurement which has unlimited options (theoretically) of continuous value

48
Q

Types of Continuous data

A
  • Ratio Data

- Interval Data

49
Q

Discrete or Categorical data definition….

A

Data fits into a limited number of categories

50
Q

Types of Discrete or Categorical data

A
  • Nominal Data

- Ordinal Data

51
Q

Nominal Data definition….

A

A type of Discrete or Categorical data in which categories are in arbitrary order

e.g. gender, ethnicity, martial statue, mortality

Note: if Dichotomous data; only 2 categories

52
Q

Ordinal Data definition….

A

A type of Discrete or Categorical data in which categories are ranked in a logical order but the difference b/w categories is NOT equal

e.g. NYHA Function call I - IV, 0-10 pain scale

NOTE: Have nothing in b/w like no decimals, no 1.4

53
Q

Interval Data definition….

A

A continuous data that has legitimate mathematical values

e.g. celsius tem scale

0 ≠ NONE

54
Q

Ratio Data definition….

A

A continuous data that has EQUAL INTERVALS b/w values including a meaningful zero point

e.g hight, weight, time

0 = NONE

55
Q

If your mode and median are greater than your mean than your data is….

A

Negatively (left) skewed

56
Q

When data is normally distributed ….

A
  • The mean, median, and mode are all the same value
  • 68% if the values fall within 1 SD of the mean
  • 95% if the values fall within 2 SDs of the mean
  • 99.7% if the values fall within 3 SDs of the mean
57
Q

Data is skewed to the right (positively) when ….

A
  • There are more low values in the data set
  • The Outliers are the high values
  • Mean > Mode
58
Q

Data is skewed to the left (negatively) when ….

A
  • There are more high values in the data set
  • The Outliers are the low values
  • Mean < Mode
59
Q

Independent variable is the…

A

Change or intervention by the researcher

60
Q

Dependent variable is the…

A

The outcome of the intervention (independent variable)

61
Q

What is the most appropriate value to use when representing skewed or non-normally distributed data?

A

Median

62
Q

To find RR…..formula?

A

RR = Risk in treatment group / Risk in control group

63
Q

To find AR…..formula?

A

AR = % of Incidence exposed - % of Incidence unexposed

64
Q

What is more preferred for Nominal data? Mean, Median or Mode?

A

Mode

65
Q

What is more preferred for Ordinal data? Mean, Median or Mode?

A

Median

66
Q

What is more preferred for Continuous data which is normally distributed? Mean, Median or Mode?

A

Mean

67
Q

What is Standard deviation (SD)?

A

Standard deviation (SD) indicates how spread out the data is and to what degree the data is dispersed away form the mean.

The higher the dispersion of data the lager the SD

68
Q

Margin of error is denoted by …..?

A

Alpha

69
Q

Incidence rate definition

A

Incidence rate = New reported cases / summed person-years of observation (avg population during time interval)

70
Q

Prevalence rate definition

A

Prevalence = Cases in a population in a given time period / total population at that time

71
Q

Power is denoted by ….?

A

Beta

72
Q

CI is denoted by …?

A

Alpha

73
Q

p-value is denoted by …?

A

Alpha

Biostatistics (2 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions