Brainscape's Knowledge GenomeTM

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


See full index

Epidemiology 3 > Class 29-37: Intro To Biostats > Flashcards

Class 29-37: Intro To Biostats Flashcards

1
Q

How do researchers choose to accept or reject the null hypothesis?

A

Statistical analysis

Based on p and confidence intervals.

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

3 primary levels for variables based on answers:

A

Nominal
Ordinal
Interval

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

2 key attributes of data measurement:

A

Magnitude

Consistency of scale.

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

Each attribute can be assessed w/ a “yes” or “no” response to the inquiry of:

A

“Does it have it?”

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

No magnitude and no consistency

Dichotomous/binary and NON ranked

Simply labeled variables w/o quantitative characteristics (dichotomous)

A

Nominal

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

Has magnitude but no consistency of scale

Ranked categories

Pain scales, severity of disease

A

Ordinal

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Has magnitude and consistency of scale

Anything drawn w/ exact values

A

Interval / ratio

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

Nominal and ordinal attributes are considered:

Interval attributes are considered:

A

Discrete; continuous

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

Which statistical tests are selected based on level of data being compared

A

ALL statistical tests

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

After data, is collected we can appropriate go _____ in specificity/detail of data measurement (levels), but we can never go _____

A

Down; up

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

Non-comparative. Simple description of various elements of the study’s data

A

Descriptive statistics.

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

Measures of central tendency and dispersion

A

Mode/ median/ mean
Outliers
Minimum / max /. Range
Interquartile range= Q3-Q1

Know how to calculate these b/c it will be free points on the test.

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

The average of the squared differences in each individual measurement value and the groups mean

A

Variance- from the mean

The larger the number= the more variable

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

Square root of variance value (restores units of mean)

A

Standard deviation (SD)

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

Normally distributed= (one word)

A

Symmetrical

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

What graph is found when mean / median / mode are equal or near-equal:

A

Normally distributed

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

Interval data must be:

A

Normally distributed.

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

Stats tests useful or _____________________ data are called parametric tests

A

Normally-distributed

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

SD in normal distribution:

A

68%-top of bell curve

95%= +2 SD

99.7%= +3 SD

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Parametric tests

A

Fixed mean / median / mode

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

Positively skewed graph

A

Asymmetrical distribution w/ one tail longer than the other

A distribution is skewed anytime the median differs from the mean (when mean is higher than median.

Mean > median

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

Negatively skewed graph:

A

Asymmetrically distributed w. One tail loner than another to the left.

Distribution is skewed anytime the median differs from the mean (when mean is lower than median)

Mean < median

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q 
Mean = 15.15
Median= 3
Mode= 0
A

Mean > median

Positively skewed

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

Outliers do not change:

A

The mode

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

Range is:

A

subtraction btw min and max.

The difference btw the 2 values.

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

Mean 5.05
Median: 7.0
Mode: 7

Skewed?

A

Mean < median

Skewed to the left

Negatively skewed.

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

Mean: 44.31
Median: 47.0
Mode: 49

Skewed?

A

Mean < median

Negative skewed.

Shift to the left

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

What Age extremes represent 95% of data?

A

Mean + (2xSD)

Mean - (2xSD)

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

A a measure of the asymmetry of a distribution

Perfectly normal distribution is symmetric and has value of 0

A

Skewness

Want to be closer to 0

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

A measure of the extent to which obs’s cluster around the mean. For a normal distribution, the value of 0

+= more cluster

-=less cluster

A

Kurtosis

Want to be closer to 0

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

Positive kurtosis =

A

More clustered

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

What is the age range of middle 68%?

95%

99%

A

One SD

2 SD

3 SD

Add to mean 3 times or

subtract to mean 3 time ??

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
33
Q

Which of mean, mode, median could adequately represent the measure of central tendency for the gender variable?

A

Mode values would describe the # of each genders ( the most frequent)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
34
Q

Which variable is the most descriptive variable of nominal data

A

Mode is the most descriptive variable of data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
35
Q

What data type can median/ mean/ and mode ALL be defendable

A

Interval

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
36
Q

Median and mode defendable for data type?

A

Ordinal

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
37
Q

Req’d assumptions of interval data for proper parametric test:
(2)

A
  1. Normally- distributed -look at mean,median,mode-look at graph, look at skewness values,
  2. Equal variances:
    run statistical test: levenne’s test
  3. Randomly-derived and independent
    * if these are not good enough, then interval / parametric CANT be used
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
38
Q

Common statistical test for parametric test/interval data:

Compares equal variances

A

Levene’s test

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
39
Q

How to handle data that’s not normally distributed:

A
  • could use ordinal family stat. Test. (Non-parametric tests)
  • could throw out outliers.
  • transform data to a standardized value. (Z score or log)- can create a normal distribution. [issue: how do you log BP?]

Segars-picks ordinal typically
*TQ

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
40
Q

What should you always do for data interpretation?

A

Run descriptive statistics and graphs

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
41
Q

Researchers will either accept or reject this perspective, based on:

A

Statistical analysis

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
42
Q

Rejecting the null hypothesis when you shouldn’t have!

A

Type 1 error (alpha)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
43
Q

Dont reject the null when you should have

A

Type II error (beta)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
44
Q

The ability of a study design to detect a true difference if one exists btw group-comparisons….

The level of accuracy in corectly accepting/rejecting the null

A

Power (1-ß)

ß=beta=type 2 error

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
45
Q

The larger the sample size, the greater the likelihood (ability) of detecting a difference if one truly exists.

Increase in power

A

Sample size.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
46
Q

Most researchers accept up to _____ type 2 beta error rate…so must researchers want 80% chance of finding differences

What about alpha error rate?

A

20% of the BETA rate!!

5% for type 1 (alpha) rate

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
47
Q

The number one issue in power that ppl worry about?

A

Sample size!

48
Q

3 common characteristics for sample size determination:

A
  1. Minimum difference btw groups deemed “significant”
  2. Expected variation of measurement.
  3. Alpha (type 1) and beta (type 2) error rates and confidence interval.
    - add in anticipated drop-outs or loss to f.u
49
Q

Statistical tests determine the possible error rate or chance in compared difference or relationship btw variables

A

P values

Or type 1 error rate

Or alpha error rate

50
Q

How do p value and type 1 error rate differ?

A

They dont theyre the same thing

51
Q

% chance of making type 1 error.

By convention, accept about 5% risk of being wrong

A

P value

52
Q

If P value is < 5% (or whichever is preset value), can you reject the null?

A

Yes! This is statistically significant.

53
Q

Authors that pick 1% preset p value are _____likely to reject the null

A

LESS

54
Q

If the p value is set higher (~10%), it is ________ to find group differences

A

Easier

But they have a higher risk of being WRONG

55
Q

Define probability value:

A

Probability of making type 1 error

56
Q

Know how to explain the statistical significance of a p value in own words:

A

The P value is the probability or chance of making a type I error if rejecting the null hypothesis.

57
Q

What 2 areas do you love to see high p values?

A

Table 1 characteristics

And

Levenne’s test —-this shows that the studies randomization process worked!

58
Q

Most common selections are 90,95,99%

Calc at an a priori percentage of confidence that statistically the real difference or relationship resides.

Based on: variation in sample and sample size

A

Confidence interval (CI)

59
Q

Journals are moving away from solely reporting p values; or showing them at all.

A

Now people are using CI

Confidence interval.

60
Q

Single best guess at relationship or difference btw groups

The value of 0 represents no difference

Range represents SD

A

Point estimate

61
Q

If CI crosses 1.0 or an absolute difference of 0.0:

A

No difference

Sameness

NOT SIGNIFICANT = p>0.05

62
Q

Slide 63: bivalirudin study. Interpret MAjor bleeding CI’s:

A

Compared to unfractionated heparin, Bivalrudin 34% less likely to have major bleed than heparin,

and can be said w. 95% confidence that the real group difference is btw 51% - 10% reduced risk,

which is statistically significant.

63
Q

Looking at forest plots, you dont want CI to cross:

A

1 on the x axis

64
Q

Important consideration:

A

Does statistical significance actually confer meaningful, clinical significance?

65
Q

4 key questions to selecting the correct statistical test:

A
  1. What data level is being recorded?**most important
  2. What type of comparison/assessment is desired?
  3. How many groups are being compared?
  4. Is the data independent or related (paired)?
66
Q
  1. What data level is being recorded?
A

What data have magnitude? (Y/n)

Does data have a fixed interval? (Y/n)

-the remaining 3 questions get you around the other portions of each individual sheet

67
Q
  1. What type of comparison/assessment is desired?
A

Correlation test

68
Q

Provides a quantitative measure of the strength and direction of a relationship btw variables

A

Correlation

Values range from -1 to +1

69
Q

A correlation that controls for confounding variables

A

Partial correlation

70
Q

Are 2 things related and how are they related?

A

Correlation

71
Q

Positive correlation:

+1.0

A

One goes up; the other does as well

72
Q

Negative correlation

-1.0

A

One goes up; the other goes down

73
Q

Zero correlation:

0

A

No correlation whatsoever

74
Q

Perfect correlation:

A

45 degree angle up or down

75
Q

Artificially fitted and slanted so that the difference btw line and each individual measurement is the smallest distance possible.

Like an average of all of the dots

A

Correlation line

76
Q

Nominal correlation:

A

Contingency coefficient

77
Q

Ordinal correlation:

A

Spearman correlation

78
Q

Interval correlation:

A

Pearson correlation- “is there a linear relationship?”

P> 0.05 for a pearson correlation just means there is no linear correlation; there may still be non-linear correlations present!

79
Q

All correlations can be run as ___________________ to control for confounding

A

Partial correlation

80
Q

NOT only used to see if ppl survive.

Frequency of occurrence or change in category over time

Help us understand when time is important=changes over time.

A

Survival test

81
Q

Compares the proportion of, or time-to, event occcurences btw groups

Visual image of changes over time.

Commonly represented by:

A

Kaplan-meier curve

82
Q

Nominal survival test:

A

Log-rank test

83
Q

Ordinal survival test:

A

Cox-proportional hazards test

84
Q

Interval survival test:

A

Kaplan-meier test

*nominal, ordinal, and interval can all be represented by kaplan-meier curve

85
Q

Outcome prediction/ association of the groups:

Allows us to generate an asso.
Or
To take a bunch of variables and try to predict an outcome.

A

Regression test

86
Q

Nominal regression test:

A

Logistic regression

87
Q

Ordinal regression test:

A

Multinominal logistic regression

88
Q

Interval regression test:

A

Linear regression

89
Q

You can obtain an ____ from a regression

A

OR odds ratio

90
Q

Data that is derived independent of their group. Groups are treated and followed independently from other groups

A

Independent data

91
Q

2 groups of independent data of nominal data:

Males vs. females

A

Pearson’s- chi squared test (x squared)

92
Q

3 groups (or more) of independent data of nominal data:

A

Chi-square test of independence (x squared)

93
Q

Greater than 2 groups w/ expected cell count. Of <5 event occurrences

A

Fischer’s exact test

94
Q

Greater than or equal to 3 groups of independent data-nominal data, for statistically significant findings (P<0.05) in 3 or more comparisons, one must perform subsequent analysis:

A

Post-hoc testing: to determine which groups are different

95
Q

POst hoc testing for nominal data:

Adjusts the p value for # of comparisons being made, very conservative.

Take # of comparisons to do and divide the p values

0.05/3 (groups) = 0.01667 is new p value

A

Bonferroni correction: test of inequality

96
Q

2 groups of paired/related data nominal data:

A

Mcnemar test

97
Q

> 3 groups of paired/related data:

A

Cochran

98
Q

Paired data = related data

From the same person.

He will use before and after / pre-post-/ baseline end/ as the terminology..

A

McNemar test (2 groups related data)

Cochran (>3 groups of paired/related data)

99
Q

2 groups of independent data ordinal:

A

Mann-whitney test

100
Q

> 3 groups of independent data ordinal:

A

Kruskal-wallis test

101
Q

2 groups of paired/related data ordinal:

A

Wilcoxon signed rank test

102
Q

> 3 groups of paired/related data ordinal:

A

Friedman test

103
Q

Post hoc tests for 3 or more group comparisons:

See where the various differences are in between the groups.

Not needed if initially NOT stat. Significant!

A

Student-newman-keul test

Dunnett test

Dunn test

104
Q

Post hoc test compares all pairwise comparisons possible

All groups must be equal in size

Ordinal data

A

Student-newman-keul test

105
Q

Post hoc test for 3 or more tests compares all pairwise comparisons against a single control

All groups must be equal in size

Ordinal data

A

Dunnett size

106
Q

Useful post hoc test comparing groups unequally: ordinal

A

Dunn test

107
Q

2 groups of independent data-interval data

A

Student t-test

108
Q

> 3 groups of independent data-interval

A

ANOVA: analysis of variance-powerful enough to handle any number of groups

MANOVA: multiple analysis of variance

109
Q

Must perform a ______ if statically significant and >3 groups

A

Post hoc

110
Q

> 3 groups of independent data w/ confounders in interval data

A

ANCOVA: Analysis of co-variance

MANCOVA: multiple analysis of co-variance

111
Q

2 groups of paired/related interval data

A

Paired t-test

Data that is related

112
Q

> 3 groups of paired/related interval data

A

Repeated measures ANOVA

Repeated measures MANOVA

113
Q

> 3 groups of paired/related data w/ confounders in interval data.

A

Repeated measures ANCOVA or MANCOVA

114
Q

Can use student-newman-keul, dunnett, or dunn test for post hoc testing. What’re 2 others for interval data?

A

Tukey or scheffe test: compares all pairwise comparisons possible. All groups must be = in size..
–tukey: more conservative than Stu.N.K.
–scheffe: MOST conservative.
Bonferroni correction: adjusts p values for # of comparisons made

115
Q

Agreement btw evaluators (consistency of decisions, determinations)

Looking for consistency of agreement

A

Kappa statistic

Difference in radiologist reading films

-1 to +1
+=good agreement
-=poor agreement

116
Q

Review: 4 key questions to ask:

A
  1. What data level is being recorded?
  2. what type of comparison/assessment is desired?
  3. how many groups?
  4. Is the data independent or related (paired)?

Epidemiology 3 (3 decks)

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