Intro to Biostats Flashcards
(132 cards)
1
Q
a research perspective which states there will be no difference between the comparison groups
A
null hypothesis H0
2
Q
statistical perspectives that can be taken by the researcher in their alternative hypothesis
A
superior
noninferior
equal
3
Q
alpha error
A
type I error
rejecting the null when you should accept it
false positive
4
Q
beta error
A
type II error
accepting null when you should reject it
false negative
5
Q
define power
A
statistical ability of a study to detect a true difference when it exists
“accuracy”
6
Q
the ______ the sample size, the greater the ability of _________ .
A
greater
ability to detect a true statistical difference
increase in power
7
Q
the smaller the difference between group, that is required to show a statistical difference, then the greater _________ is needed.
A
greater sample size is needed
8
Q
when determining sample size you should anticipate …….?
A
drop outs and lost to follow up
so oversample in the beginning to compensate
9
Q
bell curve percentages based on standard deviation
A
1 stdD = 68%
2 stdD = 95%
3 = 99.7%
10
Q
probability value = ?
A
p value
11
Q
the probability value is selected before or after the study starts?
A
before
12
Q
if the p value is lower than the alpha value, then we say?
A
alpha value = 5%, 1%, etc.
we say it is statistically significant
13
Q
relate p value to a statistically significant test
A
the p value is lower than alpha
so we reject the null (not accept)
14
Q
relate a p value less than the alpha of 5%, and the risk of type I error
A
p value is lower, we reject the null
therefore, the risk of experiencing a type I error is acceptably low = less than 5%
15
Q
at 95% confidence and p value of 0.005, what is the risk of error?
A
.5% risk of being wrong
16
Q
relate a p value of 0.01% and 3 groups
A
there is at least one significant difference between the 3 groups
typically between control and the most extreme group
17
Q
should baseline data be statistically significant or not different?
A
should show no statistical difference
to show that our experiment groups are not different so final results will show a difference only if my intervention caused it
18
Q
a p value of 0.91, what is your chance of being wrong?
A
91% chance of being wrong when you say there is a statistical difference (type I error)
if you claim a difference you have a 91% chance of being wrong
19
Q
when do we want p values to not be statistically different
A
- when comparing baseline characteristics at start
2. When using a levene’s test
20
Q
3 primary level for variables - data types
A
nominal
ordinal
interval/ratio
21
Q
3 key attributes of data measurement
A
order/magnitude
consistency of scale (equal distance)
rational absolute zero
22
Q
nominal
A
no order
no consistency of scale
simply work w/ no quantitative characteristics
23
Q
any question that only has 2 categories is always what type of data?
A
nominal
24
Q
ordinal
A
has order
no consistency of scale
ex. pain scale, stress levels, happiness ratings
disagree, somewhat disagree, neutral, etc.
25
interval/ratio data
has order
has consistency of scale
ratio has absolute zero
26
interval data
arbitrary zero value
0 does not mean absence
temperature
27
ratio data
has an absolute zero
0 = absence
ex. 0 heartbeat = dead
28
after data is collected, we can appropriately go _____ in specificity/detail of data measurement levels, but never ____ .
go down
but never up
in terms of nominal, ordinal, interval, ratio
29
measures of dispersion/spread
mean, median, mode
outliers
min/max and range
IQR
30
difference between variance and standard deviation
variance is the distance from the mean of one particular value
standard deviation represents a % of data being this far from the mean
31
relate bell graph to percentiles
broken into 4 25% sections about the median (=50th percentile)
32
IQR
interquartile range
Q1 - Q3 = IQR
25th - 75th percentile = IQR
33
statistical tests used on normally distributed data is called ?
parametric tests
34
positively skewed
tail pointing to the right/positive direction
mean > median
35
negatively skewed
tail pointing to the left/negative direction
mean < median
36
if the data is not skewed then how are the mean and median related?
they should be the same/ almost the same
37
what are the 3 ways to tell if the data is skewed?
1. are the mean and median the same?
2. what does the graph look like?
3. what is the skew value?
38
skewness value
if data is not skewed it will be as close to zero as possible
can have pos./neg. values
39
kurtosis
a measure of extent to which the data clusters about the mean
normal distribution, kurtosis = 0
40
positive kurtosis
= higher clustering about the mean
41
negative kurtosis
= less clustering about the mean
42
discrete vs. continuous data
discrete is solid numbers whilst continuous can have decimals
43
required assumptions for interval/ratio data
1. normally distributed
2. equal variances
3. randomly derived and independent
44
levene's test
tells us if interval/ratio data is normally distributed w/ equal variances or not
45
what if interval data is not normally distributed?
just use a non-parametric test
or transform the data using z-scores (log transformations)
46
variables required when interpreting a p value
1. is it significant
2. who was higher/lower
3. by how much?
include all three, no specific order
47
______ must be equal in order to pick an interval test.
variances
48
levene's test is used to assess whether ______ are equal between ?
variances between all groups
49
before running a levene's test you need? and why
need the null hypothesis stating there is no difference
we want the p value to come back not significant to prove the variances are equal
if we prove they're equal data can then be treated as interval data
50
number of siblings is an example of _____ data
interval data
51
define confidence interval
an interval around the p value that we are %% confident that the true difference is within this range
52
a CI that includes reducing and increased risk
means that it is not significant because a significant test cannot show both directions
53
when interpreting a CI for OR/RR, and the range contains 1.0
is not significant
if range crosses 1.0 then it is not significant
54
when interpreting CI for actual data values, and crosses zero
it is not significant
55
does statistical significance actually confer meaningful, _____ significance?
clinical significance
56
4 key questions to selecting the correct statistical test
1. what data level is being recorded?
2. what type of comparison/assessment is desired?
3. how many groups being compared?
4. is the data independent or related/paired?
57
correlation tests
provides quantitative measure of strength & direction of a relationship between variables
ranges from -1 to +1
refers to line graphs/ slope
58
nominal correlation test
contingency coefficient
59
ordinal correlation test
spearman correlation
60
interval correlation test
pearson correlation
61
running a partial correlation
to control for confounding
62
contingency coefficient
for nominal correlation testing
63
spearman correlation
for ordinal correlation testing
64
pearson correlation
for interval correlation testing
65
what do correlation tests tell you?
tell you the relationship between two variables
66
gender is _____ data
nominal
67
a test to determine event-occurrence or time to event
survival test
68
what does survival describe
the lack of the "event" occurring
69
survival test
compares the proportion of events over time, or time to events
between groups
70
nominal survival test
log-rank test
71
ordinal survival test
cox-proportional hazards test
72
interval survival test
Kaplan-meier test
73
log-rank test
nominal survival test
74
cox-proportional hazards test
ordinal survival test
75
Kaplan-meier test
interval survival test
76
Kaplan-meier curve
a graphical representation of a survival test
all tests can provide this
(even tho interval survival test has this same name)
77
see changes over time
survival test
78
testing for outcome predictions or associations
regression testing
79
regression
provides a measure of relationship between variables and allows the prediction about the dependent/outcome, when the independent is known
can use several variables to increase prediction
80
regression tests also calculate ?
OR for a measure of association
81
nominal regression test
logistic regression
82
predict whether you do or do not get something
nominal regression
only two options
83
if the outcome variable (dependent variable) is ordinal data type
then choose ordinal regression test
84
ordinal regression test
multinominal logistic regression
85
if the outcome variable is of the interval data type
then use interval regression test
ex. predicting actual gpa number
86
interval regression test
linear regression
87
logistic regression
nominal regression test
88
multinominal logistic regression
ordinal regression test
89
linear regression
interval regression test
90
want to predict the likelihood of some outcome
regression testing
91
what do you evaluate to determine what type of regression test to run?
only what data type the outcome variable is
92
univariate
unadjusted OR
93
ordinal data - 2 groups of independent data
mann-whitney test
94
ordinal data - >3 groups of independent data
Kruskal-wallis test
95
ordinal independent data
- -both tests compare the median values between groups
- -also used for non parametric interval data
- -if 3+ groups are significant must do a post-hoc test to determine differences
96
3+ group comparison that is significant - ordinal independent data
then you must do a post-hoc test to determine what the differences are
97
ordinal data - 2 groups of paired/related data
Wilcoxon signed rank test
98
ordinal data - 3+ groups of paired/related data
friedman test
99
ordinal paired/related data
- -both tests compare median values
- -can be used for non parametric interval tests
- -if significant in 3+ tests must do post-hoc test
100
key words for paired/related data
pre vs post
before vs after
baseline vs end
101
ordinal data - post-hoc tests for 3 or more group comparisons
student-newman-keul test
Dunnett test
dunn test
102
student-newman-keul test
compares all pairwise comparisons possible
all groups must be equal in size
post-hoc test for ordinal data
103
Dunnett test
compares all pairwise comparisons against a single control
all groups must be equal in size
post-hoc test for ordinal data
the other two tests find all comparisons possible - this is everything vs one specific thing
104
dunn test
compares all pairwise comparisons possible
useful when all groups are not of equal size
post-hoc test for ordinal data
105
ordinal post-hoc test: when groups are not equal in size
dunn test
106
ordinal post-hoc test: to find all comparisons possible
student-newman-keul test
| dunn test
107
interval data: 2 groups of independent data
student t-test
108
interval data: 3+ groups of independent data
analysis of variance - ANOVA
109
interval data - independent data
tests compare means of all groups against dependent variable
--must do post-hoc test when 3+ group comparison is significant
110
interval data: 3+ groups of independent data w/ confounders
analysis of Co-variance - ANCOVA
111
ANCOVA
compares the means of all groups against a dependent variable while also controlling for the co-variance of confounders
for interval independent data w/ confounders
112
how many groups can an ANOVA analyze?
any number of groups
113
interval data: 2 groups of paired/related data
paired t-test
compares the mean values between groups that are related
114
interval data: 3+ groups of paired/related data
repeated measures of ANOVA
compares the means of all groups of related data against a dependent variable
must do post-hoc if significance is found
115
interval data: post-hoc tests for 3+ group comparisons
student-newman-keul test
Dunnett test
dunn test
same explanations as ordinal data
plus
tukey/scheffe tests
Bonferroni correction
116
tukey/scheffe test
interval post-hoc test
compares all pairwise comparisons possible
groups must be equal in size
117
tukey vs. scheffe tests
tukey -- more conservative than the stu.n.k
scheffe -- less affected by violations in normality and homogeneity of variance
*most conservative
118
Bonferroni correction
adjusts the p value for # of comparisons being made
very conservative
interval data post-hoc test
119
validation/assessment committee
kappa statistic
| kappa interpretation
120
kappa statistic
a correlation test
| shows relationships between evaluators
121
kappa interpretation
```
+1 = the observers perfectly classify everyone the same way
0 = no relationship between observers classifications above what is expected by chance
-1 = observers classify everyone exactly the opposite of each other
```
122
kappa K
value can be + or -
| meaning good agreement or poor agreement
123
kappa test significance
to determine if the decisions of the observers is consistent amongst multiple observers
are their classifications good?
124
2 groups of independent nominal data
pearson's Chi-square test
125
3 or more groups of independent nominal data
chi-square test of independence
126
nominal data: 2 or more groups w/ expected cell count of <5
fisher's exact test
127
nominal data - 3 or more groups of independent data -- what to do after getting a significant result
must run post-hoc to determine which groups are different
multiple chi square tests is not acceptable
Bonferroni test of inequality
128
2 groups of related nominal data
McNemar test
129
3 or more groups of related nominal data
Cochran
same as chi squared but mathematically factors in concept of paired data
then Bonferroni test of inequality for post-hoc testing
130
key words for paired/related data
pre vs post
before vs after
baseline vs end
131
'prediction' is a key word for what type of assessment desired?
regression testing
132
'event-occurrence' or 'time to event' are key phrases for what type of desired assessment?
survival testing
