Final Exam Flashcards
(135 cards)
1
Q
evidence based medicine
A
quality revolution in healthcare
2
Q
Demings philosophy
A
quality is about people, not products
3
Q
Deming facts
A
- didn’t believe in quotas
- worked for US Census and Western Electrical
- improved manufacturing quality during wartimes
4
Q
kaizan
A
quality improvement requires teamwork, open communication and problem solving
5
Q
nelson data to wisdom continuum
A
organizing data so that it can provide new insights and information
6
Q
history of probability
A
basically people aren’t good at understanding probabilty
7
Q
uniform distribution
A
block, each score is equally as likely
8
Q
probability distributions
A
allows you to distribute possible outcomes and which is most common
9
Q
normal distributions
A
bell curve, rare events are the tails
10
Q
exponential distributions
A
rare events
11
Q
availability bias
A
linking an event to something that happened in our past
12
Q
Monty Hall problem
A
odds of winning go from 1/3 to 2/3 when you switch
13
Q
categorical measurements
A
put observations into named categories (HIV status, gender)
14
Q
ordinal measurements
A
categories that can be put in rank order (cancer stage, smoking)
15
Q
quantitative measurements
A
numerical values that can be put on a number line (age, weight, BMI)
16
Q
observation
A
unit upon which a measurement is made (ie. a person/row)
17
Q
variable
A
thing we measure (ie. ID or age/column)
18
Q
value
A
realized measurement for a variable (ie. age=27/cell)
19
Q
objectivity
A
not making data conform to a preconceived worldview
20
Q
reliability
A
ability to collect the same values for variables repeatedly (how close the darts are to each other)
21
Q
validity
A
how truthful the data is (darts hitting the bullseye)
22
Q
internal validity
A
truth within a study
23
Q
external validity
A
if results can apply beyond the study
24
Q
incidence
A
new cases in a population over a defined period
25
prevalence
total number of cases at a given point in time
26
non-experimental vs experimental
experimental assigns subjects to groups according to explanatory variables
27
case-control
subjects with a certain disease are matched to a similar group without the disease
28
cohort
two groups (1 exposed and 1 non-exposed) are followed to compare rates of new cases
29
James Lind Scurvy trials
treatment for scurvy, 6 different treatment plans, example of an RCT
30
RCT
group of individuals with the same condition and assigning them to interventions or control
31
convenience sampling
worst kind of sampling, usually biased, sampling whoever is around
32
power of sampling
can be effectively used a number of ways
33
frequency distributions
check distributions for outliers, errors, normal distribution, and if any can be combined
34
symmetry
balance in the pattern
35
modality
number of peaks
36
kurtosis
width of tails
37
departures
outliers, they skew data
38
positive skew
right tail is longer
39
negative skew
left tail is longer
40
mean
gravitational center
41
median
middle value
42
mode
value with the highest recurrence
43
range
spread of data (maximum-minimum)
44
frequency table
list all data values and frequency count
45
sample vs population mean
usually use a sample population mean to estimate the population mean
46
quartiles
divides data into 4 equal groups
47
variance
how spread out data is around the mean
48
standard deviation
spread of data around the mean
49
random variables
number that has different values depending on chance
50
population
set of all possible values for a random variable
51
event
outcome/set of outcomes
52
probabilities
proportion of times an event may occur in a population
53
discrete random variables
countable set of possible outcomes
54
continuous random variables
unbroken continuum of possible outcomes
55
probability mass function (pmf)
assigns probabilities to all possible outcomes for a discrete random variable
56
area under the curve
probability, adds up to 1
57
cumulative probability
probability of said value or less
58
probability density function (pdf)
assigns probabilities to all possible outcomes for a continuous random variables
59
binomial random variable
discrete random variable with only 2 outcomes
60
normal random variable
most common type of continuous random variable (ie. height, weight, systolic bp)
61
68-95-99.7 rule
68% of data is within u+-o and so on...
62
SEM equation
SEx=s/square root of n
63
statistical inference
how you generalize from the particular to the general
64
central limit theorem
sampling distribution of x-bar tends towards normality
65
z-scores
gives you the p-value
66
null hypothesis
no difference/association
67
significance levels
p-values and whether you should reject Ho
68
one-sided vs two-sided
one-sided looks for values larger than the null, two-sided is for when you don't know the direction of the alternative
69
point estimation
single best estimate of a parameter
70
confidence intervals
type of interval estimation
71
interval estimation
surrounds point estimate with margin of error
72
family of t-distributions
like a z-distribution but with more df and more uncertainty
73
df
degrees of freedom that allow tails to be skinnier or broader
74
relationship between df and distributions
df increases ->t-tails get skinnier->t becomes more like z
75
paired data
get data from 2 groups and compare
76
paired t-test
each point matches another in a different sample
77
conditions for inference (using a t-test)
simple random sample, valid information, normal population, large sample
78
normality condition for using a t-test
normality applies to the sampling distribution of the mean, not the population
79
single sample t-test
one group, comparisons are made to an external population
80
independent 2-sample t-test
two separate groups with no pairing, compare the separate groups
81
Levene's test
tests that the variances are equal (thats the null), f-test to determine pooled variance
82
ANOVA
analysis of variance
83
statistics used to compare 3+ means
use ANOVA, with a continuous variable
84
family-wise error rate
probability of making a type 1 error
85
variability between groups (MSB)
mean square between, variability between groups of means around the grand mean
86
variability within groups (MSW)
mean square within, average amount of variation within groups
87
post hoc comparisons
only if you accept the alternative hypothesis, tells you which of the means differ
88
LSD vs. Bonferroni
bonferroni is more conservative
89
if the interval doesn't include 0...
it is statistically significant
90
homoscedasticity
equal in variance
91
heteroscedasticity
unequal in variance
92
correlation
determines if there's significant association
93
r
linter relationship between -1 and 1
94
r^2
coefficient of determination, variance in Y explained by X
95
what affects correlation
confounding, outliers, non-linear relationships
96
residuals
distance from data point to the line
97
dummy variables
giving categorical variables to independent variables in a multiple regressions, k-1
98
binary response variable
categorical variable with 2 responses
99
chi-square test
two categorical variables, compare expected to observed, the more difference there is the more association there is
100
Mantel Haenszel test
using another categorical to split data up more, need a large sample size
101
assumptions for parametric tests
normal distributions, large sample sized, quantitative data
102
assumptions for non-parametric tests
doesn't assume normality, observations are independent
103
advantages of non-parametric
use on non-normal data, small sample size, easier to apply
104
disadvantages of non-parametric
loss of info, harder to reject null, decreased statistical power
105
general rules for non-parametric
use parametric whenever possible
106
univariate vs multivariate
testing the relationship between two variables vs testing the relationship of multiple variables
107
outcome variable
event time, dependent, variable in question
108
survival analysis
time to some event (ie. death, infection, hospitalization) need to define the outcome variable
109
logistic regression
multiple regression with a binary outcome variable (ie. age vs diabetes diagnosis)
110
fitted model
actual model that contains outcome and explanatory
111
sample size rules (for general regression model)
n>30, 1 variable per 30-50
112
Cox regression
survival analysis and logistic regression together, binary response
113
consecutive sampling
used a lot in healthcare, sampling people with characteristics you like, not purely random
114
simple random sampling
everyone has a known probability of being sampled, best kind of sampling
115
stratified random sampling
divides populations into groups so that each group has an equal chance of being included
116
systematic sampling
samples every nth individual
117
cluster sampling
sampling of a natural grouping
118
n
sample size
119
x
variable
120
xi
value of individual I for variable x
121
u
population mean
122
s
standar deviation
123
x-bar
sample mean
124
degrees of freedom calculation
Welsh method or conservative method
125
conservative post hoc
makes it more difficult to detect statistical differences among the means
126
Cox
determine what variables are most associated with outcome and time, consider multiple variables
127
undercoverage bias
some groups are left out ur underrepresented
128
volunteer bias
self-selected participants, tend to be atypical of the population
129
nonresponse bias
large percentage of individuals refuse to participate/cannot be contacted
130
where are proportions from?
categorical variable
131
chi-sqaures are non-parametric which means...
there is a decrease in statistical power and it compares ranked data
132
Pearson's correlation is equivalent to...
spearman's ranked something
133
correlation doesn't mean
causation
134
key features of RCT
- randomizatoin
- control group for comparison
- blinding or masking
- ethics
135
what can multiple regression analysis help you do?
determine confounding
