week 3

Question 1

independent variable

Answer 1

the variable that is manipulated
presumed cause of an effect
what is being observed

Question 2

dependent variables

Answer 2

the outcome of an intervention or exposure
measured variable used to determine the effects of the independent variable
outcome whose variation we seek to explain or account for by the influence of independent variables

Question 3

confounder

Answer 3

factor other than the independent variable that influences the outcome

Question 4

attribute variables

Answer 4

used to describe a sample

Question 5

explanatory variables

Answer 5

variable that causally explains the relationship or outcome under study

Question 6

predictors

Answer 6

variable that is causally related to a future outcome

Question 7

internal validity

Answer 7

extent to which the study lacks bias

how well does the study support a causal relationship?

Question 8

external validity

Answer 8

generalizability of results

can the results be applied to the population?

Question 9

bias

Answer 9

a systematic error in the way a study is carried out that can lead to false conclusions
any trend in the collection, analysis, interpretation, publication or review of data that can lead to conclusions tht are systematically different from the truth

Question 10

threats to internal validity

Answer 10

history
maturation
testing
instrumentation
group assignment
loss to follow up
tmt crossover
compensatory issues

Question 11

threats to ext validity

Answer 11

subject selection
setting where research is conducted
time since study

Question 12

causation

Answer 12

an outcome or event will occur as a result of a previous event

Question 13

association

Answer 13

a statistical relationship btw two events that may or may not be causal

Question 14

criteria for causation

Answer 14

exposire precedes outcome
strong association
biologically credible
consistent with previous research
dose-response relationship
alternative expanations

Question 15

direct measures

Answer 15

concrete values

Question 16

indirect measures

Answer 16

abstract representations of quantities and/or characteristics

Question 17

constructs

Answer 17

abstract variables that cannot be seen directly, but are inferred by measuring relevant behaviors that are observable
multidimensional
development of an instrument

Question 18

categorical variables

Answer 18

nominal variables: counts, frequencies, percents

ordinal variables: rank ordered categories, quantitative analysis often ambiguous

Question 19

numeric variables

Answer 19

interval and ratio variables

Question 20

transforming scales

Answer 20

can change a numeric scare to categirocal but cannot change categorical to numeric

Question 21

random error

Answer 21

chance variation in measurement

Question 22

systematic error

Answer 22

results from an identifiable source

Question 23

sources of error

Answer 23

inaccuracy, instrument inprecision, subject response bias

Question 24

analytic procedures are used to quantify ____ due to random error

Answer 24

uncertainty

Question 25

____ is dealt with in the design of the study anf through good measurement procedures

Answer 25

bias

Question 26

variance

Answer 26

measure of variability or spread of observations in the sample

function of both true variability within the population and variability due to measurement error

Question 27

reliability

Answer 27

degree to which a measurement procedure is repeatable

Question 28

validity

Answer 28

degree to which a measurement correctly estimates the true value of the object being measures

Question 29

first requirement of measurement

Answer 29

can it be repeated consistently with minimal error?

Question 30

second requirement of measurement

Answer 30

does the test/measure actually measure what it claims to measure?

Question 31

A useful clinical instrument also must be able to detect ______ over time

Answer 31

change

Question 32

the measure must also be ____ to change

Answer 32

sensitive

Question 33

standardized response mean (SRM)

Answer 33

expresses change in standard deviation units

requires numerical outcomes

=(mean of pre to post test change) / (stdev of change score)

.8 = large change