BIOSTATISTICS Flashcards
TYPES OF VALIDITY
-internal
-external
The extent to which a
study establishes a
trustworthy
cause-and-effect
relationship between a
treatment and an
outcome
INTERNAL VALIDITY
Refers to how well the
outcome of a study can
be expected to apply to
other settings.
EXTERNAL VALIDITY
example of internal validity
methodology
example of external validity
results and
conclusion
Gives information that describes the data in some
manner
DESCRIPTIVE STATISTICS
T/f: Data is also described by compiling it into a graph,
table or other visual representation.
True
Uses a random sample of data taken from a large
population to describe and make inferences about
the population
INFERENTIAL STATISTICS
Analyze the sample to generalize the whole using
statistical tools
INFERENTIAL STATISTICS
From a population, you
get a sample to describe.
DESCRIPTIVE STATISTICS
When you represent the
population using a sample
to make a conclusion on
the population.
INFERENTIAL
STATISTICS
The smallest numbers
that can actually belong
to different classes
LOWER CLASS LIMITS
The largest numbers
that can actually belong
to different classes
UPPER CLASS LIMITS
Are the numbers used to separate classes, but
without the gaps created by class limits.
CLASS BOUNDARIES
MEASUREs OF CENTRAL TENDENCY
MEAN, MEDIAN, MODE
T/F: The disadvantage of using the mean as a measure
is that IT IS SENSITIVE TO UNUSUAL VALUES
MEAN
defined as the point in the distribution with 50% of
the measure on each side of it.
MEDIAN
Midpoint of the distribution
Median
T/f: Median is Not affected by extreme values
True
Value that appears most or most occurring value
Mode
T/F: Mode is Not affected by extreme values
True
Disadvantage of mode
difficult to use in a small sample of
continuous data
If there is one pea
UNIMODAL
If there are two peaks
BIMODAL
Simplest measure of variation
● Difference between the largest and the smallest
observations
RANGE
Average of squared deviations of values from the
mean
VARIANCE
How far each number from the data set is from the
mean
Variance
Heterogeneity or homogeneity among samples and Heterogeneity or homogeneity among samples
STANDARD DEVIATION
STANDARD DEVIATION unit follows that of
mean
How far the data set is from the mean
STANDARD DEVIATION
Shows variation relative to mean
COEFFICIENT OF VARIATION (CV)
Coefficient of Variation
(SD/mean) X 100
std dev =
square root of variance
variance =
mean / (n-1)
Complete information of data can be presented
TABULAR
Visual representation to display relationship
GRAPHICAL
T/F: In graphical data presentaiton, Title must be stand alone
True
Graph title should appear at the
bottom
use sample data to make inferences (or
generalizations) about a population
INFERENTIAL STATISTICS
Process of generalizing or drawing conclusions
about the target population on the basis of results
obtained from a sample.
INFERENTIAL STATISTICS
collection of all possible
individuals, objects, or
measurements of interest.
POPULATION (N)
portion, or part, of
the population of
interest
SAMPLE (n)
a probability and is,
in reality, the probability of rejecting a true null
hypothesis.
LEVEL OF SIGNIFICANCE
a statement about one or more
populations.
HYPOTHESIS
Hypothesis of no
difference
NULL HYPOTHESIS
What is being tested, in
which the decision is
being made - reject or
accept
NULL HYPOTHESIS
(H0) Ideal situation
rejected
T/F: If H0
is rejected, HA is
automatically accepted
True
What we believe is true
if H0
is rejected
Alternative hypothesis
Your expected conclusion, or what you hope to
conclude as a result of the experiment should be
placed in the
alternative hypothesis.
T/f: The null hypothesis should contain an expression
of equality, either =, ≤ or ≥.
true
is the hypothesis that will be
tested.
null hypothesis
T/F; The null and alternative hypotheses are
complementary
true
= stastical hypothesis
2 tail, 2 rejection regions
≤
One tail, rejection
region on right
≥
One tail, rejection
region on left
sampled population or populations are at least
approximately normally distributed
PARAMETRIC
procedures that test hypotheses that are not
statements about population parameters
NON-PARAMETRIC
Used mainly on interval
and ratio scale data
PARAMETRIC
Tend to need larger
samples
PARAMETRIC
Data should fit a particular
distribution; data can be
transformed to that
distribution.
PARAMETRIC
Samples should be drawn
randomly from the
population.
PARAMETRIC
More powerful than
non-parametric equivalent
PARAMETRIC
Less power than the
equivalent parametric
test
PARAMETRIC
Can be used on data that
are not normally
distributed
NON-PARAMETRIC
Can be used where the
samples are not selected
randomly
NON-PARAMETRIC
Can be used on small
samples
NON-PARAMETRIC
Can be used on ordinal
and nominal scale data
NON-PARAMETRIC
procedures that make no assumption about the
sampled population
DISTRIBUTION-FREE
A statistical measure of the strength of a linear
relationship between paired data.
PEARSON FORMULA OF CORRELATION
Positive values denote
positive linear
correlation
Negative values denote
negative linear
correlation
A value of 0 denotes
no linear correlation
The closer the value is to 1 or –1, the __________
the linear correlation.
stronger
The farther the value is to 1 or –1, the __________
the linear correlation.
weaker
an effect size and so we can verbally
describe the strength of the correlation using the
guide that Evans (1996) suggests for the absolute
value of r
Correlation
If the absolute value of your correlation coefficient
is above the critical value, you ________ your null
hypothesis
reject
If the absolute value of your correlation coefficient
were less than the critical value, you would fail to
________ your null hypotheses:
fail
used for interval and nominal
data.
Point Biseria
Used for Nominal to nominal
data.
Phi Coefficien
between ordinal and another ordinal
Spearman’s
measures if the difference is
significant or by chance.
Chi-square