Intro to Biostats- Week 1 Flashcards
What are the three steps of data measurements in human studies?
- Data will be collected on desired variables.
- Comparisons are commonly made. (statistical analysis)
- Inferences will be made about the sample-derived ‘data’ and their comparisons. (null hypothesis)
Researchers will either accept or not accept this, based on statistical analysis?
Null Hypothesis (H0)
What is a Null Hypothesis?
A research perspective that states there will be no (true) difference between the groups being compared.
What are the three statistical perspectives that can be taken by the researcher? (in relation to null hypothesis?)
- Superiority
- Noninferiority
- Equivalency
What are the three key attributes of data management?
- Order/Magnitude
- Consistency of scale/ equal distance
- Rational absolute Zero
What are the three primary levels for variables based on three key attributes?
- Nominal
- Ordinal
- Interval or Ratio
Describe “Nominal” in relation to the three primary attributes of data management.
- No order or Magnitude
- No consistency of scale
- No quantitative characteristics
(Nominal variables are labeled-variables without quantitative characteristics)
Describe “Ordinal” in relation to the three primary attributes of data management.
- Yes order of Magnitude
- No consistency of scale
- No units
Describe “Interval/Ratio” in relation to the three primary attributes of data management.
- Yes order of magnitude
- Yes consistency of scale
- Yes absolute zero, but they are different for both.
Describe the difference between “Interval” and “Ratio”
Interval = Arbitrary zero value (0 doesn't mean absence) Ratio = Absolute (rational) zero value (0 means absence of measurement value)
All statistical tests are selected based on what?
Level of data being compared
After data is selected you can go up/down in specificity of data measurement levels, but never up/down?
- down
2. up
Data is represented by what in quantitative study designs?
Numbers
Data is represented by what in qualitative study designs?
Words
What is descriptive statistics?
Non-comparative, simple description of various elements of the study’s data
What is the mean of a data set?
The usual average, add all numbers and divide by the amount of numbers in the set
What is the median of a data set?
The median is the middle value of the data set, when they are aligned in numerical order.
What is the mode of a data set?
The mode is the number that is represented more than any other number of the data set.
What is the Range of a data set?
the range is the maximum minus the minimum
What is the Interquartile range? (IQR)
The interquartile range is the difference between two different quartile points, for example the 25th percentile is 10 and the 75th percentile is 20, Q3 - Q1 = 10.
What is Variance?
the average of the squared-differences in each individual measurement value (x) and the groups’ mean.
Standard Deviation
square root of Variance value (restores units of mean)
A normally distributed graph is what?
symmetrical
What does it mean when a graph is symmetrical?
It is when a dataset is normally-distributed the following values (PARAMETERS) are equal/near equal
What type of stat tests are useful for normally-distributed data?
Parametric tests
What is an asymmetrical distribution?
When one tail of the graph is longer than another tail
What makes a graph positively skewed?
mean>median
What makes a graph negatively skewed?
Median>Mean
What is skewness?
a measure of the asymmetry of a distribution.
A perfectly-normal distribution that is symmetric will have a skewness value of what?
0
What is Kurtosis?
A measure of the extend to which observations cluster around the mean.
A normal distribution will have a kurtosis value of what?
0
A positive kurtosis value means what?
more cluster around the mean
A negative kurtosis value means what?
less cluster around the mean
How much of the range of data is shown within the first standard deviation?
68%
How much of the range of data is shown within the first two standard deviations?
95%
How much of the range of data is shown within the first three standard deviations?
99%
In nominal and ordinal data the mean represents what?
nothing. you can’t use it because the numbers have no meaning.
What are the two required assumptions of interval/ratio data?
- normally distributed
2. equal variances
What is a test we can do to describe the two required assumptions of interval/ratio data?
Levene’s test
What does Lavene’s test show?
calculate if groups are normally distributed with equal variance
How can we handle data that is not normally-distributed?
- Use a statistical test that does not require the data to be normally-distributed (non-parametric tests)
- Transform data to a standardized value (z-score or log transformation) (in hopes that transformation allows data to be normally-distributed)
Researchers either accept or don’t accept WHAT based on statistical analysis?
Null Hypothesis
What is Type 1 error?
Not accepting the null hypothesis when it is actually TRUE, and you should have accepted it!
What is type 2 error?
Accepting the null hypothesis when it is actually false, and you have NOT accepted it.
In which type of error is there no true differences between the groups, but in error you did not accept the Null Hypothesis.
Type 1
In which type of error is there a true difference between the groups, but in error you accepted the null hypothesis?
Type 2