Unit 1: Data Collection & Desciptive Statistics Flashcards
Hypotheses must be…
Testable and falsifiable
In an equation, what is
n
Sample size
In an equation, what is
Σ
Sum (add the values)
Σ is the capital Greek letter sigma
In an equation, what is
xi
Individual data points
In an equation, what is
s or σ
Standard deviation
σ is the lower case Greek letter sigma
In an equation, what is
SEx̄
Standard Error of the Mean (also called “standard error”)
In an equation, what is
x̄
Mean
Pronounced “x bar”
Explaining the meaning of:
x̄
The average of the values
Explaining the meaning of:
s or σ
The average spread of the sample data around the mean
Explaining the meaning of:
SEx̄
How far from the sample mean the actual population mean is 68% likely to be
Explaining the meaning of:
95% confidence
How far from the sample mean the actual population mean is 95% likely to be
What does this image show?

Normal distribution
Describe all important statistics in this image
Highest point = mean, median, and mode
s = standard deviation

What percentage of samples are expected to fall in the red area?

50%
What percentage of samples are expected to fall in the red area?

x̄ ± 1s = 68%
What percentage of samples are expected to fall in the red area?

x̄ ± 2s = 95%
Consider the following for a normally-distributed sample:
- x̄ = 10
- s = 3
- n = 100
- SEx̄ = 0.3
What can you determine about the sample?
The mean sample value is 10.
68 individuals fell between 7 and 13
95 individuals fell between 4 and 17
Consider the following for a normally-distributed sample:
- x̄ = 10
- s = 3
- n = 100
- SEx̄ = 0.3
What can you determine about the population?
There is a 68% chance the population mean falls between 9.7 and 10.3
and a 95% chance the population mean falls between 9.4 and 10.6
Compare
Sample and Population
Sample (n) is a subset of the population (N), and the goal is to have the sample be representative of the population
What are the
Two Types of Data
Qualitative
and
Quantitative
Types of
Quantitative Data
Raw data are directly measured / counted
Manipulated data are calculated based on raw data
Examples of
Manipulated data
Mean, rates, and other statistical measures
What should all tables contain?
- Descriptive title that would allow the table to be understood even in absence of other information
- Headers with units!
- Data that has consistent decimal places and no units (already in the header)
How to convert from base unit to milli
Ex: 5 liters → ? mL
Multiply by 1,000
i.e. Move decimal to the right three places
5 L = 5,000 mL