Quiz 1 - Lectures 1 and 2 Flashcards
All the blanks in the lecture slides
variable
characteristic that changes over time and/or for different people or objects
experimental unit
person or object on which variable is being measured
Measurement
data value comes when a variable is measured on experimental unit
Population
set of all measurements of importance to investigator
Sample
subset of measurements selected from population
Univariate
1 variable is measure on a single experimental unit
Bivariate
2 variable measured on a single experimental unit
multivariate
2+ variables measured on a single experimental unit
Qualitative
variable measures a quality or characteristic
quantitative
variable measures a numerical quantity or amount
Discrete
variable can assume only countable number of values, finite
Continuous
variable can assume any value within an interval
statistical table
list of categories and measure of how often each value occured (frequency)
Data Distribution
a graph
Categorical
Categorical and qualitative are exchangeable
Frequency
number of measurements in each category
relative frequency
proportion of measurements in each category
percentage
relative frequency x 100%
the sum of frequencies…
is always n (the total # of measuremtns in set)
the sum of relative frequency…
is always 1
the sum of percentages…
is always 100%
when qualitative variable, categories should be chosen so measurements will fall into…
1 and only 1 category
when qualitative variable, categories should be chosen so each measurement has…
1 category to fall into
Time series
data set that forms when a quantitative varible is recorded over time at equally spaced intervals
line chart
best data distribution for time series
trend
pattern used to make a prediction about the future
dotplot
the simplest graph for quantitative data
Class
subinterval created when you divide up an interval from smalles to largest measurements
Class boundaries
numbers that create upper and lower limits of class
Class width
difference between upper and lower class boundaries
class frequency
number of measurements falling into that particular class
the number of classes in a relative frequency histogram
usually 5 to 12
more data =
more classes
With this data you must assign 1 class for each integer value for a histogram
discrete data
location
center of data cloud
shape
spread of distribution
skewed to the right
greater proportion of measurements lie to the right of the peak, contains a few unusually large measurements
skewed to the left
greater proportion of measurements lie to the left of the peak, contains a few unusually small measurements
unimodal
1 peak
bimodal
2 peaks, often represents a mix of 2 different populations in data set
uniform
heights are the same for each class