Basic terminology, Frequency distribution, Histograms Flashcards
Module 1: Handout 1, handout 2, handout 3
population
large group of individuals
data
facts or observations
statistics
analyzes data
variables
data that can vary or are changeable, basically both x and y
variable types
- quantitative
- qualitative
- continuous
- discrete
quantitative variable example
age, income, number of children, GPA
quantitative variable
variables that are presented in numerical form
qualitative variable example
place of origin, gender
qualitative variable
variables that are organized into categories
continuous variable
a variable that seemingly has an infinite number of possibilities EX age (I can be 19.31 years old)
discrete variable
a variable that only have a certain number of possible outcomes EX whole integers
discrete variables that are considered continuous
income is a variable that can have a specific range of outcomes, but it is moreso considered continuous because of the many possible outcomes
sample
subset/smaller group of one whole population
sample types
- representative
- random
- biased
representative sample
members in a sample that represent a population as a whole
biased sample
a sample that is not random
sample mean
a statistic true to the sample, not the population
population/true mean
a statistic that is true for the whole population
frequency distribution
sorts data into classes
class width
the number difference between the first number of one class and the first number of the next class
each class of the frequency distribution has a…
class width
class width example
the first class is 0-9, second class is 10-19, so the class width is 10 since 10-0=10
choosing a class width
calculate the range of data, then divide by the number of classes you want
choosing a class width example
lightest member is 172lbs, heaviest is 250lbs, so range is 78 and if i want 5 classes then do 78+5=15.6 or 15
normal distribution
the frequency distribution initially starts low, then its highest, then low again kind of like an upside down parabola
uniform distribution
frequencies are constant..? so each class would roughly have the same number
exponential distribution
the maximum frequency will be at the end of one range (beginning or end)
bimodal distribution
two maximums frequencies
frequency
The amount in each class of a frequency distribution
Two rules that are required for frequency distribution are…
that the class widths are consistent for each class and there are at least 5 classes
Steps to create a frequency distribution
1) Find the lowest number and highest number of the data
2) Do highest# minus lowest# which would equal the “range”
3) Divide the “range” by the number of classes you are using which equals the “class width”
4) The “class width” is rounded to a whole number
5) Then create an x&y chart
6) The X column includes all the data for the lowest-highest numbers
7) The Y column answers the X column
8) Then looking at the Y column numbers, identify the type of distribution (normal=parabola, uniform=line, exponentional=exponential line, bimodal=two parabolas)
What is a histogram ?
a visual representation of a frequency distribution
What goes on the vertical axis?
frequency
What goes on the horizontal axis?
classes