define data.
some kind of measurement or observation, must be defined and chosen clearly, then measure it
define variable.
some aspect or quality that varies or changes among the population
what is qualitative data? what is another name for this type of data?
- something that is not a number, often includes a visual feature or characteristic
- includes numbers that have been categorized
- also called categorical data
what is quantitive data? what is another name for this type of data?
- number or quantity
- also called numerical data
what are the two types of qualitative data?
- ordinal
- nominal
what is ordinal categorical data?
there is a natural order to the categories, (eg) feelings
what is nominal categorical data?
there is no natural order to the categories, not alphabetical, (eg) colours
define frequency/count.
the number of times a particularly value occurs, only one category is shown
define frequency distribution.
list or table with each category and the frequency, contains multiple categories
define proportions/relative frequencies.
number of one category divided by the total number of subjects
what does the greek letter sigma mean?
means add up all things on the right
how is qualitative data shown? in terms of graphical summaries.
- bar chart (list of categories on a side and bars corresponding to categories count/proportion/%)
- pie chart (circle divided into areas of size matching percentages)
what are the two types of numeric data?
- discrete
- continuous
what is discrete numerical data?
stuff that we can count (countable), be put in a list, and consists of integers
what is continuous numerical data?
any number in a range or interval, with infinitely many decimal places, value cannot be put in a list
how is numerical data organized?
numbers are grouped into classes or bins
what must happen in order to organize numerical data?
we have to lose something (like the infinitely many decimals)
how many bins are typically used when sorting numerical data?
5 - 20 bins (so we do not lose a lot of data but is still more easily understandable
what is single-value grouping of numerical data?
no grouping, every value is in its own section, used almost exclusively with discrete data
what is cut point grouping of numerical data?
continuous numerical data sorted by using intervals or ranges with a lower cut point (minimum) and an upper cut point (maximum)
what does a square bracket mean? “[”
means the number is included
what does a round bracket mean? “(“
means the number is not included
what is a histogram?
used to display quantitive data, we count how many values are in each interval (category)
what is the benefit of using a stem-and-leaf or dot plot over a histogram? what are these plots ideal for?
- lots of details included
- good for small data sets
