|
V1
Descriptive Statistics Hi everyone.
Welcome to this first video on descriptive statistics. I'm Renee Clark from
the Swanson School of Engineering. In this first video we're going to talk
about the following topics: what are the two main types of data? The two main
types are quantitative and qualitative and also why
it's important to differentiate between them. From there we're going to talk
about the subtypes of quantitative data with some examples as well as the
subtypes of qualitative data with some examples. Okay so two main
types of data: the first is quantitative, the second is qualitative. But the
question is why is it important to differentiate between them? The answer is is because this
enables you to choose and apply the correct statistical technique for a
certain type of data or certain data set that you might have. Okay
quantitative data which is the first main type consists of measurements and
numbers. Okay there are two subtypes of quantitative data. The first is
continuous data and you've heard this term before. Okay
continuous data has a whole number as well as a fractional or decimal
portion. Okay so for example 10.912 kilograms. Okay the whole number portion
is 10 the decimal or fractional portion is the 912. Okay with continuous data or continuous variables you can
specify them theoretically to finer and finer levels of precision. Okay so
this means that any value is possible. So for
example 10.11 2 3 4 6 6 7 on and on and on inches is a theoretically possible
value. Now whether you have the equipment to measure it to that level of
precision is a different story but it is
theoretically possible to have something that measures that. Okay the second
subtype of quantitative data is discrete data. Okay now with discrete data or
discrete variables it can have only certain or fixed values which we will describe it more on the next slide. Okay still talking
about quantitative data. Continuous data consists of things such as height,
weight, time, length, temperature, humidity. Generally
things you can measure. Okay discrete data, which as
we said can only take on certain or fixed values, can consist of the
following types of data. The first is count data,
for example the number of pets you may have in your household. So for example you could say I have two pets in my
household. You can't say you have 2.5 pets in your household right or 3.17 pets
in your household. The number of pets or something similar can only be a
whole number right? Another example of discrete data
is shoe size. Okay, so for example, in the United States our system looks as
follows: you know someone might have a size six or wear a seven and a half or
wear a nine or a 12 and a half. Generally we don't see shoe sizes shoe sizes outside of that at least in the
US system. Okay neck size would be another example of a
of a discrete piece of data. Dollar amounts are also considered discreet. Qualitative data
also known as categorical data and this is because
with qualitative data, the data comprise categories of a variable, which
you'll see what we mean in a minute. There are two subtypes of qualitative
data. Okay the first is ordinal qualitative data. Okay with ordinal data, the
categories are naturally ordered and ranked. Okay so what do we mean by that?
For example, okay teaching evaluation survey responses or OMET survey
responses. Okay you as a student can rank an
instructor's effectiveness on a scale anywhere from strongly disagree about a
certain teacher's teaching effectiveness, to disagree, to neutral, to agree,
to strongly agree. So there are five different
categories that you know that measure a particular instructor's teaching
effectiveness and you rank that instructor on one of those five categories.
Okay another example of an ordinal qualitative variable or piece of data
would be the severity of one's pain. Okay it may range anywhere from no pain, to mild pain, to moderate pain, to severe
pain. Okay so as you can see, those pieces of data
or the categories are naturally ordered or there's a natural ranking to them.
Okay this is in comparison to nominal qualitative data, which is the second
qualitative data subtype. With nominal variables, the categories have no
natural ordering. Okay so for example, candy color: purple, red, or orange
okay has no natural ordering. Now you may like one candy color over the next
but that's a different variable. That would be preference for candy color. Candy
color in and of itself has no natural ordering. Another example of a nominal
variable would be region of the US, you know in terms of western region,
midwestern region, etc. Okay again has no natural ordering. It is a nominal
categorical variable. We thank the
National Science Foundation under Grant 2335802 for supporting our work.
Thank you for watching! |