The 2 Types of Data

There are many different kinds of data out there. The first kind is called qualitative data, which is stuff like opinions and thoughts. The other kind is called quantitative data, which includes stuff like numbers and measurements. There is the continuous data, which includes things like height, weight, and time. And there is discrete data, which includes things like sex or race. Data can also be categorized as ordinal and nominal. A set in ordinal data has an ordered sequence to it.

Because data comes in many forms. There are quantitative data, qualitative data, and nominal data. Quantitative data can be continuous or discrete.

What is data?

Data is things that are collected. It can be quantitative or qualitative. Quantitative data can be continuous (like height) or discrete (like particular species). Qualitative data has different kinds of categories, like nominal (like names), ordinal (like sizes), and normal (like numbers).

Data is any kind of information. You have different kinds of information, like quantitative and qualitative. Quantitative means you can count it or measure it. Qualitative means you can't count it or measure it, you have to look at it in other ways. If a thing can be counted, or measured in any way, then you have quantitative data.

There are a lot of ways to describe it. There is quantitative data, like how tall someone is. And there is qualitative data, like what kind of person someone is. There are also ratio data, and interval data and ranking data.

If you have a set of things, there are different ways of analyzing it. You can analyze it using numbers. If there is a number for each thing in the set, then you have quantitative data. If there is no number for each thing in the set, but there are only different categories for which to put each thing into, then you have qualitative data. Quantitative data can be continuous or discrete. Continuous data has an infinite number of possible numbers along a scale.

Numerical data is nearly infinite in range, but it's still finite. There are simple types of data you can use but to make a good model you need more complex types of data.

Statistical data can be classified into two types: discrete and continuous data. Discrete data has only a finite or limited number of values such as male or female; discrete stands for counting objects individually. Continuous data takes on any value within some range, such as height, temperature or weight; it is measured in units rather than counted. Further, quantitative data makes sense only if it comes in the form of numbers. Qualitative (or "categorical") data consists not of numbers but of categories.

Here is a transcribed audio lesson:

there's really a tree of the

types of data that you can have so data

is is a pretty broad term

and and most people categorize it into

two main views and the first is the

quantitative data

and and you know we're going obviously

the other one is qualitative but in the

quantitative piece of it you have

you have the continuous or variable data

and then you have discrete data so

continuous data would be

when you say how tall is the person it

can be any number along a scale and

obviously you're not going to have a 40

foot tall person but anywhere within

that range it could be any of an

infinite number of decimals you know you

can have

anywhere along a sliding scale that

you're not fixed at what you can choose

discrete data would be something like

how many wheels are on the vehicle that

you're looking at and generally it'll be

two for a motorcycle

three for

a three wheel atv four for a truck

six for a dually there's a finite number

of choices and when you have that finite

number of choices it becomes discrete

data

now on the qualitative side you have the

open questions and those are when you

you leave the uh you know comment

section on a questionnaire you're going

to get a piece of information that

doesn't

um

collate neatly you can't can you can't

consolidate it very neatly when you ask

how do you like your burger at a fast

food restaurant if people are going to

put any of a variety of pieces of

information there and still data it's

not data that's easily parsed out

but on the other side you have something

called attribute data and this is when

you have a specific um

you know an

a specific thing from a set of possible

answers and what you'll find is that

people often lump attribute and discrete

data together so if you have attribute

data where it's like a color

it's it's sometimes discrete and

attribute data used interchangeably as

terms and i just break it down like this

for my own convenience here as i look at

it and it gives a little bit more

structure to how you approach looking at

your data types but just keep in mind

that you may see those things used

interchangeably so sometimes you have

attribute data used to describe things

like number of wheels on a car

but anyway for the attribute data

there's two basic things when you look

at a set you'll have a sequence set

which is called ordinal data and that

just means that you have small medium

large or some kind of logical sequence

to it and you have nominal data which is

just a random

pile of possible answers like the type

of pets in a city

so you have all this different breakdown

of data and generally you know there may

be more ways to look at it but almost

any piece of data you have will fit into

one of these five ends of this tree

so let's take a look at some examples of

this data

well first is continuous if you say how

long is something or how tall is

somebody

1.2341 meters is a piece of continuous

or variable data

if you ask like i said a number of

wheels on a truck that is a discrete

piece of information or piece of data

ordinal a lot of scales or you

know when you have the five little

bubbles you fill in that'll be set up as

ordinal very satisfied satisfied average

unsatisfied things like that

nominal data as i said pets it's a group

you can pick from that group but it's a

very finite amount of possible answers

you have and of course the open answers

is please describe your shopping

experience so i could ask that question

on a questionnaire as people purchase

things off my website

so i can i can get open data like that

now the benefit of open data is you you

don't limit the possible answers a

person gives you

but you do have a lot more

time that you have to commit to really

going through that data and figuring out

what people mean

so now the issue with data as you decide

what kind of data you have

you want to make sure that you can put

the data to use properly and generally

you can go from height to a grouping of

tall medium short based on some

criteria and then you can take that into

a percentage when you when you

you know aggregate aggregate your data

and and this would be something like

yield if you have you know 27 failure

rate

you know you'd have a percentage there

and you can go in this direction very

easily when you have a very

specific piece of information such as

that height 1.2341

you can go down to the percent of people

who are tall very easily

but if you just have a number as a

percentage if you have a 27 yield or 32

percent tall it's harder to go and break

down in the other direction

so you can't take a yield number and

figure out what the actual averages or

you know readings were

or or the distribution of the actual

information at the front of it so keep

in mind that as you gather the dating

start thinking about how much effort you

want to put into it

try to predict whether you need to go

back and forth on it

so obviously taking a tape measure out

and measuring people

is a lot harder than eyeballing whether

they're tall medium or short as they

walk into a restaurant or something like

that

so the information

again the more precise you get and the

more

you know usable and flexible the answers are

the higher the cost.