Data Analysis and Statistics-skills.docx

FREE Gift included:
Watch – Basic to Advanced Level Excel Training
https://www.youtube.com/watch?v=1PepfurPwmU
Data Analysis and Statistics
Key terms
 Statistics
 Data
 Data Collection
 Descriptive Statistics
 Inferential Statistics
 Discrete Data
 Continuous Data
 Frequency Distribution
What is Statistics?
Statistics is a science that involves examining and using data. Statisticians
collect data, analyze and interpret it and then put it in a form so that it can
be presented or used. Statistics are used in almost every field in order to
make decisions or to conduct research.

Statistics is the branch of mathematics that deals with data. Data (technically
a plural word; the singular is ‘datum’) is a collection of values. For most of
what we do, it will be numerical data (such as the inflation rate, the number
of bees in a colony, or the marks in a class test), but it can also take other
forms (such as the political party a voter intends to vote for, the football
team they support, and so on).
A collection of data is often referred to as a data set or set of data¸ but other
words such as a list or simply collection are also often used. Don’t worry too
much about the words, just understand that we are referring to a collection
of values.
What is Data?
Data is the collected facts. The individual pieces of fact recorded for the purpose
of analysis is called Data.
Data collection
Data collection is all about how the actual data is collected. There are
however significant issues to consider when actually collecting data. For
data such as marks in a class test, this is fairly straightforward. Each student
has a defined mark associated with them, so the marks are simply collected
together to make the data set.
Sometimes, data is harder to collect. Counting the number of bees in a
colony isn’t easy, because they move and fly around; you may have to
approximate in such cases.
Also, if you are collecting data, you need to be careful where you get it from.
For example, suppose you want to conduct a poll on who people plan to
vote for in an election. You can’t realistically ask everyone in the whole

country (the population), so you have to choose a representative sample of
people. This isn’t as easy as it sounds. In the mid 20th century, for example,
polls were sometimes carried out by randomly calling people in the
telephone directory. This sounds representative, but in those days only the
richer people
had telephones, and so you were asking only a particular section of society,
who might well be more inclined to vote for one party rather than other. The
same issue may apply with doing a poll by email or social media platforms
today.
So, there are issues in the collection of the data; you need to make sure that
the data has been collected fairly before you go on to deal with it, and try to
present it and make conclusions.
Types of Data
1. Qualitative Data
 Data in the form of Words
 No tool used to measure it
 Does not describe quantities or amounts
2. Quantitative Data
 Describes quantities expressed numerically
 There is an objective way of measuring it
How Data is Collected
1. Primary Data
 Data collected for the first time by an investigator for a specific purpose.
 No statistical Operations have been performed
2. Secondary Data
 Data sourced from somewhere
 Statistical analyses have already been performed on it.

The Concepts of Variables
What are Variables?
 Attributes of an object under study.
 Variables are data Items
Types of Variables by Data Type
 Variable have types depending on the data they contain.
o Quantitative Variables e.g Age
o Qualitative Variables e.g Quality of an item.
Quantitative Variables
 Discrete variables: counts of individual items e.g number of people. For
example, you cannot have 2.5 people. It is either 2 or 3 people.
 Continuous variables: Measurements of continuous values e.g Age,
distance or volume. These are values that are on continuous scales. For
example you can have distance which can be 34.5 km.
Qualitative Variables
 Also known as categorical or grouping variables
 For example, for Gender (Male or Female), Marital Status and other.
 You cannot do mathematical calculation on categorical data.
Types of Variables by Role
 Independent Variables
 The variable being thought of as the cause. Variable that is affecting
the outcome of another variable.
 Provides us with data about factors that affect a certain outcome.

 They are also known as Predictors variable.
 In the principle of cause and effect. The independent variables
represent the Cause.
 Dependent Variables
 The variable is being thought of as an effect.
 The values of this variable are expected to change based on what
happens to another variable.
 These are Outcome Variables.
Measurement Levels in Data Analysis
 This is the relationship among values within a variable.
 It is very important for deciding what kind of analyses you can run
 They come from the concept of types of variables (qualitative or
quantitative)
Different measures of variable:
o Qualitative Variable
 Nominal Variables:
 Variables where the categories do not have a logical order e.g
Marital Status can’t be arranged in order.
 Nominal come from the phrase “name only”
 E.g Sex, Marital Status, Race, Colour
 Ordinal Variables:
 Variables where the categories have logical order.
 The word ordinal comes from the word “order”
 Each category or possible value is a level of the variable
 e.g. satisfaction level, level of education, level of
agreement, continuous variables expressed as groups;
something like age group or classes of age.
 Order like education can be grouped in Primary Education,
Secondary Education and Tertiary Education.

 Ordinal can also be captured as rating level satisfaction from
scale 1 to 10.
 Binary Variables:
 Variables with only 2 categories; True or False, Yes or No, On
or Off.
o Quantitative Variables
 Ratio variables:
 These are continuous variables with an absolute zero point.
 For example, for number of people an absolute zero mean there are
no people.
 Values have quality of intervals.
 Interval variables:
 Values have equality of intervals
 The ratio between 2 numbers is not meaningful
 There is no absolute zero, an example here is measuring the decree
of temperature – a zero degree Celsius doesn’t mean there is
absent of temperature level.
Population vs Sample
 Study: Differences between using soft copy vs hard copy study materials on
education performance at a university.
 Population: Let’s say you have 3000 students in your university that you want
to study. Those 3000 students are the population of the University.
o A Population is a complete group of people, objects or items you are trying
to study.
 Sample: Although you have 3000 students as population of the school, you
may not be able to study all the 3000 so you may decide to take a subset or
few of the students to study. The subset taken is called a Sample.
o A Sample is a smaller group of people or objects taken from the population.
o This group will actually participate in your study e.g by responding to a
questionnaire.
o Statistics give us the power to generalize to the population.

Branches of Statistics
1. Descriptive Statistics:
 Numbers used to describe or summarize the sample data
 Aimed at describing the data at hand; not the entire population but the
sample data.
 Use statistical tools such as Mean (Average), Median, Standard Deviation,
Variance etc. We also use Chart to represent such data.
2. Inferential Statistics:
 Uses data from the sample to make generalizations about the population
from where the sample was taken.
 Example of Inferential test are Correlations, T-test, Regression analysis

Data Analysis and Statistics-skills.docx

Recommended

More Related Content

Similar to Data Analysis and Statistics-skills.docx (20)

Recently uploaded (20)

Data Analysis and Statistics-skills.docx