Statistics
- Statistics is the discipline that concerns the collection,
organization, analysis, interpretation, and presentation of data. In
applying statistics to a scientific, industrial, or social problem, it is
conventional to begin with a statistical population or a statistical
model to be studied.
- the practice or science of collecting and analyzing numerical data
in large quantities, especially for the purpose of inferring
proportions in a whole from those in a representative sample.
Variable
- In mathematics, a variable is a symbol, typically a letter, that refers
to a mathematical object. One says colloquially that the variable
represents or denotes the object, and that any valid candidate for
the object is the value of the variable.
- Mathematics
(of a quantity) able to assume different numerical values.
Population
- The term population mean represents the average score of the
population on a given variable and symbolizes: μ = ( Σ Xi ) / N. The
symbol 'μ' stands for the population mean. Meanwhile, 'Σ Xi'
indicates the sum of all scores in the population (such as X1, X2, X3,
and so on).
Sample
- A sample is a selection (subset) of data from a larger group of data,
(called the population.) A sample should be representative of the
population, this means the sample and the population should have
similar properties. A population is a particular group of individuals
or items.
- In statistics, quality assurance, and survey methodology, sampling
is the selection of a subset or a statistical sample of individuals
from within a statistical population to estimate characteristics of
the whole population.
Data
- In statistics, data is a collection of facts, observations, or
measurements that are used to analyze and make decisions. Data
can be numerical or categorical, and is the starting point for
statistical analysis.
Sampling Techniques
- Sampling techniques in statistics are methods used to select a
subset of a population for study in order to gain insights about the
larger group:
- The goal of sampling is to approximate the characteristics of a
larger population that are relevant to a research question.
Sampling techniques are important because studying an entire
population can be expensive, time-consuming, or even
impossible.
- Here are some sampling techniques:
- Simple random sampling
Every member of the population has an equal chance of being
selected for the sample.
- Stratified random sampling
The population is divided into groups, and members are randomly
selected from each group.
- Systematic sampling
A random selection is made for the first item, and then a rule is
used to select every nth item after that.
- Convenience sampling
A non-probability sampling method that involves selecting a
sample based on convenience.
- Quota sampling
A non-probability sampling method.
- Purposive sampling
A non-probability sampling method.
- Expert sampling
A non-random technique that involves selecting respondents
based on their expertise on the topic being studied.
- Snowball sampling
A technique that involves identifying a few respondents who meet
the selection criteria and asking them to recommend others who
also meet the criteria.
The classification of branches of statistics
- Descriptive statistics
Involves gathering and organizing data to describe its properties,
such as mean, variance, skewness, and kurtosis.
- Inferential statistics
Uses the properties of data to draw conclusions, test hypotheses,
and make predictions. Examples of inferential statistics include
linear regression analysis, analysis of variance (ANOVA),
logit/Probit models, and null hypothesis testing.
Classification of variables
- Variables can be classified into two main categories: categorical
and numeric. Each category can then be further classified into
subcategories:
- Categorical variables: Can be classified as either nominal or
ordinal. Categorical variables are also known as qualitative
variables.
- Numeric variables: Can be classified as either discrete or
continuous.
The types of data
- Qualitative data
Also known as categorical data, this type of data is observed and
cannot be measured numerically. Examples include gender, race,
age group, and origin.
- Quantitative data
Also known as numerical data, this type of data can be measured or
counted and is expressed in numbers. Examples include height,
distance, and water.
- These two main types of data can be further subdivided into four
subtypes:
- Nominal data
Categorical information that lacks inherent order or ranking.
Examples include gender, nationality, or hair color.
- Ordinal data
A type of qualitative data that groups data into ordered categorical
variables. Examples include socioeconomic status and educational
level.
- Discrete data
Data with values that are separate and distinct. It can be counted
but not measured. An example is the number of heads in 100 coin
flips.
- Continuous data
Represents measurements and their values can't be counted but
can be measured. An example is height.
Different methods of sampling techniques
- Simple random sampling
A random selection process where each member of the population
has an equal chance of being selected. This method is best for
homogeneous populations.
- Convenience sampling
Samples are selected from the population because they are easily
available to the researcher.
- Quota sampling
Samples are created based on specific characteristics or traits,
such as age. This method is often used when researchers need to
collect data from a specific demographic.
- Systematic sampling
Similar to simple random sampling, but individuals are chosen at
regular intervals instead of randomly generating numbers.
- Non-probability sampling
The researcher's judgment or convenience is used to select
samples, rather than ensuring that each member of the population
has an equal chance of being included. This approach can
introduce bias and limit the generalizability of findings.
- Snowball sampling
Selected participants are asked to refer to others who may qualify
for the survey. This method is useful when there is no sampling
frame available or when the researcher doesn't know much about
the target population.
- Stratified sampling
The population is divided into subsets, or strata, based on shared
characteristics. This method improves the accuracy and
representativeness of the results by reducing sampling bias.
- Cluster sampling
The unit of analysis is based on intact groups, such as an entire
school or classroom, rather than individuals.
Different scale or level of measurement of data
- Nominal
Data is categorized but not structured or ordered. Examples
include male/female, pass/fail, and presence/absence.
- Ordinal
Data can be categorized and ranked, but there's no information
about what differentiates the categories. These values can't be
added to or subtracted from.
- Interval
Data can be categorized, ranked, and evenly spaced, but there is no
true zero. The distance between successive numbers is equal, but
zero does not mean there is none of the property being measured.
- Ratio
Data can be categorized, ranked, evenly spaced, and has a natural
zero. This allows researchers to compare differences or intervals,
and assess ratios.