WEBVTT

00:00.000 --> 00:10.000
Different types of statistical analysis.

00:10.000 --> 00:19.000
Descriptive statistical analysis.

00:19.000 --> 00:22.000
This type focuses on summarizing and presenting

00:22.000 --> 00:24.000
the main features of a data set.

00:24.000 --> 00:28.000
Measure such as mean, median, mode, range

00:28.000 --> 00:31.000
and standard deviation fall under this category.

00:31.000 --> 00:34.000
It helps organize and simplify large amounts of data

00:34.000 --> 00:36.000
for better understanding.

00:36.000 --> 00:39.000
This type of analysis focuses on describing

00:39.000 --> 00:41.000
the main features of a data set,

00:41.000 --> 00:44.000
offering a snapshot of its central tendency,

00:44.000 --> 00:50.000
variability, and distribution.

00:50.000 --> 00:53.000
Inferential statistical analysis.

00:53.000 --> 00:56.000
Inferential analysis involves concluding

00:56.000 --> 00:59.000
about a population based on a sample of data.

00:59.000 --> 01:02.000
It uses probability theory and statistical methods

01:02.000 --> 01:06.000
to make predictions or inferences about a larger group

01:06.000 --> 01:12.000
based on a smaller representative sample.

01:12.000 --> 01:14.000
Prescriptive analysis.

01:14.000 --> 01:16.000
This type involves recommending actions

01:16.000 --> 01:19.000
based on the analysis of past data.

01:19.000 --> 01:21.000
It goes beyond predicting outcomes

01:21.000 --> 01:23.000
and suggests optimal courses of action

01:23.000 --> 01:26.000
to achieve specific objectives.

01:26.000 --> 01:29.000
It's particularly useful for decision making

01:29.000 --> 01:34.000
and strategic planning.

01:34.000 --> 01:36.000
Predictive analysis.

01:36.000 --> 01:39.000
Predictive analysis involves using historical data

01:39.000 --> 01:43.000
and statistical algorithms to predict future outcomes.

01:43.000 --> 01:46.000
It's commonly used in forecasting trends,

01:46.000 --> 01:49.000
identifying patterns, and making informed predictions

01:49.000 --> 01:53.000
about future events.

01:53.000 --> 01:55.000
Causal analysis.

01:55.000 --> 01:58.000
Causal analysis aims to identify the cause

01:58.000 --> 02:00.000
and effect relationships between variables,

02:00.000 --> 02:03.000
any characteristic, number, or quantity

02:03.000 --> 02:06.000
that can be measured or quantified.

02:06.000 --> 02:08.000
It goes beyond correlation,

02:08.000 --> 02:11.000
attempting to establish a direct relationship

02:11.000 --> 02:13.000
between one variable and another,

02:13.000 --> 02:18.000
helping understand the reasons behind observed phenomena.

02:19.000 --> 02:22.000
Exploratory data analysis.

02:22.000 --> 02:25.000
This analysis involves exploring data sets

02:25.000 --> 02:29.000
to discover patterns, relationships, or anomalies.

02:29.000 --> 02:32.000
It includes techniques such as data visualization,

02:32.000 --> 02:35.000
summarization, and trend identification.

02:35.000 --> 02:38.000
EDA is often a preliminary step

02:38.000 --> 02:44.000
in understanding the nature of the data.

02:44.000 --> 02:46.000
Mechanistic analysis.

02:46.000 --> 02:48.000
Mechanistic analysis seeks to understand

02:48.000 --> 02:50.000
the underlying mechanisms or processes

02:50.000 --> 02:53.000
that lead to certain observations.

02:53.000 --> 02:55.000
It goes beyond statistical associations

02:55.000 --> 02:58.000
and aims to uncover the fundamental workings

02:58.000 --> 03:03.000
or processes responsible for the observed data patterns.