Scribd
Upload
3 views

5.2.5. Population and Sample - Sampling

Uploaded by

ranjithias2003
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
3 views

5.2.5. Population and Sample - Sampling

Uploaded by

ranjithias2003
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

Siddhardhan

Population & Sample


- Sampling Techniques

Math for Machine Learning


1. Sample Study

A sample study is a study which is carried out on a


sample which represents the total population.

Sample
Population

Average Blood Sugar Level = ?


Types of Sampling Techniques

Sampling Techniques:

Simple Random Sampling

Systematic Sampling

Stratified Random Sampling

Cluster Sampling

(Probability Sampling Techniques)

(Non-Probability Sampling Techniques)


Simple Random Sampling

In Simple Random Sampling, the sample is randomly picked from a larger


population. Hence, all the individual datapoints has an equal probability to be
selected as sample data.

Example: Employee survey in a company

Pros: Cons:
1. No sample Bias 1. Population size should be high
2. Balanced Sample 2. Cannot represent the population
3. Simple Method of sampling well sometimes
4. Requires less domain knowledge
Systematic Sampling

In Systematic Sampling, the sample is picked from the population at regular


intervals. This type of sampling is carried out if the population is
homogeneous and the data points are uniformly distributed

Example: Selecting every 10th member from a population of 10,000

Pros: Cons:
1. Quick & easy 1. Data manipulation risk
2. Less bias 2. Requires randomness in data
3. Even distribution of data 3. Population should not have
patterns.
Stratified Random Sampling

In Stratified Random Sampling, the population is subdivided into smaller


groups called Strata. Samples are obtained randomly from all these strata.

Example: Smartphone sales in all the states

Pros: Cons:
1. Finds important characteristics in the 1. Cannot be performed on
population populations that cannot be
2. High precision can be obtained if the classified into groups.
differences in the strata is high 2. Overlapping data points
Cluster Sampling

Cluster Sampling is carried out on population that has inherent groups. This
population is subdivided into clusters and then random clusters are taken as
sample.

Example: Smartphone sales in randomly selected states

Pros: Cons:
1. Requires only fewer resources 1. Cannot be performed on populations
2. Reduced Variability without natural groups
3. Advantages of both Random 2. Overlapping data points
sampling and Stratified Sampling 3. Can’t provide a general insight for the
entire population

You might also like