Convenience sample

Here the researcher chooses the sample as per his / her convenience.

It those unit of population will be selected which are in the easy reach of researcher.

Snow ball sampling (chain referral sampling)

In snow ball sampling initially a small sample = chosen

It is much smaller than what is requited

Then selected sample unit help to further selection of more unit.

This new unit further help to another unit selection

This process in continues until sample greatest than required size.


Dimensional sampling

In dimensional sampling researcher specifics, all dimensions of variables.

  And then choose the sample such way that all dimensions are represented in sample.

The sample size of study depending upon the 1purposing of study  2size and nature of the population understudy 3 purpose of study 4time and researcher available for research.

Data collection

Next step: collect data.

-         Hypothesis ne verify cheyyunna data collect cheyyuka.

Collected by 1 originally by the researcher. Or 2 it can be extracted from the data already available.

-         Data can be primary or secondary depending upon it’s source.


Primary data

Is that which collected by the researcher specifically as per the requirement of the study.

Data is collected for a fresh study.

Data collected by a researcher through.


 2 questionnaires

 3 interviews

4 observation etc

Will be considered as primary data.

-         Researcher can record data by observing the sample unit.

-         For this the researcher can either be a part of the group under study or simply can observe the outside.

-         Observation can also made in natural setting or in a controlled environment.

-         Interview can be arranged over telephone / videocall / in personal depending upon the availability of fund and time and depth of study.

-         Data can also collect through survey from: from can be filled by sending through 1 email 2 visiting respondent personally 3 online tools can be used like google from online polis or using website for survey.

-         Questionaries are used to also respondent about their choice views and opinion.

This can be ended (question with multiple choice responds)

This can be close ended (question whit descriptive answer)

-         Or combined

-         Data published already cannot be consider as primary data.


Secondary data

-         It is already available and not collected originally by the researcher for the indent study.

-         It can be collected from published or unpublished source.

-         Published source include:

1 historical document

2 public records

3 statistics

4 reports of ministries or journal

5 book / magazine

6 newspaper / publication


Unpublished source secondary data:

1 diary

2 letters

3 unpublished biographies

-         The selection of method for data collection depend up on the nature of study.

(like for historical studies only secondary data can be used)


Data analysis and hypothesis

-         The next step is to draw conclusion from the data collected.

So as to answer the research questions and to easily the established hypothesis.


-         For this the raw data collected needs to be processed and It can be analysed manually or with the help of software of data management such as Microsoft excel and access and statistical analyse tools like spss / R language / stata & so on.


Commonly used data analysis tricks

Frequency: it helps to know about the extent of preference.

            Eg: (25-50) idayilulla aalukalkk ethra social media account und unn ariyanam.

-         This is a simple a count of people who be longa to this age group and social media accounts.

-         For data with options like yes or no

-         Use 1 for yes or no

-         Then count 1st so get news (who studies)


Percentage: -

It is used to calculate proportion out of total.

Eg: what is the proportion of people in the age group of 25-50 who has social media account.

Answer: - can be answered by dividing the number of people in the age group having social media account with total population of this age group. The X100

% can be also used to find growth rate and declined rate.

Mean: - mean is used to find average number of responses.

It can be used to find:

1 average income

2 average marks

3 average age / speed view

There are different measures like mean / median / mode.

Median: - is used o fins idle value of available data.

Mode: - is used to find value which repeated maximum number of time.

            Eg: “such as most  preferred dish at restaurant”


Standard deviation

-         It is measure of spread of data, around the average.

-         It signifies how diverse of data is.

-         It is useful measure for comparing different set of data. As comparing only one the basis of 1st average will not give complete image.

o   Eg: 2 /// company A, B income of A= 1180 / 1200 /1220 & income of 1110 / 1150 / 2340. Now age of both company = 1200.

o   But there is a hope difference in salary.

-         The difference can be realised with standard deviation.



-         correlation analysis is used to study the relation between variables.

-         It can show the nature of relationship it is whether. If is positive / negative.

-         Positive correlation means: if there is an increase or decrease in the other variable.

-         Positive correlation means increase in one decrease In other variable.

Spurious correlation: data verifies the relationship between variable but the relationship= not realistic. 



-         Regression analysis is used to study the cause-and-effect relationship between dependant & independent variable.

-         Trend in the data can be recorded using such an analysis to make prediction for future.

-         Regression analysis also tell the degree of explained variation.

-         Eg: the impact of different factor like healthy / numbers of rooms / design of the house / road network / neighbourhood on the price of a house is known then price of hours in future can be predicted.

The next step is to present the data is findings this can be presented in the form of text / table / graphs /charter.

-         Explanation can be provided in text.

-         Tables are used to express data.

-         Tables can be constructed for time series data / cross sectional data / and panel data.

-         Data can be expressed in tables in absolute from or in percentage.

-         Graphs are an effective way to show trend & variation.

-         Pictorial representation can be line chart / colonography slacked bar chart / box plot / histogram / pie chart / doughnut chart / scatter plot / population pyramid area chart / radar chart / suable chart / surface chart / Nandigram.


Look chart on txt good who study  //// 2.17

Hypothesis testing

-         the next step is to verify the hypothesis.

-         Null hypothesis is subject to verification.

There can be 2 type conclusion possible.

1 reject null hypothesis

2 unable to reject null hypothesis

-         Different test like 1 t-test, F-test, chi-square test, etc. can be used to test hypothesis.

-         The value of statistic is not be calculated & compared with calculated value of statistics.         

If the complect value lies with in the range of tabulated value. We are unable to reject null hypothesis.

-         The level of significance considered for tabulated value is generally 5% to 1%

 Samskrithi's Teaching Aptitude Notes Previous Pages and Next Page Click Below Links 

For RA Part -07 Notes - Click Here 

Research Aptitude Notes Part -09- Click Here