Ad Code



What is Data Analysis ? | Objectives. Process, Types, Phases & Key Consideration

Data Analysis

Contents :
  1. Meaning of Data Analysis.
  2. Objectives of Data Analysis.
  3. Key Consideration of Data Analysis.
  4. Types of Data Analysis.
  5. Phases of Data Analysis.
  6. Process of Data Analysis.

What is Data Analysis ?

Data analysis can be defined as the process of gathering, modelling and transforming data so as to get useful information, suggestions and conclusions in decision-making.

Appropriate analytical tools are used to convert raw data into information that can be used in marketing research. Percentile and ratios are some elementary methods of data analysis. Some statistical methods such as mean, median, mode, percentage, and standard deviation should be used as per requirement.

Tests of significance, factor analysis, multiple discriminate analysis, and regression analysis can also be used as advanced statistical tools.

Objectives of Data Analysis 

  • Assessment and improvement of the quality of the data.
  • Compare the target population with the population being studied (sampling population).
  • Forecast the possible areas where faults can occur (such as degree of non-response, amount of denials, the comparison groups or the reduction or decrease in number).
  • Assessment of the measures of frequency (such as mean, median, mode, etc.) and their amount.
  • Assessing, i.e. how much strong relationship exists among the variables.
  • Measurement of the degree of ambiguity.
  • Observe and control the influences of other associated characteristics.
  • Making inferences and taking decisions.
  • To acquire insights regarding the relationships which are being observed or not attended.

Key Considerations in Data Analysis 

In order lo draw precise conclusion from the data analysis many problems, issues and considerations have to be dealt with carefully during the entire process of data analysis. The investigator is aided with these conclusions while making the decisions.
The points of consideration during data analysis are as follows :
  1. Avoid business during the entire stages of data analysis.
  2. There should be clarity in terms of the purpose of the research or the field of the research study or analysis.
  3. During the research analysis, objective of the problem domain should be clear.
  4. Researcher should have good knowledge and experience of using statistical tools.
  5. Select the right techniques for the analysis.
  6. The assumption of every statistical tool should be studied properly prior to data analysis.
  7. The size of the sample should be large enough in order to facilitate the right outcomes and decisions.
  8. The conclusion must be consistent & trustworthy.
  9. Proper training should be given to the observer and data analysis to avoid the errors and faults.
  10. The presentation of the data must be suitable and appropriate.
  11. The preciseness of the analysis is must, so that there is no room for doubt.
  12. The features of the sample under study should be properly understood.
  13. The person carrying out the data analysis should be fully acquainted with the different accessible formats and layouts for presenting the data.
  14. Every step of the data analysis should be well planned and should be carefully observed to avoid the deviation.

Types of Data Analysis 

1) Descriptive and Causal Analysis : 
The descriptive analysis is mainly employed for the purpose of elaborating the data (taken from the population) which is under the sampling observation either graphically or numerically.
It is possible to carry out the analysis of one, two or more than two variables at the same time. Thus, based on the number of variables used, data analysis can be defined as :

i) Uni-variate Analysis : 
It is one of the simplest forms of data analysis. In this method summarization of the data depends on the separate variables of a data set.
The use of this technique is mainly related to those cases when the investigator likes to take individual measurement of the sample, оr in case when there are many measurements but the researcher studies only one variable at a time.

ii) Bi-Variate Analysis : 
This analysis is used for the measurement when there is some relationship between two variables. The results are obtained in the form of percentage, scatter plot, histogram table, correlation coefficient, etc. This analysis also identifies that weather the variables which are under the study is dependent or independent.

iii) Multivariate Analysis : 
Due to the complexity of the research problem in present days, the data analysis has both multiple independent and dependent variables. So, this analysis is used by the researchers when they take two or more variables for the measurement all the same time.
Note : Based on the nature of the problem, generally every statistical method is classified as uni-variate or multivariate analysis.

2) Inferential Analysis / Statistical Inference :
It is used by the investigators when they have acquired the data from the sample through a random procedure (using probability method) and with a high response rate. If the data collection is done through non-probability method with the lower response rate, then this method is not used for the analysis. The two main groups of the problems which are deals with the statistical deduction are as follows :

i) Estimation : 
Estimation is a procedure which is employed in the case of the statistics (which is acquired from the sample) for the purpose of estimating the unknown parameter of the population under study.

ii) Hypotheses Testing : 
Hypothesis testing is the procedure to examine the hypothesis of the main population from where the sample has been drawn.

Phases of Data Analysis 

Basically data analysis is divided in two phases / Steps :

1) Preliminary Data Analysis : 
Preliminary data analysis is applied before the hypothesis testing for obtaining the knowledge about the properties of the collected data. This analysis clarifies that how well the coding, inputting, scaling art done. It also clarifies the data validity or systematic bias. The outcome of this analysis influences result and conclusion.

2) Hypothesis Testing : 
It is required to check the assumptions before testing hypothesis to improve the interpretation of the results of the tests. Hypothesis testing finds the validity of the
assumption with a view to choose between two opposite hypothesis about the population parameter.

Process of Data Analysis 

The data analysis process, or alternately, data analysis steps, involves gathering all the information, processing it, exploring the data, and using it to find patterns and other insights. The process consists of:

  1. Data Requirement Gathering : Ask yourself why you’re doing this analysis, what type of data analysis you want to use, and what data you are planning on analyzing.
  2. Data Collection : Guided by the requirements you’ve identified, it’s time to collect the data from your sources. Sources include case studies, surveys, interviews, questionnaires, direct observation, and focus groups. Make sure to organize the collected data for analysis.
  3. Data Cleaning : Not all of the data you collect will be useful, so it’s time to clean it up. This process is where you remove white spaces, duplicate records, and basic errors. Data cleaning is mandatory before sending the information on for analysis.
  4. Data Analysis : Here is where you use data analysis software and other tools to help you interpret and understand the data and arrive at conclusions. Data analysis tools include ExcelPython, R, Looker, Rapid Miner, Chartio, Metabase, Redash, and Microsoft Power BI.
  5. Data Interpretation : Now that you have your results, you need to interpret them and come up with the best courses of action, based on your findings.
  6. Data Visualization : Data visualization is a fancy way of saying, “graphically show your information in a way that people can read and understand it.” You can use charts, graphs, maps, bullet points, or a host of other methods. Visualization helps you derive valuable insights by helping you compare datasets and observe relationships.


Post a Comment