Analyzing-and-Visualzing-Data-reply

2 days ago

Rajani Sade 

Data examination: Identifying physical properties and meaning

COLLAPSE

Top of Form

Data examination: Identifying physical properties and meaning

                Next step after Data acquisition is data examination. Here we examine the physical properties of the data, what it contains and what we can get from it. Physical properties we need to observe from the data are type, size, and condition. This is more mechanical work. We have to observe the surface characteristics to understand its properties. Type gives us the nature of the data whether it is qualitative or quantitative. If a variable is qualitative, we have to find out if it is text or nominal or ordinal. If a variable is quantitative then we have to find out if it is interval or ratio, whether it is continuous or discrete. Based on the type we can come up with statistical analysis methods. Size of the variable is the number of bytes it occupies in the database. For each column we have to find out the format of the data and maximum length it requires. Condition tells us about the quality of the data. Some of the checks we do to check the quality of the data is missing values, erroneous values, inconsistency, duplicate records, incorrect dates, Special characters, leading or training blanks etc. From the condition we can estimate what kind of cleanup we can do to make this data useful for the analysis.

 

Reference:

Kirk, A. (2016). Data Visualisation: A Handbook for Data Driven Design. Thousand Oaks, CA: Sage Publications, Ltd. ISBN: 978-1-4739-1214-4

Bottom of Form

Niteshkumar Laxmidas Patel 

Data Examination

Data examination is a process, in which, you would examine and understand the data that one has gathered. It is really important to know that when working with information, you should study the data before making any further decisions. Data investigation is to confirm our outcomes whether it is substantial, reproducible and verifiable. Data  examination is also a procedure of investigating, purging, changing, and demonstrating information with the objective of finding valuable data, illuminating conclusions, and supporting basic leadership (Kirk; 2016) .Data examination has various aspects and methodologies, incorporating assorted systems under an assortment of names, while being utilized as a part of various business, science, and sociology spaces. There are cases, for example at leading information organizations, for example, Amazon and Google, where information is utilized as a part in which examined data, comes about themselves to settle on the choices, for instance with respect to proposal engines , PageRank, and request anticipating frameworks.So, it is important to examine data before making decisions regarding business (Rosenthal, Robert; Rosnow, Ralph L; 1991). 

References:- 

Kirk, A. (2016). Data Visualisation: A Handbook for Data Driven Design (p. 50). SAGE Publications.

Rosenthal, R., & Rosnow, R. L. (1991). Essentials of behavioral research: Methods and data analysis. Boston, MA. 

 

2 days ago

Emmanuel Tachu 

Data Exploration

COLLAPSE

Top of Form

Data exploration resonates with me because this is the process whose completion provides extensive familiarity of a dataset, a step further than what is accomplished at the level of the data examination process (Kirk, 2016). At the data exploration stage, more insight is gotten from datasets and data quality is also a key component that is involved at this stage. The use of a statistical programming language is a great tool for data exploration. Data exploration relies heavily on proper data transformation for best results. Data exploration can be used to show trends in data and relationships between variable or objects (Tan, Steinbach, Karpatne & Kumar, 2019). The use of data visualization tools such as scatter plots, bar charts, heat maps, histograms can be used for a better understanding of data. Using visualizations tools can also be used to view outliers in a data set. Having a curious mindset is a highly valued quality for data scientist, especially in the data exploration phase (EMC, 2015).

References:- 

Kirk, A. (2016). Data Visualisation: A Handbook for Data Driven Design (p. 50). SAGE Publications.

Bottom of Form