The chart you select to represent your data will be influenced by many factors. Kirk (2016) has put each chart into the five main families below:

• Categorical: Comparing categories and distributions of quantities values
• Hierarchical: Charting part-to-whole relationships and hierarchies
• Relational: Graphing relationships to explore correlations and connections
• Temporal: Showing trends and activities over time
• Spatial: Mapping spatial patterns through overlays and distortions

Reply to 

Relational chart- Scatter Plot

As Kirk mentioned, the Relational chart types are about drawing relationships to explore correlations and connections. The correlation explains the linear relationship between the two entities. If it is 0, then there is no relation, 1 represents linear relationship and -1 represents the negative relationship.

I would like to present a scatter plot https://plot.ly/~mendy/1093.embed this explains the required sleep quantity of human beings by age. Here the y-axis represents the hours and the x-axis represents the age. As we go along the x-axis toward the greater numbers, the points move down which means the y-values are decreasing, making this a negative correlation.

This graph is simple and easy to understand, the graph itself clearly explains that when the person we a person grows older, he or she needs less sleep. The slope of the graph is decreasing, without doing any calculations also the audience can easily understand this.

There a room for improvement in this Visualization, this is a very simple and plain graph. We can apply color coding for this. For example, if we know the age group of the audience or our targeted customers, so we can highlight that dots with different colors, they are easy to attract, people also think their sleep quantity with this graph.

References:

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

•https://plot.ly/~mendy/1093.embed

Venkata Sudhir Manepalli

Week #6 Discussion

COLLAPSE

Data visualization define as representing textual and numeric raw data into viewer visualization. The author says there are four involving stages to define a good data visualization as goes through this involvement process such as

1. Formulating your brief.
2. Working with data.
3. Establishing your editorial thinking.
4. Data Representation.

The first three stages mainly focus on refining data from the raw data and also gives an outline of the project’s entry point and exit point which exactly similar to the wire frame or flow of the project. Here question comes in the final stage when discussing the data representation where exactly how to show the collected data?

So the data representation is the critical stage among these, to represent the visual of the data. As the author stated based on the data the visual charts will be changed or belongs to particular chart families by many factors. Here I select a Relational chart from the chart families of acronym CHRTS.

Relational Chart

The charts discuss showing the relationship between one variable to many variables in a different. These relations can be in shown either positive or negative. Sometimes these can be neutral as well. These relational charts are done for one-dimensional data, which shows different data points in a linear way. Such kind of data sets is linearly varying with the time as an independent variable. These type charts are also known as time-variant charts.

Why this chart?

The scale of declaring data points in charts mostly depends on the variables declared on either axis which mostly explains the relationship between fixed variables and variant variables. In most cases, the change can only be represented by Time.

Scatter Plot is one of the plot types from the relational chart type which explains two numeric variables in two axes and defines the data point. It’s easy to make a connection between two entities. Correlation is also strong. If the data points vary to the maximum level, we can perform a mathematical transformation to make strong relation between the entities, for example, using log functions we can convert the values into decimals and performs a linear functionality between the variables.

References

https://www.mathsisfun.com/data/scatter-xy-plots.h...

Kirk, A. (2019). Data visualization: a handbook for data driven design. Los Angeles: SAGE

Hemanth Gogineni

Discussion

According to Kirk (2016), The chart you select to represent many factors will influence your data. Today I would like to discuss the Bar charts, which are a part of the categorical family, which is mainly used to compare categories and distributions of quantities and values.

Bar graphs are an amazingly powerful visual to use in introductions and reports. They are well known because they permit the users to perceive examples or patterns unquestionably more effectively than reading a table of numerical data. Bar graphs are an effective way to compare items between different groups. A bar chart shows a bar for every category. The bars are similarly separated and similarly broad. The length of each bar is relative to the recurrence of the comparing category.

Bar charts help us to interpret the difference in the trends in a large number of categories. They are easy to use and commonly used types of data presentations. Aside from visual contrasts, there is significant crucial differentiation between bar graphs and scatter plot and the line plot. Both of which display two numerical variables – the variables on both axes are numerical. In contrast, the bar chart has categories on one axis and statistical frequencies on the other. “Bar charts are intended as visualizations of categorical variables. When the variable is numerical, the numerical relations between its values have to be considered when we create visualizations.” (Adhikari. A (2018))

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

Adhikari, Ani (2018). Foundations of Data Science. (Chapter7) .UC Berkeley.