In research and statistics, data are fundamental. Through the analysis of data, one can learn, test hypotheses, and develop conclusions. As such, regression analysis comes in as a statistical tool used to compare the relationship between two variables. Gunst (2018) asserts that by assessing the two sets of data, modeling the future relationship between them can be possible.
There are different kinds of data that can be used to develop various kinds of graphs. The graphs include bar graphs, pie charts, histograms, and line graphs. This entirely depends on the information gathered. Data can be quantitative or qualitative. While quantitative data is documented in numbers and signifies measurements or counts like weight and temperature, qualitative data represents those traits that cannot be measured with numbers, for instance, taste, skin color, or marital status. Furthermore, these data can still be categorized as discrete or continuous. Discrete data cannot be divided into smaller units. For example, a household can have 3 people and not 3.5 people. Continuous data can be in any numerical value and also be divided into smaller units.
Delegate your assignment to our experts and they will do the rest.
An example of when I used data was a time when I developed a relationship between two variables (teen birth rate and poverty level data) in my local area. The dataset was n = 50 for the different estates in my area. The variables were y = birth rate per 100 females aged 26 to 17 years and x = poverty levels. X was found as a percentage of the estate population with income below the mark defined by the federal government. A plot of the above data on scatterplot showed a linear relationship with a positive slope. The regression equation was y = 1.373x + 4.236 with a slope of 1.3, meaning that for each one percent of birth rate, there was a corresponding increase of one percent increase in the poverty rate. In this research, I employed a linear regression analysis method to obtain our relationship. The outcome was successful and related to the real situation, that is, the birth rate for 16 to 17-year-old girls increase as the poverty levels increase in the area.
Reference
Gunst, R. F. (2018). Regression analysis and its application: a data-oriented approach. Routledge.
Response 1
Data is the backbone of solving any problem. You have clearly put into perspective the importance of data and research in your telecommunication network field. I liked the way you used data to develop a relationship between two variables, network availability, and customer's downtime. This is what regression analysis entails. In the end, the data analysis would inform the solution to the problem. In your example, it determined that 99.96% network availability was too low compared to the required 99.9995%. I concur with you that to develop a relationship, extensive research is key. Looking into your task, you gathered data from the outage trouble tickets and customers who experienced downtime in that month. The data was then collected for the last 6 months, plugged into excel and bar charts to come up with the conclusion. I could recommend using a scatterplot and regression line, alongside the bar chart, to plot the collected data to be able to arrive at fine-tuned results. From this, a correct equation would be developed, which may generate more accurate results.
Response 2
Data can be in ratios, numbers, or intervals. Your explanation of the different kinds of data is well put. It can be numeral, that is measurable, or discrete. The kind of information contained in the data dictates the kind of graph to use. I concur with you that Bar Charts and Pie Charts are useful for showing percentages and comparisons between different variables. I like how you have used Nike’s sales to explain how data is used. From your example, it can be seen that you were comparing two variables, market share, and Nike’s products. It shows how regression analysis is useful when comparing different variables among organizations. Besides, I could recommend the use of scatterplot and regression line to develop equations and relationships between the variables in the context. This can help generate more accurate and reliable results. The fact that you have used different countries showed that you have adequate data to deduce the conclusion, which is the aim of regression analysis.
