Blog

Abstract

Data analysis, also known as “analysis of data” or “data analytics”, is the process of inspecting and cleansing data, transforming it, and modeling it with the aim of finding useful information and supporting decisions. There are many facets to data analysis. They include a range of approaches and techniques that can be used in different areas, such as science and business. Data mining, which focuses on predictive and not merely descriptive modeling, is one type of data analysis. Business intelligence, on the other hand, involves data analysis that heavily relies on aggregation. Data analysis in statistical applications can be broken down into three types: exploratory, confirmatory and descriptive statistics. EDA is about discovering new features in data CDA to confirm or discredit existing hypotheses. Predictive analytics is concerned with the application of statistical models to predict or classify, while text analytics uses statistical, linguistics and structural techniques to extract information from textual sources. There are many types of data analysis. Data integration is the precursor to data analysis. Data analysis is closely tied to data visualization, data dissemination, and data analysis. Data modeling is often referred to as data analysis.

Introduction

Data processing is the first step in transforming raw data into information. Next, data analysis follows. Data analysis is the use of statistical techniques to organize data in order to answer research questions. Analyses can be described as the order, breaking down of the data into its constituent parts and manipulating the data to answer the research question. Analysing is followed by the interpretation of the research results. This allows you to draw inferences and conclusions about the relationships. An open-minded, flexible analyst will devise a plan to analyze data.

Good, Bar, and Scats have provided four methods to begin analysis of the data gathered.

1. To think in terms significant tables that are allowed by the data.
2. To carefully examine the problem statement and the earlier analysis, and to review the original data records.
3. To be able to look at the problem from a layman’s perspective or to discuss it with others.
4. You can use statistical calculations to analyze the data. All of these methods can be used for data analysis. Factors such as the type of data and the qualifications of the researcher who is performing the analysis, as well assumptions that underlie a statistical technique, can influence the data analysis strategy.

Objectives

When planning for the future requires that you frame the problems through goal identification and realistic goals and targets, it is crucial to do so. The way problems are presented will determine the nature of solutions and the criteria by which they will be evaluated. This section identifies goals and objectives for East Anchorage’s future transportation system. It helps ensure that we achieve those goals by ensuring that our future transportation system is in line with these goals. This section describes the current goals and objectives that guide transportation planning and improvements at the local, state, federal and national levels.

Different types of Anaysis

Quantitative data is anything that can be expressed in numbers or quantified. Quantitative data can be expressed as a number or quantified in the following examples: scores on achievement tests, hours studied, weight of a subject. These data can be represented as ordinal, interval, and ratio scales. They are easily manipulable.

Qualitative data can’t be expressed in numbers. Nominal scales like gender, socioeconomic status, religious preference, and so on are often considered qualitative data. Data analysis is the process of breaking down a data set into its components for individual examination. Data analysis refers to the process of obtaining raw data and then converting it into useful information for decision-making. Data analysis is the process of analyzing data in order to answer questions, disprove theories, or test hypotheses. John Tukey, a statistician, defined data analysis as “Procedures for analysing data, techniques for interpret the results of such procedures and ways of planning the collection of data to make it easier, more precise, or more accurate. Also, all the machinery and results (mathematical), statistics that apply to the analysis of data.” Below are the phases. These phases are iterative. Feedback from later phases can lead to additional work in the earlier phases.

Data requirements

Based on the needs of the customers or those who are directing the analysis, the data that is required for the analysis’s inputs are determined. An experimental unit is the general entity on which data will be collected. It can also refer to a population or person. You can specify and obtain specific variables about a population, such as income and age. Data can be either numerical or categorical (i.e. a text label for numbers). Data collection Data can be collected from many sources. Analysts may communicate the requirements to data custodians, such as IT personnel within an organisation. Data may also be collected using sensors such as traffic cameras and satellites. You can also obtain it through interviews, downloading from online sources, and reading documentation.

Data processing

Conceptually, the phases of the intelligence process used to transform raw information into actionable intelligence and knowledge are similar to those in data analysis. Data must first be processed or organized for analysis. These may include putting data into tables (i.e. structured data) and then analyzing it in statistical software or spreadsheets.

Data cleaning

Data that has been processed and organized may become incomplete, duplicated, or incorrect after it is done. Data cleaning is required when there are problems with the data’s storage and entry. Data cleaning is the act of correcting and preventing these errors. Record matching, identifying errors in data, overall quality, data quality, column segmentation, and duplication are all common tasks. These data issues can be identified using a variety of analytical methods. With financial data, for example, totals may be compared to published numbers that are believed to be reliable. You may also review unusual amounts that exceed or fall below pre-determined thresholds. There are many types of data cleansing that can be done depending on what type of data is being cleaned, such as employer names, phone numbers, and email addresses. To get rid of data that has been entered incorrectly, quantitative data methods can be used. Although spell-checkers for textual data can reduce the number of incorrectly entered words, it is difficult to determine if the words are correct.

Conclusion

We will no longer be able to do live data analysis. We need different types of analysis in each field. This will help as much. Data analysis can be used in many areas, including the statistical, economic, and business fields. This analysis will give us accurate and reliable results.

Refer to

1. Research methodology (Shashi K.Gupta, Praneet Rangei)