At SmartCapitalMind, we're committed to delivering accurate, trustworthy information. Our expert-authored content is rigorously fact-checked and sourced from credible authorities. Discover how we uphold the highest standards in providing you with reliable knowledge.
Data analysis techniques allow researchers to review gathered data and make inferences or determination from the information. Most techniques focus on the application of quantitative techniques to review the data. A few of the more popular quantitative data analysis techniques include descriptive statistics, exploratory data analysis and confirmatory data analysis. The latter two involve the use of supporting or not supporting a predetermined hypothesis. Groups who may use these techniques include individual researchers, students, businesses, government agencies and actuaries, among other parties needing information and data.
Quantitative data analysis attempts to remove researcher bias from gathered data. Heavy use of statistics, probabilities or other mathematical techniques allows individuals to use standard methods for interpreting data. When researchers attempt to use qualitative data analysis techniques — often based on the individual’s personal background, preferences or basic research and reasoning principles — the gathered data may be misread or incorrectly interpreted. Therefore, mathematical techniques are less susceptible to these errors and often more accepted by other individuals or researchers.
Descriptive statistical analysis separate or summarize data into specific groups. Demographics are a common set of descriptive statistics. Researchers will gather information relating to a population’s age, sex, household size, income, job type and other information. Another type of descriptive statistical analysis is the completion percentage of a quarterback when playing in a football game. If the quarterback completes six out of eight pass attempts, he has a 75 percent completion percentage. A flaw in this technique is the inability for the statistics to provide additional information, such as the length of each pass.
Exploratory data analysis techniques often involve the use of box plots, histograms, Pareto charts, scatter plots or a stem-and-leaf plot. The main purpose for this technique is to support a stated hypothesis from a researcher. For example, a researcher may desire to prove a hypothesis about the age range of owners who drive a specific type of car, such as a minivan. To test and support this hypothesis, the researcher will gather information and create a box plot to determine the number of owners within his stated range. The statistics will provide information to support or not support the hypothesis and show how many outliers are in the gathered data.
Confirmatory data analysis techniques are the opposite of exploratory techniques. In these tests, the researcher is looking to disprove the null hypothesis, which is a statement generally accepted as true by most individuals. To disprove the null hypothesis, the researcher will gather specific information related to the hypothesis and test the average, variance, p-values and confidence intervals. The confidence interval proven by the confirmatory data analysis will provide information as to how confident the researcher should be about whether the null hypothesis is true or false.