Data Management Basic Steps

Data Management Six Basic Steps

• 1. Identify the problem or opportunity:

  • Define the objective of the study.
  • Determine if the study focuses on a population or a sample, and how large the sample should be.
  • Specify if the study involves treatment, an experiment, or a measurement.

• 2. Decide on the method of data collection:

  • Choose between internal, external, primary, or secondary data.
  • Select an appropriate method (experimental study, observation, survey, or questionnaire).

• 3. Collect the data (sampling techniques):

  • Non-probability sampling: Uses judgment, voluntary, or convenience samples.
  • Probability sampling: Employs random, systematic, stratified, or cluster sampling.

Data Classification and Summarisation

• 4. Classify and summarise the data:
  • Categorize data as qualitative (nominal or ordinal) or quantitative (discrete or continuous).
  • Classify data based on measurement levels (nominal, ordinal, interval, or ratio).
  • Summarize data graphically (tables, histograms, frequency polygons, ogives, Pareto charts, time series graphs, pie charts, stem-and-leaf plots, box plots).
  • Summarize data using descriptive statistics (measures of central tendency, variation, and position).

Data Analysis and Presentation

• 5. Present and analyse the data:

  • Use descriptive statistics to analyze data properties and distribution shape. This is done by using graphical summaries and descriptive summaries.
  • Employ inferential statistics (confidence intervals, hypothesis testing, ANOVA, correlation, regression analysis).

• 6. Make the decision and conclusion:

  • Based on analysis, suggest the best decisions, options, solutions, and conclusions for the study.

Data Types

• Qualitative (Categorical/Attributes):

  • Data representing categories or classifications.
  • Examples include: sex, color of hair/eyes, ethnic background, make of car.
  • Data are classified using codes or numbers.

• Quantitative (Numerical):

  • Data that can be measured or counted.

  • Includes both discrete and continuous data.

  • Examples include: number of students, number of correct answers on a quiz, weights of sumo wrestlers.

  • Can be ordered or ranked (ratio/interval)

  • Discrete Data: Data that can only take on certain, separate values (can be counted). Example: number of students.

  • Continuous Data: Data that can take on any value within a given range. Example: weight, height.

• Nominal data:

  • Values represent categories or groups.
  • The values cannot be ranked.
  • Examples include: gender, race, colors.

• Ordinal Data:

  • Values represent categories with a meaningful order.
  • Examples include: feeling (dislike to like), color.

• Interval Data:

  • Values represent intervals with equal differences between them.
  • Zero point is arbitrary. Example: temperature.

• Ratio Data:

  • Values represent intervals with equal differences and a meaningful zero point.
  • For instance: income, age, height, etc.

Levels of Measurement

• The level of measurement describes how data are categorized and measured.
• The four levels are nominal, ordinal, interval, and ratio.
• Different statistical procedures are appropriate depending on the level.

Example Data Types:

• The type of calculator you use: Qualitative
• Number of pairs of shoes you own: Quantitative Discrete
• Weights of sumo wrestlers: Quantitative Continuous