M

Types of Data - Module One Lesson Two

Biology: Classification of Animals (Taxonomy)

  • In Biology, we learn to classify or group animals by kingdom, phylum, class, orders, families, genera, and species.
  • Example taxonomy:
    • Kingdom: Animalia
    • Phylum: Chordata
    • Class: Mammalia
    • Order: Cetacea
    • Family: Delphinidae
    • Genera: Tursuiops
    • Species: T. Turncatus

Botany: Plant Classification (By Characteristics)

  • The slide shows a diagram about plants based on characteristics and seed production.
  • Key ideas:
    • DON’T MAKE SEEDS
    • PLANTS: Has no true roots, stems, or leaves and leaves (structure) – this line reflects a diagrammatic split
    • No Flowers (gymnosperms)
    • MAKES SEEDS; Flowers (angiosperms)
    • Examples listed: FERNS, CONIFERS, SUNFLOWER
    • ALGAE; MOSSES (categories shown in the diagram)

Classifying Data: Overview

  • We also classify data by its characteristics.
  • Knowing the type of data you have in a statistical research study is important since it allows you to determine what statistical analyses can be used for the study.
  • There are two methods for classify data:
    • Type classification
    • Level of Measurement classification
  • RECALL from Lesson One: Data is the set of actual responses or values you get when asking about a particular variable.

Classifying Data by TYPE

Qualitative Data

  • Involves labels or descriptions of traits using words or phrases.
  • Could be numbers, but not typically used in calculations.
  • Also called “categorical” data.
  • “Quality.”
  • Examples:
    • Eye Color
    • ID numbers (GHC ID, SS#, license plate)
    • Gender
    • Ethnicity
    • Political Affiliation
    • Hometown
    • Yes/No or Agree/Disagree

Quantitative Data

  • Counts or measurements.
  • Numbers with which calculations can be performed.
  • “Quantity.”
  • Examples:
    • Height
    • Weight
    • Age
    • Pulse Rate
    • Amount of rain
    • Exam scores
    • Temperature

Quantitative Data: Discrete vs Continuous

Discrete Data

  • Result of counting.
  • Involves whole units, no fractions or decimals.
  • “Number of …”
  • Examples:
    • Number of children
    • Number of books on a shelf
    • Number of credit cards
    • Number of eggs a hen lays
    • Number of calls received in a day

Continuous Data

  • Result of measuring.
  • Could involve fractions and/or decimals.
  • Can assume an infinite number of values between any two specific numbers (continuum).
  • Examples:
    • Height
    • Weight
    • Temperature
    • Distance traveled

Data Classification Diagram (Summary)

  • Data → Quantitative / Qualitative
  • Discrete / Continuous (under Quantitative)

Data Classification by LEVEL OF MEASUREMENT

  • Four levels of measurement:
    • Nominal
    • Ordinal
    • Interval
    • Ratio
  • The higher the level, the more mathematical calculations and statistical analyses options are available.

Nominal Data

  • Involves Qualitative Data only.
  • Classifies data into mutually exclusive (nonoverlapping) exhaustive groups.
  • Has no sense of order or ranking.
  • Cannot be used in mathematical calculations (it’s words!).
  • Examples:
    • True/False
    • Political Affiliation
    • Zip Codes

Ordinal Data

  • Involves Qualitative Data only.
  • Classifies data into mutually exclusive exhaustive groups with RANKS or a sense of order.
  • Exact differences do not exist between ranks (ranks are subjective or open to interpretation by researcher).
  • Cannot be used in mathematical calculations (no add/subtract).
  • Examples:
    • Letter grades (A, B, C, D, F)
    • Survey responses (Above average, average, below average, poor)
    • Judging contest (1st, 2nd, 3rd)

Interval Data

  • Involves Quantitative data.
  • Has ranks or sense of order; the exact differences between values exist and are meaningful; ranks are objective.
  • Can be added or subtracted.
  • Does not have a TRUE zero; zero is a placeholder and does not mean “absence of something.”
  • Examples:
    • Temperature (0° does not mean no heat): 0^
      igtharrow 0^ ext{C} (illustrative goal: 0 does not imply absence of heat)
    • Calendar dates
    • IQ scores (0 does not mean no intelligence or no brain)

Ratio Data

  • Involves Quantitative data.
  • Has ranks or sense of order; the exact differences between values exist and are meaningful; ranks are objective.
  • Can be added, subtracted, multiplied, and divided.
  • Has a TRUE zero; zero implies “absence of something” or nothing.
  • Examples:
    • Height
    • Number of phone calls in a day
    • Salary
    • Exam score

Quick Reference: Levels and Types (Diagramatic Overview)

  • ORDINAL | INTERVAL | RATIO | NOMINAL
  • QUALITATIVE | QUANTITATIVE

Examples (Practice): EXAMPLES

Classifying Variables: Practice Problems

  • Number of books students carry in their backpacks – Quantitative Discrete – Ratio
  • Weights of the backpacks with books in them – Quantitative Continuous – Ratio
  • Colors of backpacks students carry – Qualitative – Neither discrete nor continuous – Nominal

Additional Practice: More Classification

  • Prices of your favorite pair of jeans – Quantitative discrete – Ratio
  • Sizes of T-shirts – Qualitative – Neither discrete nor continuous – Ordinal
  • Number of t-shirts you own – Quantitative discrete – Ratio
  • Bank account PIN numbers – Qualitative – Neither discrete nor continuous – Nominal
  • Jersey numbers on baseball players – Qualitative – Neither discrete nor continuous – Nominal
  • Temperature at the local baseball game – Quantitative continuous – Interval