Data types of measurement scales
18 likes•5,312 views
This document discusses different types of measurement in research. It outlines four levels of measurement: nominal, ordinal, interval, and ratio. Nominal measurement involves categories with no intrinsic ordering. Ordinal involves rank ordering but unknown distances between ranks. Interval has equal distances between points on the scale, but no true zero. Ratio has a true zero point and allows for absolute comparisons of magnitudes. The document provides examples for each level and discusses their appropriate uses in research design and statistical analysis. More sensitive levels of data allow for more powerful statistical tests but are not always feasible. Researchers should aim for the highest valid level of measurement possible.
Data types of measurement scales
- 1. Types of Measurement Dr Raju Indukoori Dr S S N Raju Indukoori 1
- 2. Direct measures Physiological Measures: Heart rate, Blood pressure, Breathing rate, Galvanic skin response, Eye movement, Magnetic resonance imaging, etc. Behavioral measures • in a naturalistic setting: Videotaping leave-taking behavior (how people say goodbye) at an airport. • in a laboratory setting: Videotaping superior-subordinate interactions in a simulated environment. Dr S S N Raju Indukoori
- 3. Indirect measures 1) Relying on observers’ estimates or perceptions with indirect questions – asking executives at advertising firms if they think their competitors use subliminal messages – asking subordinates, rather than managers, what managerial style they perceive their supervisors employ. 2) Unobtrusive measures: measures of accretion, erosion, etc. “garbology” research—studying discarded trash for clues about lifestyles, eating habits, consumer purchases, etc. Dr S S N Raju Indukoori 3
- 4. Miscellaneous measures • Archived data – example: court records of spouse abuse – example: number of emails sent to/from students to instructors • Retrospective data – example: family history of high BP – example: employee absenteeism or turn-over rates in an organization Dr S S N Raju Indukoori 4
- 5. Levels of Data Scaling 1. Nominal Scale 2. Ordinal Scale 3. Interval Scale 4. Ratio Scale nominal ordinal interval ratio Dr S S N Raju Indukoori 5
- 6. 1.Nominal data • It is crude form of data with limited scope for statistical analysis • It relies on categories, classifications, or groupings like students, South Indian, etc.. • Merely measures the presence or absence of something – gender: male or female – Pin Codes 530017, 530010…. – Marital status Dr S S N Raju Indukoori 6
- 7. 1.Nominal data • nominal categories aren’t hierarchical, one category isn’t “better” or “higher” than another. • assignment of numbers to the categories has no mathematical meaning. • nominal categories should be mutually exclusive and exhaustive. Dr S S N Raju Indukoori 7
- 8. Contd…. • nominal data is usually represented “descriptively” • graphic representations include tables, bar graphs, pie charts. • there are limited statistical tests that can be performed on nominal data • if nominal data can be converted to averages, advanced statistical analysis is possible Dr S S N Raju Indukoori
- 9. Contd…. Character •Classified as mutually exclusive and collectively exhaustive • No order, distance or natural origin •Even the presence of numbers doesn’t carry any value but just labels. Basic Empirical Operation Determination of Equality Numerical Operation Counting Descriptive Statistics •Frequency and percentage in each category •Mode Example •Gender: M/F •Serial Number: 1, 2, 3, 4 Dr S S N Raju Indukoori 9
- 10. 2.Ordinal data • It is more sensitive and reliable than nominal data, but still lacking in precision. • Exists in a rank order, hierarchy, or sequence like highest to lowest, best to worst, first to last. • It allows for comparisons along some dimension: Ex - Meenakshi is prettier than Radhika, Rajesh is taller than Ravish. • No assumption of “equidistance” of numbers. Ex: Promotions and increments • Researchers do sometimes treat ordinal data as if it were interval data • There are limited statistical tests available with ordinal data Dr S S N Raju Indukoori 10
- 11. 2. Contd. Most popular persons on social media 1st, 2nd, 3rd places finishes in IPL Top 10 movie box office hits of 2018 Best books of 2018 Top 10 Tourist destinations Top 10 Tourism Destinations in Vizag City 1. INS Kurusura Submarine Museum 2. TU 142 Air Craft Museum 3. Vuda City Central Park 4. Rishi Konda Beach 5. Rama Krishna Beach 6. Simhachalam Temple 7. Yarada Beach 8. Kailasagiri 9. Dolphin Nose 10. Vuda Park Dr S S N Raju Indukoori 11
- 12. 2. Contd…. Character: •Classified • Ordered • No distance or natural origin Basic Empirical Operation: Determination of greater or lesser value Numerical Operation: Rank Ordering Descriptive Statistics: Median, Range, Percentile Ranking Example: Quality of Room Service 1)Outstanding 2)Good 3)Not upto the mark. Dr S S N Raju Indukoori 12
- 13. 3. Interval data • Reepresents a more sensitive type of data or sophisticated form of measurement • Assumption of “equidistance” applies to data or numbers gathered – gradations, increments, or units of measure are uniform, constant • Examples: – Scale data: Likert scales, Semantic Differential scales – Stanford Binet I.Q. test – most standardized scales or diagnostic instruments yield numerical scores Dr S S N Raju Indukoori
- 14. 3. Contd…. • The scores can be compared to one another, but in relative, rather than absolute terms. example: If ICICI is rated a “4” on attractiveness, and SBI with “2,” it doesn’t mean ICICI SBI is twice as attractive as SBI • There is no true zero point (a complete absence of the phenomenon being measured) example: A person can’t have zero intelligence or zero self esteem • Scale data is usually aggregated or converted to averages • Amenable to advanced statistical analysis Dr S S N Raju Indukoori
- 15. 3. Contd.. Character •Classified • Ordered • Distance • Natural origin Basic Empirical Operation Determination of equality of intervals or differences Numerical Operation Arithmetic operations on intervals between numbers. Descriptive Statistics Mean, Standard Deviation, Variance Example Temperature in Degrees Celcius 1) 12- 20 2) 21-30 3) 31-40 4) 41-50 Dr S S N Raju Indukoori 15
- 16. 4.Ratio data It is the most sensitive, powerful type of data . The ratio measures contain the most precise information about each observation that is made Examples: • Weight and height as units of measure • Time as a unit of measure • Distance as a unit of measure (setting an odometer to zero before beginning a trip) Dr S S N Raju Indukoori 16
- 17. 4. Contd… • It is more prevalent in the natural sciences, less common in social science research • It includes a true zero point (complete absence of the phenomenon being measured) • It allows for absolute comparisons Example: If Rajesh can lift 200 lbs and Vijay can lift 100 lbs, Rajesh can lift twice as much as Vijay i.e 2:1 ratio Dr S S N Raju Indukoori
- 18. 4. Contd… Character •Classified • Ordered • Distance • Natural origin Basic Empirical Operation Determination of equality of ratios Numerical Operation Arithmetic operations on intervals between numbers. Descriptive Statistics Geometric Mean, Coefficient of Variation Example Age in Years Dr S S N Raju Indukoori 18
- 19. More examples of levels of data • Nominal Scale: number of males versus females who are HCOM majors • Ordinal Scale: “small,” “medium,” and “large” size drinks at a movie theater. • Interval Scale: scores on a “self-esteem” scale of Hispanic and Anglo managers • Ratio Scale: runners’ individual times in the L.A. marathon (e.g., 2:15, 2: 21, 2:33, etc.) Dr S S N Raju Indukoori 19
- 20. Application to experimental design For a dependent variable • Rely on nominal or ordinal measurement only if other forms of data are unavailable, impractical, etc. • Always employ the highest level of measurement available, e.g, interval or ratio, if possible • Try to find established, valid, reliable measures, rather than inventing your own “home-made” measures. Dr S S N Raju Indukoori 20