Data Types and Measurement Scales

MIDAS automatically infers data types and measurement scales when loading data. Measurement scales directly affect the available graph types and statistical methods, so verify they are set correctly.

See Data Preparation and Import for instructions on loading data and changing types.

Measurement Scales

Measurement scales classify "what operations are meaningful for a given data". Based on Stevens' (1946) four levels of measurement.

Nominal Scale

Data representing categories with no meaningful order. Only equality ($=$, $\neq$) is meaningful.

Examples: Gender (male/female), colors (red/blue/green), country names

In MIDAS:

• Bar charts and other category-based summaries
• Cross tabulation (chi-square test)
• Group separation by Color/Fill in Graph Builder

Ordinal Scale

Categories with meaningful order, but no defined interval between values. Comparisons ($<$, $>$) are meaningful.

Examples: Satisfaction (low/medium/high), grade level (1st/2nd/3rd year), grades (A/B/C/D)

In MIDAS:

• All nominal operations, plus order-aware graph display
• Defining order in enum type makes graph axes respect the specified order

Interval Scale

Equally spaced numeric data where differences are meaningful, but ratios are not. The zero point is arbitrary.

Examples: Temperature (Celsius), year (AD)

• The difference between 20°C and 10°C is a meaningful 10°C
• However, 20°C is not "twice as warm" as 10°C

In MIDAS:

• Histograms, scatter plots, and other continuous value graphs
• Mean, standard deviation, correlation coefficients
• Hypothesis testing (t-test)

Ratio Scale

Equally spaced numeric data with a true zero point. Both differences and ratios are meaningful.

Examples: Height, weight, price, age

• The difference between 20kg and 10kg is a meaningful 10kg
• Furthermore, 20kg is "twice as heavy" as 10kg

In MIDAS:

• All interval scale operations
• Coefficient of variation (CV) and geometric mean calculation

Scales and Analysis Methods

Analysis Method	Required Scale	MIDAS Feature
Frequency counts	Nominal or above	Crosstab, Statistics
Median, quartiles	Ordinal or above	Statistics
Mean, standard deviation	Interval or above	Statistics
Correlation coefficient	Interval or above	Statistics (select 2 columns)
t-test	Interval or above	Two-Sample Test, Paired Test
Mann-Whitney U, Wilcoxon signed-rank	Ordinal or above	Two-Sample Test, Paired Test
Regression analysis	Interval or above	Linear Regression, GLM
Histogram	Interval or above	Graph Builder
Bar chart	Nominal, Ordinal	Graph Builder
Coefficient of variation, geometric mean	Ratio	Statistics (Comparison)

Auto-Inference from Data Types to Measurement Scales

MIDAS determines data types on import and automatically assigns measurement scales.

Data Type	Inferred Scale	Reason
boolean	Nominal	true/false are unordered categories
int64	Ratio	Integers typically have a natural zero point
float64	Ratio	Same as integers
date	Interval	Date differences are meaningful, but ratios typically are not
datetime	Interval	Same as dates
string	Nominal	Text is treated as categories
enum	Nominal	Can be changed to ordinal when order is defined

Auto-inference may not match the actual meaning of the data. For example, postal codes are loaded as numeric but are semantically nominal. Similarly, 5-point Likert scales should be treated as ordinal rather than ratio. Right-click the column in the Data Table and select Edit Scale to change the measurement scale.

References

• Stevens, S. S. (1946). On the theory of scales of measurement. Science, 103(2684), 677-680.

See also

• Data Preparation and Import - Data type list and type conversion
• Basic Statistics - Statistics displayed by measurement scale