Describing
g Data Types
yp
Data
D
t can b
be d
described
ib d in
i various
i
ways.
Three of which are:
Qualitative vs Quantitative
Discrete vs Continuous
Measurement Scales
Qualitative vs Quantitative
Q
Q
Qualitative Data - Sometimes referred to as
Attribute or Categorical Data.
Describes a non-numeric
non numeric characteristic.
characteristic
Examples Poor Fair
Poor,
Fair, Excellent
Red, Blue, Green
Short Medium,
Short,
Medium Tall
Male, Female
Group One
One, Group Two,
Two Group Three
Three, etc
Quantitative Data
Q
Quantitative Data is something that can be quantified,
that is to say
say, something that can can be
counted or measured.
Discrete Data represent countable items.
Continuous Data usually apply to measurements.
To quantify qualitative data - apply a number scale.
Example #1: Poor
Fair
Excellent
1
3
5
Example #2:
Female = 1
Male = 2
Scales of Measurement
Nominal - Name only (arbitrary)
Examples: Area Codes,
Codes ZIP Codes,
Codes Sports Jerseys
Ordinal - Order (but no defined interval)
Example: Horse race - 1st, 2nd, 3rd, etc
Interval - Equal Intervals
Examples: Thermometer, Meter Stick, Speedometer
Ratio - Absolute Zero
Examples: Celsius Scale has negative values.
Yardstick and weight scales have absolute zero
zero.
JMP Data and Modeling
g Types
yp
JMP uses two
t
somewhat
h t diff
differing
i categories.
t
i
Data Types
Numeric
Character
Row
Modeling Types
Continuous
Ordinal
Nominal
Note the possible confusion with our previous definitions.
JMP Data Types
yp
Numeric Data refers to q
quantitative data (numbers),
(
),
may be discrete or continuous values.
JMP treats all numeric data as continuous.
Character Data applies to alphanumeric text.
If classified as character data, then “numbers”
numbers are
treated as text characters.
Row Data applies to row characteristics
characteristics.
Affects appearance of graphical displays.
We will not be concerned with row data
data.
JMP Modeling
g Types
yp
Continuous refers to data measurements.
Must be numeric data type.
Used in arithmetic calculations.
Ordinal refers to discrete categorical data.
Mayy be either numeric or character data type.
yp
If numeric, the order is the numeric magnitude.
If character, the order is the sorting sequence.
Nominal refers to discrete categorical data.
May be either numeric or character data type.
Treated as discrete values without implicit order.
JMP Modeling
g (Analysis)
(
y ) Platforms
As if the foregoing was not confusing enough,
we also have to deal with Modeling Platforms.
The Modeling Platforms are used for statistical analyses
analyses.
p
g on the platform
p
model,, JMP uses different
Depending
algorithms and sets of assumptions to arrive at the final
calculated results.
Analysis
y Models
Response Models
(Y Variable)
Continuous Response
Nominal Response
Ordinal Response
Factors Models
(X Variable)
Continuous Factors
Nominal Factors
Ordinal Factors
Analysis
y Platforms
Distribution of Y (Univariate)
Fit Y by X
M t h d Pairs
Matched
P i
Fit Model
Non-Linear Fit
Neural Nets
Time Series
Correlation (Bivariate & Multivariate)
Survival & Reliability
Distribution of Y
Univariate (One Variable)
Distributions
Hi t
Histograms
Scatterplots
Normality Testing
One Sample Hypothesis Testing
Fit Y byy X
Bivariate (Two Variables)
Scatterplot with Regression Curve
O Way
One
W ANOVA
Contingency Table Analysis
Logistic Regression
For Fit Y byy X
The roles of X and Y (nominal & continuous)
determine the type of analysis
analysis.
X
Continuous
Nominal
Continuous
Y
Nominal
Bivariate
Scatter Plot
Regression Line
t -Tests
Means
One Way ANOVA
One-Way
Line Fitting
Comparison Tests
Non-Parametric Tests
P
Powers
Testing
T ti
LSN & LSV
Logistic Regression
Contingency Table
Cross Tabs
Matched Pairs
Paired t -test
test
Fit Model
General Linear Models
Multiple Regression
T
Two
and
d Three
Th
Way
W ANOVA’s
ANOVA’
Analysis of Covariance
Fixed and Random Effects
Nested and Repeated Measures
Non-Linear Fit
Requires user generated predictor equation
equation,
using iterative procedures.
Neural Nets
Implements and analyzes standard types of
neural networks.
Times Series
Analyzes univariate time series taken over
equally spaced time periods.
Plots autocorrelations
Fits ARIMA and Seasonal (Cyclic) ARIMA’s
Incorporates smoothing models
Correlations
Bivariate and Multivariate
Scatterplot Matrices
M lti i t Outliers
Multivariate
O tli
Principle Components
Survival & Reliabilityy
Models time until an event.
Used in R li bilit Engineering
Reliability
E i
i
Survival Analysis