Recently Used
Common Methods
Survey Research
Data Visualization
Data Processing
Advanced Methods
Experimental / Medical Research
Comprehensive Evaluation
Econometric Research
Machine Learning
Meta Analysis
Text Analysis
Spatial Econometrics
Power Analysis
Quality Control
p Value Identifier
Batch Processing
0
Data Labels
Batch Processing
0
Hold Ctrl or Shift and click the headers to
select
|
Batch Processing
0
Hold Ctrl or Shift and click the headers to
select
Compute Variable
- Excel
- Sav (SPSS)
- Dta (Stata)
- Excel (CSV)
- Excel
- Sav (SPSS)
- Dta (Stata)
- Excel (CSV)
Batch Processing
0
Hold Ctrl or Shift and click the headers to
select
Settings
-
Judgment Standard
- =
- <
- >
- ± Standard Deviation
-
Outlier Handling
-
-
Batch Processing
0
Hold Ctrl or Shift and click the headers to
select
Settings
-
Judgment Standard
- > %
- > %
-
Invalid Sample
-
-
Select the number of factors and corresponding levels, then 'start'".
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
Multi-expert
Geometric Mean Matrix Calculation
Select the order of
the judgment matrix white cells, and click
"Start".
Multi-expert
Geometric Mean Matrix Calculation
Suitable for t test with summary data (mean, standard deviation, and sample size).
- Group 1Group 2
- Mean
- Standard Deviation
- Sample Size
- Mean Difference
- Confidence Level
- Hypothesis Test
- Group 1Group 2
- Mean
- Standard Deviation
- Sample Size
- Mean Difference
- Confidence Level
- Hypothesis Test
Suitable for z test with summary data (mean, standard deviation, and sample size) for large sample (N > 30).
- Group 1Group 2
- Mean
- Standard Deviation
- Sample Size
- Mean Difference
- Confidence Level
- Hypothesis Test
- Group 1Group 2
- Mean
- Standard Deviation
- Sample Size
- Mean Difference
- Confidence Level
- Hypothesis Test
Proportion z test is applicable for large sample data (N>30).
- Group 1Group 2
- Event
- Total
- Proportion Difference
- Confidence Level
- Hypothesis Test
- Group 1Group 2
- Events
- Total
- Proportion Difference
- Confidence Level
- Hypothesis Test
- Positive (Bad)Negative (Good)
- Exposed Group
- Control Group
- Confidence Level
- Independent Variable (X) Dependent Variable (Y)
- Example Below
-
- The relationships are 5 pairs as follows:
- - A affects B- B affects D- C affects D
- - A affects D- C affects B
Note: If you need to customize function formulas, you can use the Non-linear Regression (Custom Formula) method in the [Quality Control] module.
- Dependent Variable (Y)
- Independent Variable (X)
- Independent variable (X2)
- Independent variable (X3)
Set Parameter (Optional)
| Parameter | Initial value |
Lower limit (Usually not set) |
Upper limit (Usually not set) |
|---|
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
Chi-square tests can be used to assess differences between two categorical variables, X and Y. When adjusting for confounding factors such as gender, a stratified chi-square analysis can be employed. SPSSAU supports data structured as 2 × 2 × K, where X and Y are binary categories and K represents the stratum.
- Group(X)
- Outcome(Y)
- Factor (Stratum)
- Weight
Bubble charts display the relationship between X and Y, with bubble size representing Z. To show the 'label' for each point, simply add the corresponding 'Label'.
- X
- Y
- Z (Bubble size, optional)
- Bubble category (Optional)
- Label (Optional)
Please edit the 'Initial probability' and 'State transition matrix', and you can paste (Ctrl+V) or modify the data.
| State | State 1 | State 2 | State 3 |
| Probability |
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
The data format is: 1 row represents the score of 1 expert, 1 column represents 1 indicator.
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
Please input or paste the complementarity matrix. The main diagonal should be 0.5, and the sum of each pair of symmetric elements must equal 1.
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
Tip: BO and OW should be placed separately. If multiple experts are involved, input multiple rows.
Input the Best-to-other (BO) data. If multiple experts are involved, use multiple rows.
Input the Others-to-worst (OW) . If multiple experts are involved, use multiple rows.
Limited to four values: 1/2/3/4, where higher scores mean higher effectiveness, usually 3 or 4 points.
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
-
Calculation Item
- Optional: Year
- Group (Optional)
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
Edit the data, then start.
Select the predictions from both the old and new models, along with the gold standard.
-
Prediction (Old model)
-
Prediction (New model)
- Gold Standard
-
Jump Threshold
-
Model Settings
- Regression Model
- Y1 (Survival Time)
- Y2 (Survival Status)
- Dependent Variable Y
- X (Quantitative, Optional)
-
X (Categorical, Optional)
-
Nomogram Settings
-
Prediction Time 1
-
Prediction Time 2
-
Prediction Time 3
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
-
Theil Index
- Similar to GDP (Y)
- Similar to Population (N)
- Similar to GDP Per Capita
- Year (Optional)
- Group 1 (e.g., Region) (Optional)
- Group 2 (e.g., Province) (Optional)
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
Please enter latitude and longitude
After pasting (Ctrl+V) or modifying the data, click 'Start' to continue.
Upload .gal or .gwl format
- 【1】The SPSSAU project (). SPSSAU. (Version
.0) [Online Application
Software]. Retrieved from https://spssau.net.
【2】PySAL Developers. (2018). PySAL: Python Spatial Analysis Library (23.7). GeoDa Center for Geospatial Analysis and Computation.
Select Purpose
Please select
Compare the
difference between the mean and one test value
Parameters
Input Data
Input Data
Mean of Group 2
Standard Deviation of Group 2
Select Purpose
Please select
Study the mean
differences of one factor across different groups
Parameters
Input Data
Number of Levels for Factor B
Number of Levels for Factor C
Select Purpose
Please select
Compare rate with
population rate
Parameters
Input Data
Input Data
Select Purpose
Please select
Compare the
correlation coefficient with the expected value
Parameters
Input Data
Select Purpose
Please select
Power analysis for
R-squared or R-squared change in hierarchical regression
Parameters
Input Data
Select Purpose
Please select
Power analysis for
differences between coefficients in binary logistic regression
Parameters
Input Data
Select Distribution Map
-
The chart above displays the data distribution characteristics.
1. Visual Area: The red area represents the visual area corresponding to the p Value;
2. Specific Count: For Binomial or Poisson distribution, the red dashed line represents the p Value corresponding to a specific count;
3. Parameter Updates: After modifying relevant parameters, the statistics will update accordingly;
4. Standardized Values: For the Normal distribution chart, it provides calculation of standardized z Value and p Value.
-
【1】The SPSSAU project (). SPSSAU. (Version
.0) [Online Application Software].
Retrieved from
https://www.spssau.com.
【2】R.R.约翰逊,K.库比.基础统计学[M].科学出版社,2003.
Data Information
After pasting (Ctrl+V) or modifying data, set the model parameters and click "Start" to analyze.
Model Parameter Design
Experimental Data Info
Response Variable (Data)
Number of Trials
Parameter Settings
Model Settings
Others
Insufficient valid data (? rows), analysis cannot proceed. Max 20 factors allowed. Invalidity may be caused by data transformation.
Variable Selection
Model Formula Input
- Variable name format: e.g., x1, x2
- Parameter name format: e.g., parm1, parm2
- Supported math functions: abs, sqrt, log, ln, exp, sin, cos, tan, etc.
- Supported operators: +, -, *, /, ^
- Usage of mod function: mod(a, b)
| Parameter | Initial Value | Lower Bound [Usually none] | Upper Bound [Usually none] |
|---|
Test Group Data
Control Group Data
Sample Data
Factorial Design
Response Surface Design (RSM)
Randomized Design
Features: Only 2 levels per factor; allows full examination of all main effects and interactions; number of runs increases exponentially with factors.
Note: Large experimental load with many factors; recommended only for a small number of factors.
| Factor Name | Levels | Level Values (High/Low settings) |
|---|
Features: Every combination of levels for all factors is tested; number of runs increases rapidly with more factors/levels.
Note: High experimental load; recommended only when factor count is low.
| Factor Name | Levels | Level Values (High/Low settings) |
|---|
Features: Significantly reduces the number of runs by testing a fraction of combinations; quickly identifies major factors.
Note: Cannot examine all high-order interactions; best for the preliminary screening phase.
Features: Significantly reduces the number of runs, ideal for rapidly screening a large number of factors.
Note: Interaction effects cannot be analyzed; only main effects can be screened. Suitable for the preliminary screening phase.
| Factor Name | Low LevelHigh Level |
|---|
Features: Experimental points are evenly distributed with fewer runs; ideal for building quadratic regression models.
Note: Does not include all extreme combinations; cannot be used for optimization under extreme conditions.
| Factor Name | Low LevelHigh Level |
|---|
Features: Includes center points and axial (star) points; examines extreme and intermediate levels; ideal for finding optimal conditions.
Note: Involves a larger number of experimental points; experimental resources should be planned accordingly.
| Factor Name | Low LevelHigh Level |
|---|
Features: Effectively balances the experimental order and external interference, reducing systematic errors.
Note: Each level can only appear once; suitable for scenarios where the number of row and column factors are equal.
| Factor Name | Low LevelHigh Level |
|---|
Please select the number of factors and trials
Please copy your 3-column MSA data (must be in the order of: Measurement, Part,
Appraiser)
from Excel or CSV, then paste it into the table below.
Paste (Ctrl+V) or modify data, set model parameters, and click "Start" to analyze.
Parameter Settings
Paste (Ctrl+V) or modify data, set model parameters, and click "Start" to analyze.
Parameter Settings
Lower Specification Limit(LSL)
Upper Specification Limit(USL)
Target Value(Target)
Paste (Ctrl+V) your data (or edit), then click "Start" to proceed.
Paste (Ctrl+V) your data, set the parameters, then click "Start".
Parameter Settings
Forest Plot Left Columns
Forest Plot Right Columns
Effect Size
Lower Limit
Upper Limit
X-axis Title
X-axis Min
X-axis Max
Title Edit
Delete