PyProcessMacro 2.0.0__tar.gz → 2.1.0__tar.gz

{pyprocessmacro-2.0.0 → pyprocessmacro-2.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyProcessMacro
-Version: 2.0.0
+Version: 2.1.0
 Summary: A Python library for moderation, mediation and conditional process analysis. Based on Andrew F. Hayes' Process Macro.
 Author-email: Quentin André <quentin.andre@insead.edu>
 License-Expression: MIT
@@ -27,6 +27,8 @@ Requires-Dist: pandas>=2.0
 Requires-Dist: scipy>=1.10
 Requires-Dist: matplotlib>=3.7
 Requires-Dist: seaborn>=0.13
+Provides-Extra: statsmodels
+Requires-Dist: statsmodels>=0.14; extra == "statsmodels"
 Provides-Extra: test
 Requires-Dist: pytest>=8; extra == "test"
 Requires-Dist: statsmodels>=0.14; extra == "test"
@@ -62,8 +64,9 @@ softwaress. PyProcessMacro is released under a MIT license.
 # Features
 
 In the current version, PyProcessMacro replicates the following features from the original Process Macro v2.16:
-  * All models (1 to 76), with the exception of Model 6 (serial mediation) are supported, and have been numerically
-  tested for accuracy against the output of the original Process macro (see the `test_models_accuracy.py`)
+  * All models (1 to 76) are supported. Models 1 to 5 and 7 to 76 are tested for accuracy against the output of the
+  original Process macro (see `tests/test_models_accuracy.py`); Model 6 (serial mediation, added in 2.1) is tested
+  against statsmodels-based reference computations.
   * Estimation of binary/continuous outcome variables. The binary outcomes are estimated in Logit using the 
   Newton-Raphson convergence algorithm, the continuous variables are estimated using OLS.
   * All statistics reported by Process: 
@@ -92,7 +95,6 @@ In the current version, the following features have not yet been ported to PyPro
   * Support for categorical independent variables.
   * Generation of individual fixed effects for repeated measures.
   * R² improvement from moderators in moderation models (1, 2, 3).
-  * Estimation of serial mediation (Model 6)
   * Some options (`normal`, `varorder`, ...). PyProcessMacro will issue a warning to tell you if an option you are 
   trying to use is not implemented.
 
@@ -233,6 +235,8 @@ As you can see, the syntax for PyProcessMacro is (almost) identical to that of P
 
 Once the object is initialized, you can call its `summary()` method to display the estimation results
 
+The standardized result tables (`tidy()`, `glance()`, `augment()`) are described in section 6.
+
 You might have noticed that there is no argument `varlist` in PyProcessMacro. This is because the list of variables 
 is automatically inferred from the variable names given to x, y, m.
 
@@ -319,6 +323,37 @@ By default, the standard errors of the OLS outcome models use the standard (homo
 p = Process(data=df, model=4, x="Effort", y="Success", m=["MediationSkills"], cov_type="HC3")
 ````
 
+### G. Serial mediation (Model 6)
+
+In Model 6 the mediators form a chain: each mediator depends on X and on the mediators before it, and Y depends
+on X and on every mediator. Pass two to four mediators in causal order. PyProcessMacro reports the specific
+indirect effect through every ordered subset of mediators (three paths for two mediators, seven for three,
+fifteen for four), labelled by the path, plus the total and the pairwise contrasts when `total=True` and
+`contrast=True`.
+
+````python
+p = Process(data=df, model=6, x="Effort", y="Success", m=["Attention", "MediationSkills"], total=True)
+p.summary()
+````
+
+Model 6 has no moderators, so the spotlight, floodlight and plotting methods do not apply to it. Its estimates are
+checked against products of statsmodels coefficients and against an independent resampler; no PROCESS output for
+Model 6 is part of the test fixtures yet, so a comparison file generated with PROCESS 2.16 would be a welcome
+contribution.
+
+### H. Effect sizes for the indirect effect
+
+With `effsize=True`, PyProcessMacro also reports the partially standardized indirect effect (the indirect effect
+divided by the standard deviation of Y) and the completely standardized indirect effect (further multiplied by the
+standard deviation of X), each with a bootstrap confidence interval computed by standardizing within every resample,
+as PROCESS does. The option applies to unmoderated indirect paths with a continuous outcome, that is Models 4 and 6
+with `logit=False`.
+
+````python
+p = Process(data=df, model=4, x="Effort", y="Success", m=["MediationSkills"], effsize=True)
+p.indirect_model.effect_size_summary()
+````
+
 ## 2. Accessing the estimation results
 
 After the `Process` object is initialized, you are not limited to printing the summary. PyProcessMacro implements the
@@ -416,6 +451,28 @@ Note that the methods are called from the `indirect_model` object! If you call `
 error.
 
 
+### E. Diagnostics and custom tests with statsmodels
+
+Each outcome model can be handed to [statsmodels](https://www.statsmodels.org), which refits the same design
+matrix with the same covariance estimator and returns the statsmodels results object. From there you get
+`summary()`, custom contrasts with `t_test()` and `wald_test()`, heteroskedasticity and influence diagnostics,
+variance inflation factors, prediction intervals, and the table formatters that accept statsmodels results.
+statsmodels is optional: install it with `pip install pyprocessmacro[statsmodels]`.
+
+````python
+p = Process(data=df, model=7, x="Effort", y="Success", w="Motivation", m=["MediationSkills"], suppr_init=True)
+
+fit = p.outcome_models["Success"].to_statsmodels()   # a statsmodels RegressionResults
+print(fit.summary())
+fit.t_test("Effort + MediationSkills = 0")
+
+fits = p.to_statsmodels()                              # every outcome model, keyed by outcome name
+````
+
+For a different question, statsmodels also ships `statsmodels.stats.mediation.Mediation`, Imai-style causal
+mediation with a sensitivity analysis; it estimates a different quantity and is a useful cross-check rather than
+a replacement for the PROCESS approach.
+
 ## 3. Spotlight and Floodlight Analysis 
 
 ### A. Compute direct/indirect effects for specific values (spotlight analysis)
@@ -646,6 +703,32 @@ g = p.plot_conditional_indirect_effects(med_name="MediationSkills", x="Motivatio
 ````
 ![PlotCustomKws](images/Ex12.png)
 
+## 6. Standardized results: tidy(), glance() and augment()
+
+Every table PyProcessMacro prints is also available in a standardized form, modelled on R's broom package:
+
+* `tidy()` returns one long DataFrame with one row per estimate and fixed column names: `component`
+  (`outcome`, `direct`, `indirect`, `total`, `contrast`, or `index_mm`, `index_pmm`, `index_mmm`, `index_cmm`),
+  `outcome`, `term`, `moderator`, one column per moderator of the model holding the spotlight value the row is
+  evaluated at, then `estimate`, `std_error`, `statistic`, `p_value`, `conf_low`, `conf_high`, `method`,
+  `conf_level` and `n_boot`. Pass `component=` to keep one kind of row.
+* `glance()` returns one row of fit statistics per outcome model, including the log-likelihood, AIC and BIC.
+* `augment()` returns the analysis data with `.fitted_<outcome>` and `.resid_<outcome>` columns per outcome model.
+
+````python
+p = Process(data=df, model=7, x="Effort", y="Success", w="Motivation", m=["MediationSkills"], suppr_init=True)
+
+estimates = p.tidy()                        # every estimate
+indirect = p.tidy("indirect")               # only the conditional indirect effects
+fit = p.glance()                            # R², AIC, BIC, ... per outcome model
+residuals = p.augment(outcome="Success")    # fitted values and residuals of the outcome model
+
+estimates.to_csv("process_model7.csv", index=False)
+````
+
+`summary()` returns the text it prints, so `report = p.summary()` keeps a copy, and a `Process` object displayed at
+the end of a notebook cell shows its tables as HTML.
+
 # 7. About
 PyProcessMacro was developed by Quentin André during his PhD in Marketing at INSEAD Business School, France. 
 

{pyprocessmacro-2.0.0 → pyprocessmacro-2.1.0}/PyProcessMacro.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyProcessMacro
-Version: 2.0.0
+Version: 2.1.0
 Summary: A Python library for moderation, mediation and conditional process analysis. Based on Andrew F. Hayes' Process Macro.
 Author-email: Quentin André <quentin.andre@insead.edu>
 License-Expression: MIT
@@ -27,6 +27,8 @@ Requires-Dist: pandas>=2.0
 Requires-Dist: scipy>=1.10
 Requires-Dist: matplotlib>=3.7
 Requires-Dist: seaborn>=0.13
+Provides-Extra: statsmodels
+Requires-Dist: statsmodels>=0.14; extra == "statsmodels"
 Provides-Extra: test
 Requires-Dist: pytest>=8; extra == "test"
 Requires-Dist: statsmodels>=0.14; extra == "test"
@@ -62,8 +64,9 @@ softwaress. PyProcessMacro is released under a MIT license.
 # Features
 
 In the current version, PyProcessMacro replicates the following features from the original Process Macro v2.16:
-  * All models (1 to 76), with the exception of Model 6 (serial mediation) are supported, and have been numerically
-  tested for accuracy against the output of the original Process macro (see the `test_models_accuracy.py`)
+  * All models (1 to 76) are supported. Models 1 to 5 and 7 to 76 are tested for accuracy against the output of the
+  original Process macro (see `tests/test_models_accuracy.py`); Model 6 (serial mediation, added in 2.1) is tested
+  against statsmodels-based reference computations.
   * Estimation of binary/continuous outcome variables. The binary outcomes are estimated in Logit using the 
   Newton-Raphson convergence algorithm, the continuous variables are estimated using OLS.
   * All statistics reported by Process: 
@@ -92,7 +95,6 @@ In the current version, the following features have not yet been ported to PyPro
   * Support for categorical independent variables.
   * Generation of individual fixed effects for repeated measures.
   * R² improvement from moderators in moderation models (1, 2, 3).
-  * Estimation of serial mediation (Model 6)
   * Some options (`normal`, `varorder`, ...). PyProcessMacro will issue a warning to tell you if an option you are 
   trying to use is not implemented.
 
@@ -233,6 +235,8 @@ As you can see, the syntax for PyProcessMacro is (almost) identical to that of P
 
 Once the object is initialized, you can call its `summary()` method to display the estimation results
 
+The standardized result tables (`tidy()`, `glance()`, `augment()`) are described in section 6.
+
 You might have noticed that there is no argument `varlist` in PyProcessMacro. This is because the list of variables 
 is automatically inferred from the variable names given to x, y, m.
 
@@ -319,6 +323,37 @@ By default, the standard errors of the OLS outcome models use the standard (homo
 p = Process(data=df, model=4, x="Effort", y="Success", m=["MediationSkills"], cov_type="HC3")
 ````
 
+### G. Serial mediation (Model 6)
+
+In Model 6 the mediators form a chain: each mediator depends on X and on the mediators before it, and Y depends
+on X and on every mediator. Pass two to four mediators in causal order. PyProcessMacro reports the specific
+indirect effect through every ordered subset of mediators (three paths for two mediators, seven for three,
+fifteen for four), labelled by the path, plus the total and the pairwise contrasts when `total=True` and
+`contrast=True`.
+
+````python
+p = Process(data=df, model=6, x="Effort", y="Success", m=["Attention", "MediationSkills"], total=True)
+p.summary()
+````
+
+Model 6 has no moderators, so the spotlight, floodlight and plotting methods do not apply to it. Its estimates are
+checked against products of statsmodels coefficients and against an independent resampler; no PROCESS output for
+Model 6 is part of the test fixtures yet, so a comparison file generated with PROCESS 2.16 would be a welcome
+contribution.
+
+### H. Effect sizes for the indirect effect
+
+With `effsize=True`, PyProcessMacro also reports the partially standardized indirect effect (the indirect effect
+divided by the standard deviation of Y) and the completely standardized indirect effect (further multiplied by the
+standard deviation of X), each with a bootstrap confidence interval computed by standardizing within every resample,
+as PROCESS does. The option applies to unmoderated indirect paths with a continuous outcome, that is Models 4 and 6
+with `logit=False`.
+
+````python
+p = Process(data=df, model=4, x="Effort", y="Success", m=["MediationSkills"], effsize=True)
+p.indirect_model.effect_size_summary()
+````
+
 ## 2. Accessing the estimation results
 
 After the `Process` object is initialized, you are not limited to printing the summary. PyProcessMacro implements the
@@ -416,6 +451,28 @@ Note that the methods are called from the `indirect_model` object! If you call `
 error.
 
 
+### E. Diagnostics and custom tests with statsmodels
+
+Each outcome model can be handed to [statsmodels](https://www.statsmodels.org), which refits the same design
+matrix with the same covariance estimator and returns the statsmodels results object. From there you get
+`summary()`, custom contrasts with `t_test()` and `wald_test()`, heteroskedasticity and influence diagnostics,
+variance inflation factors, prediction intervals, and the table formatters that accept statsmodels results.
+statsmodels is optional: install it with `pip install pyprocessmacro[statsmodels]`.
+
+````python
+p = Process(data=df, model=7, x="Effort", y="Success", w="Motivation", m=["MediationSkills"], suppr_init=True)
+
+fit = p.outcome_models["Success"].to_statsmodels()   # a statsmodels RegressionResults
+print(fit.summary())
+fit.t_test("Effort + MediationSkills = 0")
+
+fits = p.to_statsmodels()                              # every outcome model, keyed by outcome name
+````
+
+For a different question, statsmodels also ships `statsmodels.stats.mediation.Mediation`, Imai-style causal
+mediation with a sensitivity analysis; it estimates a different quantity and is a useful cross-check rather than
+a replacement for the PROCESS approach.
+
 ## 3. Spotlight and Floodlight Analysis 
 
 ### A. Compute direct/indirect effects for specific values (spotlight analysis)
@@ -646,6 +703,32 @@ g = p.plot_conditional_indirect_effects(med_name="MediationSkills", x="Motivatio
 ````
 ![PlotCustomKws](images/Ex12.png)
 
+## 6. Standardized results: tidy(), glance() and augment()
+
+Every table PyProcessMacro prints is also available in a standardized form, modelled on R's broom package:
+
+* `tidy()` returns one long DataFrame with one row per estimate and fixed column names: `component`
+  (`outcome`, `direct`, `indirect`, `total`, `contrast`, or `index_mm`, `index_pmm`, `index_mmm`, `index_cmm`),
+  `outcome`, `term`, `moderator`, one column per moderator of the model holding the spotlight value the row is
+  evaluated at, then `estimate`, `std_error`, `statistic`, `p_value`, `conf_low`, `conf_high`, `method`,
+  `conf_level` and `n_boot`. Pass `component=` to keep one kind of row.
+* `glance()` returns one row of fit statistics per outcome model, including the log-likelihood, AIC and BIC.
+* `augment()` returns the analysis data with `.fitted_<outcome>` and `.resid_<outcome>` columns per outcome model.
+
+````python
+p = Process(data=df, model=7, x="Effort", y="Success", w="Motivation", m=["MediationSkills"], suppr_init=True)
+
+estimates = p.tidy()                        # every estimate
+indirect = p.tidy("indirect")               # only the conditional indirect effects
+fit = p.glance()                            # R², AIC, BIC, ... per outcome model
+residuals = p.augment(outcome="Success")    # fitted values and residuals of the outcome model
+
+estimates.to_csv("process_model7.csv", index=False)
+````
+
+`summary()` returns the text it prints, so `report = p.summary()` keeps a copy, and a `Process` object displayed at
+the end of a notebook cell shows its tables as HTML.
+
 # 7. About
 PyProcessMacro was developed by Quentin André during his PhD in Marketing at INSEAD Business School, France. 
 

{pyprocessmacro-2.0.0 → pyprocessmacro-2.1.0}/PyProcessMacro.egg-info/SOURCES.txt

@@ -8,6 +8,10 @@ PyProcessMacro.egg-info/dependency_links.txt
 PyProcessMacro.egg-info/requires.txt
 PyProcessMacro.egg-info/top_level.txt
 pyprocessmacro/__init__.py
+pyprocessmacro/bootstrap.py
+pyprocessmacro/effsize.py
 pyprocessmacro/models.py
 pyprocessmacro/process.py
+pyprocessmacro/serial.py
+pyprocessmacro/tidy.py
 pyprocessmacro/utils.py

{pyprocessmacro-2.0.0 → pyprocessmacro-2.1.0}/PyProcessMacro.egg-info/requires.txt

@@ -4,6 +4,9 @@ scipy>=1.10
 matplotlib>=3.7
 seaborn>=0.13
 
+[statsmodels]
+statsmodels>=0.14
+
 [test]
 pytest>=8
 statsmodels>=0.14

{pyprocessmacro-2.0.0 → pyprocessmacro-2.1.0}/README.md

@@ -28,8 +28,9 @@ softwaress. PyProcessMacro is released under a MIT license.
 # Features
 
 In the current version, PyProcessMacro replicates the following features from the original Process Macro v2.16:
-  * All models (1 to 76), with the exception of Model 6 (serial mediation) are supported, and have been numerically
-  tested for accuracy against the output of the original Process macro (see the `test_models_accuracy.py`)
+  * All models (1 to 76) are supported. Models 1 to 5 and 7 to 76 are tested for accuracy against the output of the
+  original Process macro (see `tests/test_models_accuracy.py`); Model 6 (serial mediation, added in 2.1) is tested
+  against statsmodels-based reference computations.
   * Estimation of binary/continuous outcome variables. The binary outcomes are estimated in Logit using the 
   Newton-Raphson convergence algorithm, the continuous variables are estimated using OLS.
   * All statistics reported by Process: 
@@ -58,7 +59,6 @@ In the current version, the following features have not yet been ported to PyPro
   * Support for categorical independent variables.
   * Generation of individual fixed effects for repeated measures.
   * R² improvement from moderators in moderation models (1, 2, 3).
-  * Estimation of serial mediation (Model 6)
   * Some options (`normal`, `varorder`, ...). PyProcessMacro will issue a warning to tell you if an option you are 
   trying to use is not implemented.
 
@@ -199,6 +199,8 @@ As you can see, the syntax for PyProcessMacro is (almost) identical to that of P
 
 Once the object is initialized, you can call its `summary()` method to display the estimation results
 
+The standardized result tables (`tidy()`, `glance()`, `augment()`) are described in section 6.
+
 You might have noticed that there is no argument `varlist` in PyProcessMacro. This is because the list of variables 
 is automatically inferred from the variable names given to x, y, m.
 
@@ -285,6 +287,37 @@ By default, the standard errors of the OLS outcome models use the standard (homo
 p = Process(data=df, model=4, x="Effort", y="Success", m=["MediationSkills"], cov_type="HC3")
 ````
 
+### G. Serial mediation (Model 6)
+
+In Model 6 the mediators form a chain: each mediator depends on X and on the mediators before it, and Y depends
+on X and on every mediator. Pass two to four mediators in causal order. PyProcessMacro reports the specific
+indirect effect through every ordered subset of mediators (three paths for two mediators, seven for three,
+fifteen for four), labelled by the path, plus the total and the pairwise contrasts when `total=True` and
+`contrast=True`.
+
+````python
+p = Process(data=df, model=6, x="Effort", y="Success", m=["Attention", "MediationSkills"], total=True)
+p.summary()
+````
+
+Model 6 has no moderators, so the spotlight, floodlight and plotting methods do not apply to it. Its estimates are
+checked against products of statsmodels coefficients and against an independent resampler; no PROCESS output for
+Model 6 is part of the test fixtures yet, so a comparison file generated with PROCESS 2.16 would be a welcome
+contribution.
+
+### H. Effect sizes for the indirect effect
+
+With `effsize=True`, PyProcessMacro also reports the partially standardized indirect effect (the indirect effect
+divided by the standard deviation of Y) and the completely standardized indirect effect (further multiplied by the
+standard deviation of X), each with a bootstrap confidence interval computed by standardizing within every resample,
+as PROCESS does. The option applies to unmoderated indirect paths with a continuous outcome, that is Models 4 and 6
+with `logit=False`.
+
+````python
+p = Process(data=df, model=4, x="Effort", y="Success", m=["MediationSkills"], effsize=True)
+p.indirect_model.effect_size_summary()
+````
+
 ## 2. Accessing the estimation results
 
 After the `Process` object is initialized, you are not limited to printing the summary. PyProcessMacro implements the
@@ -382,6 +415,28 @@ Note that the methods are called from the `indirect_model` object! If you call `
 error.
 
 
+### E. Diagnostics and custom tests with statsmodels
+
+Each outcome model can be handed to [statsmodels](https://www.statsmodels.org), which refits the same design
+matrix with the same covariance estimator and returns the statsmodels results object. From there you get
+`summary()`, custom contrasts with `t_test()` and `wald_test()`, heteroskedasticity and influence diagnostics,
+variance inflation factors, prediction intervals, and the table formatters that accept statsmodels results.
+statsmodels is optional: install it with `pip install pyprocessmacro[statsmodels]`.
+
+````python
+p = Process(data=df, model=7, x="Effort", y="Success", w="Motivation", m=["MediationSkills"], suppr_init=True)
+
+fit = p.outcome_models["Success"].to_statsmodels()   # a statsmodels RegressionResults
+print(fit.summary())
+fit.t_test("Effort + MediationSkills = 0")
+
+fits = p.to_statsmodels()                              # every outcome model, keyed by outcome name
+````
+
+For a different question, statsmodels also ships `statsmodels.stats.mediation.Mediation`, Imai-style causal
+mediation with a sensitivity analysis; it estimates a different quantity and is a useful cross-check rather than
+a replacement for the PROCESS approach.
+
 ## 3. Spotlight and Floodlight Analysis 
 
 ### A. Compute direct/indirect effects for specific values (spotlight analysis)
@@ -612,6 +667,32 @@ g = p.plot_conditional_indirect_effects(med_name="MediationSkills", x="Motivatio
 ````
 ![PlotCustomKws](images/Ex12.png)
 
+## 6. Standardized results: tidy(), glance() and augment()
+
+Every table PyProcessMacro prints is also available in a standardized form, modelled on R's broom package:
+
+* `tidy()` returns one long DataFrame with one row per estimate and fixed column names: `component`
+  (`outcome`, `direct`, `indirect`, `total`, `contrast`, or `index_mm`, `index_pmm`, `index_mmm`, `index_cmm`),
+  `outcome`, `term`, `moderator`, one column per moderator of the model holding the spotlight value the row is
+  evaluated at, then `estimate`, `std_error`, `statistic`, `p_value`, `conf_low`, `conf_high`, `method`,
+  `conf_level` and `n_boot`. Pass `component=` to keep one kind of row.
+* `glance()` returns one row of fit statistics per outcome model, including the log-likelihood, AIC and BIC.
+* `augment()` returns the analysis data with `.fitted_<outcome>` and `.resid_<outcome>` columns per outcome model.
+
+````python
+p = Process(data=df, model=7, x="Effort", y="Success", w="Motivation", m=["MediationSkills"], suppr_init=True)
+
+estimates = p.tidy()                        # every estimate
+indirect = p.tidy("indirect")               # only the conditional indirect effects
+fit = p.glance()                            # R², AIC, BIC, ... per outcome model
+residuals = p.augment(outcome="Success")    # fitted values and residuals of the outcome model
+
+estimates.to_csv("process_model7.csv", index=False)
+````
+
+`summary()` returns the text it prints, so `report = p.summary()` keeps a copy, and a `Process` object displayed at
+the end of a notebook cell shows its tables as HTML.
+
 # 7. About
 PyProcessMacro was developed by Quentin André during his PhD in Marketing at INSEAD Business School, France. 
 

{pyprocessmacro-2.0.0 → pyprocessmacro-2.1.0}/pyprocessmacro/__init__.py

@@ -7,4 +7,4 @@ from .utils import ConvergenceError
 
 __all__ = ["Process", "ConvergenceError"]
 
-__version__ = "2.0.0"
+__version__ = "2.1.0"