Switched all documentation to foot references

source/anova_documentation.rst

@@ -48,7 +48,7 @@ By default, this method will return the measures of :math:`R^2`, :math:`\text{Ad
 note that for the factor terms the reported :math:`\eta^2` and :math:`\omega^2` will be partial, i.e. :math:`\eta^2_p` and :math:`\omega^2_p` respectively.
 Additionally, :math:`R^2` and :math:`\eta^2` are the same but have different names due to coming from different frameworks
 which uses different terminology. Formulas for how to calculate these effect sizes
-comes from :cite:`grissomkim2012`.
+comes from :footcite:p:`grissomkim2012`.
 
 Eta-squared (:math:`\eta^2`) and :math:`R^2`
 """"""""""""""""""""""""""""""""""""""""""""
@@ -192,5 +192,7 @@ If it's of interest, one can also access the underlying regression table.
 
 References
 ==========
-.. bibliography:: refs.bib
+.. footbibliography:: refs.bib
+
+  :cited:
   :list: bullet

source/conf.py

@@ -48,6 +48,7 @@
     'sphinx.ext.mathjax',
     'sphinxcontrib.bibtex',
 ]
+
 bibtex_bibfiles = ['refs.bib']
 
 # Add any paths that contain templates here, relative to this directory.

source/corr_case_documentation.rst

@@ -24,8 +24,8 @@ Input
 
   * **dataframe** can either be a single Pandas Series or multiple Series/an
     entire DataFrame.
-  * **method** takes the values of "pearson" :cite:`scipy_pearsonr` (the default if nothing is passed),
-    "spearman" :cite:`scipy_spearmanr`, or "kendall" :cite:`scipy_kendalltau`.
+  * **method** takes the values of "pearson" :footcite:p:`scipy_pearsonr` (the default if nothing is passed),
+    "spearman" :footcite:p:`scipy_spearmanr`, or "kendall" :footcite:p:`scipy_kendalltau`.
 
 .. scipy.stats methods used in corr_case()
 .. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -120,6 +120,7 @@ srq   0.9775  0.0000
 
 References
 ----------
-.. bibliography:: refs.bib
+.. footbibliography:: refs.bib
+
    :cited:
    :list: bullet

source/corr_pair_documentation.rst

@@ -21,8 +21,8 @@ Input
 
 * **dataframe** can either be a single Pandas Series or multiple Series/an
   entire DataFrame.
-* **method** takes the values of "pearson" :cite:`scipy_pearsonr` (the default if nothing is passed),
-  "spearman" :cite:`scipy_spearmanr`, or "kendall" :cite:`scipy_kendalltau`.
+* **method** takes the values of "pearson" :footcite:p:`scipy_pearsonr` (the default if nothing is passed),
+  "spearman" :footcite:p:`scipy_spearmanr`, or "kendall" :footcite:p:`scipy_kendalltau`.
 
 ..  scipy.stats methods used in corr_case()
 .. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -178,6 +178,6 @@ Pearson r
 
 References
 ----------
-.. bibliography:: refs.bib
+.. footbibliography:: refs.bib
    :cited:
    :list: bullet

source/crosstab_documentation.rst

@@ -30,12 +30,12 @@ correction = None, cramer_correction = None, exact = False, expected_freqs= Fals
     will calculate the cell percentage based on the entire sample
   * **test**, can take "chi-square", "g-test", "mcnemar", or "fisher".
 
-      * If "chi-square", the chi-square (:math:`\chi^2`) test of independence :cite:`scipy_chi2` will
+      * If "chi-square", the chi-square (:math:`\chi^2`) test of independence :footcite:p:`scipy_chi2` will
         be calculated and returned in a second DataFrame.
-      * If "g-test", will conduct the G-test (likelihood-ratio :math:`\chi^2`) :cite:`scipy_chi2` and
+      * If "g-test", will conduct the G-test (likelihood-ratio :math:`\chi^2`) :footcite:p:`scipy_chi2` and
         the results will be returned in a second DataFrame.
-      * If "fisher", will conduct Fisher's exact test :cite:`scipy_fisher`.
-      * If "mcnemar", will conduct the McNemar :math:`\chi^2` :cite:`statsmodels_mcnemar` test for paired
+      * If "fisher", will conduct Fisher's exact test :footcite:p:`scipy_fisher`.
+      * If "mcnemar", will conduct the McNemar :math:`\chi^2` :footcite:p:`statsmodels_mcnemar` test for paired
         nominal data.
 
   * **margins**, if False will return a crosstabulation table without the total
@@ -80,7 +80,7 @@ Effect Size Measures Formulas
 Cramer's Phi (2x2 table)
 ------------------------
 For analyses were it's a 2x2 table, the following formula is used to
-calculate Cramer's Phi (:math:`\phi`) :cite:`cramer2016`:
+calculate Cramer's Phi (:math:`\phi`) :footcite:p:`cramer2016`:
 
 .. math::
   \phi = \sqrt{\frac{\chi^2}{N}}
@@ -92,7 +92,7 @@ Where N = total number of observations in the analysis
 Cramer's V (RxC where R or C > 2)
 ---------------------------------
 For analyses were it's a table that is larger than a 2x2, the
-following formula is used to calculate Cramer's V :cite:`cramer2016`:
+following formula is used to calculate Cramer's V :footcite:p:`cramer2016`:
 
 .. math::
   V = \sqrt{\frac{\chi^2}{(N*(k - 1))}}
@@ -883,6 +883,6 @@ Make sure that the outcomes are labelled the same in both variables.
 
 References
 ==========
-.. bibliography:: refs.bib
+.. footbibliography:: refs.bib
    :list: bullet
    :cited:

source/difference_test_documentation.rst

@@ -14,19 +14,19 @@ This method is similar to researchpy.ttest(), except it allows the user to use t
 
 This method can perform the following tests:
 
-  * Independent sample t-test :cite:`2018:scipy_ttest_ind`
+  * Independent sample t-test :footcite:p:`2018:scipy_ttest_ind`
 
       * `psudo-code: difference_test(formula_like, data, equal_variances = True, independent_samples = True)`
 
-  * Paired sample t-test :cite:`2018:scipy_ttest_rel`
+  * Paired sample t-test :footcite:p:`2018:scipy_ttest_rel`
 
       * `psudo-code: difference_test(formula_like, data, equal_variances = True, independent_samples = False)`
 
-  * Welch's t-test :cite:`2018:scipy_ttest_ind`
+  * Welch's t-test :footcite:p:`2018:scipy_ttest_ind`
 
       * `psudo-code: difference_test(formula_like, data, equal_variances = False, independent_samples = True)`
 
-  * Wilcoxon signed-rank test :cite:`2018:scipy_wilcoxon`
+  * Wilcoxon signed-rank test :footcite:p:`2018:scipy_wilcoxon`
 
       * By default, discards all zero-differences; this is known as the 'wilcox' method.
       * `psudo-code: difference_test(formula_like, data, equal_variances = False, independent_samples = False)`
@@ -107,7 +107,7 @@ difference_test methods
 Welch Degrees of freedom
 ^^^^^^^^^^^^^^^^^^^^^^^^
 There are two degrees of freedom options available when calculating the Welch's t-test. The default is to use
-the Satterthwaite :cite:`Satterthwaite1946` calculation with the option to use the Welch :cite:`Welch1947` calculation.
+the Satterthwaite :footcite:p:`Satterthwaite1946` calculation with the option to use the Welch :footcite:p:`Welch1947` calculation.
 
 Satterthwaite (1946)
 """"""""""""""""""""
@@ -130,7 +130,7 @@ Effect Size Measures Formulas
 
 Cohen's d\ :sub:`s` (between subjects design)
 """"""""""""""""""""""""""""""""""""""""""""""
-Cohen's d\ :sub:`s` :cite:`cohen1988` for a between groups design is calculated
+Cohen's d\ :sub:`s` :footcite:p:`cohen1988` for a between groups design is calculated
 with the following equation:
 
 .. math::
@@ -144,7 +144,7 @@ with the following equation:
 Cohen's d\ :sub:`av` (within subject design)
 """""""""""""""""""""""""""""""""""""""""""
 Another version of Cohen's d is used in within subject designs. This is noted
-by the subscript "av". The formula for Cohen's d\ :sub:`av` :cite:`lakens2013` is
+by the subscript "av". The formula for Cohen's d\ :sub:`av` :footcite:p:`lakens2013` is
 as follows:
 
 .. math::
@@ -158,9 +158,9 @@ as follows:
 Hedges's g\ :sub:`s` (between subjects design)
 """"""""""""""""""""""""""""""""""""""""""""""""
 Cohen's d\ :sub:`s` gives a biased estimate of the effect size for a population
-and Hedges and Olkin :cite:`hedges1985` provides an unbiased estimation. The
+and Hedges and Olkin :footcite:p:`hedges1985` provides an unbiased estimation. The
 differences between Hedges's g and Cohen's d is negligible when sample sizes
-are above 20, but it is still preferable to report Hedges's g :cite:`kline2004`.
+are above 20, but it is still preferable to report Hedges's g :footcite:p:`kline2004`.
 Hedge's g\ :sub:`s` is calculated using the following formula:
 
 .. math::
@@ -174,8 +174,8 @@ Hedge's g\ :sub:`s` is calculated using the following formula:
 Hedges's g\ :sub:`av` (within subjects design)
 """"""""""""""""""""""""""""""""""""""""""""""""
 Cohen's d\ :sub:`av` gives a biased estimate of the effect size for a population
-and Hedges and Olkin :cite:`hedges1985` provides a correction to be applied to provide an unbiased estimate.
-Hedge's g\ :sub:`av` is calculated using the following formula :cite:`lakens2013` :
+and Hedges and Olkin :footcite:p:`hedges1985` provides a correction to be applied to provide an unbiased estimate.
+Hedge's g\ :sub:`av` is calculated using the following formula :footcite:p:`lakens2013` :
 
 .. math::
 
@@ -188,7 +188,7 @@ Glass's :math:`\Delta` (between or within subjects design)
 Glass's :math:`\Delta` is the mean differences between the two groups divided by
 the standard deviation of the first condition/group or by the second condition/group.
 When used in a within subjects design, it is recommended to use the pre- standard
-deviation in the denominator :cite:`lakens2013`; the following formulas are used
+deviation in the denominator :footcite:p:`lakens2013`; the following formulas are used
 to calculate Glass's :math:`\Delta`:
 
 .. math::
@@ -200,14 +200,14 @@ to calculate Glass's :math:`\Delta`:
 
 Pearson correlation coefficient r (between or within subjects design)
 """""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""
-Rosenthal :cite:`rosenthal1991` provided the following formula to calculate
+Rosenthal :footcite:p:`rosenthal1991` provided the following formula to calculate
 the Pearson correlation coefficient r using the t-value and degrees of freedom:
 
 .. math::
 
   r = \frac{t}{\sqrt{t^2 + df}}
 
-Rosenthal :cite:`rosenthal1991` provided the following formula to calculate
+Rosenthal :footcite:p:`rosenthal1991` provided the following formula to calculate
 the Pearson correlation coefficient r using the z-value and N. This formula
 is used to calculate the r coefficient for the Wilcoxon ranked-sign test. Note,
 that N is the total number of observations.
@@ -220,7 +220,7 @@ that N is the total number of observations.
 Rank-Biserial correlation coefficient r (between or within subjects design)
 """"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""
 The following formula is used to calculate the Rank-Biserial
-correlation coefficient r :cite:`Kerby2012` for the Wilcoxon ranked-sign test.
+correlation coefficient r :footcite:p:`Kerby2012` for the Wilcoxon ranked-sign test.
 
 .. math::
 
@@ -474,5 +474,7 @@ Wilcoxon signed-rank Test
 
 References
 ==========
-.. bibliography:: refs.bib
+.. footbibliography:: refs.bib
+
+   :cited:
    :list: bullet

source/documentation_template.rst

@@ -679,6 +679,6 @@ Wilcoxon Signed-Rank Test
 
 References
 ----------
-.. bibliography:: refs.bib
+.. footbibliography:: refs.bib
    :cited:
    :list: bullet

source/signrank_documentation.rst

@@ -57,7 +57,7 @@ signrank methods
 
 Effect size measures formulas
 =============================
-By default no effect size measures are calculated.
+By default no effect size measures are calculated; Rank-Biserial r calculation is from :footcite:p:`Kerby2012` while the Pearson r calculation is from
 
 Rank-Biserial r :footcite:p:`Kerby2012`
 """"""""""""""""""""""""""""""""""""""""""""""""
@@ -66,7 +66,7 @@ Rank-Biserial r :footcite:p:`Kerby2012`
   \text{Rank-Biserial r = } \frac{\sum{Ranks}_{+} - \sum{Ranks}_{-}}{\sum{Ranks}_{total}}
 
 Pearson r :footcite:p:`Fritz_Morris_Richler2012`
-""""""""""""""""""""""""""""""""""""""""""
+""""""""""""""""""""""""""""""""""""""""""""""""""
 .. math::
 
   \text{Pearson r = } \frac{Z}{\sqrt{N}}

source/ttest_documentation.rst

@@ -9,19 +9,19 @@ Pandas DataFrames with relevant information pertaining to the statistical test c
 
 This method can perform the following tests:
 
-  * Independent sample t-test :cite:p:`scipy_ttest_ind`
+  * Independent sample t-test :footcite:p:`scipy_ttest_ind`
 
       * `psudo-code: ttest(group1, group2, equal_variances = True, paired = False)`
 
-  * Paired sample t-test :cite:p:`scipy_ttest_rel`
+  * Paired sample t-test :footcite:p:`scipy_ttest_rel`
 
       * `psudo-code: ttest(group1, group2, equal_variances = True, paired = True)`
 
-  * Welch's t-test :cite:p:`scipy_ttest_ind`
+  * Welch's t-test :footcite:p:`scipy_ttest_ind`
 
       * `psudo-code: ttest(group1, group2, equal_variances = False, paired = False)`
 
-  * Wilcoxon signed-rank test :cite:p:`scipy_wilcoxon`
+  * Wilcoxon signed-rank test :footcite:p:`scipy_wilcoxon`
 
       * `psudo-code: ttest(group1, group2, equal_variances = False, paired = True)`
 
@@ -107,7 +107,7 @@ Effect Size Measures Formulas
 
 Cohen's d\ :sub:`s` (between subjects design)
 ---------------------------------------------
-Cohen's d\ :sub:`s` :cite:p:`cohen1988` for a between groups design is calculated
+Cohen's d\ :sub:`s` :footcite:p:`cohen1988` for a between groups design is calculated
 with the following equation:
 
 .. math::
@@ -119,9 +119,9 @@ with the following equation:
 Hedges's g\ :sub:`s` (between subjects design)
 ----------------------------------------------
 Cohen's d\ :sub:`s` gives a biased estimate of the effect size for a population
-and Hedges and Olkin :cite:p:`hedges1985` provides an unbiased estimation. The
+and Hedges and Olkin :footcite:p:`hedges1985` provides an unbiased estimation. The
 differences between Hedges's g and Cohen's d is negligible when sample sizes
-are above 20, but it is still preferable to report Hedges's g :cite:p:`kline2004`.
+are above 20, but it is still preferable to report Hedges's g :footcite:p:`kline2004`.
 Hedge's g\ :sub:`s` is calculated using the following formula:
 
 .. math::
@@ -135,7 +135,7 @@ Glass's :math:`\Delta` (between or within subjects design)
 Glass's :math:`\Delta` is the mean differences between the two groups divided by
 the standard deviation of the control group. When used in a within subjects
 design, it is recommended to use the pre- standard deviation in the denominator
-:cite:p:`lakens2013`; the following formula is used to calculate Glass's
+:footcite:p:`lakens2013`; the following formula is used to calculate Glass's
 :math:`\Delta`:
 
 .. math::
@@ -147,7 +147,7 @@ design, it is recommended to use the pre- standard deviation in the denominator
 Cohen's d\ :sub:`z` (within subject design)
 -------------------------------------------
 Another version of Cohen's d is used in within subject designs. This is noted
-by the subscript "z". The formula for Cohen's d\ :sub:`z` :cite:p:`cohen1988` is
+by the subscript "z". The formula for Cohen's d\ :sub:`z` :footcite:p:`cohen1988` is
 as follows:
 
 .. math::
@@ -158,14 +158,14 @@ as follows:
 
 Pearson correlation coefficient r (between or within subjects design)
 ---------------------------------------------------------------------
-Rosenthal :cite:p:`rosenthal1991` provided the following formula to calculate
+Rosenthal :footcite:p:`rosenthal1991` provided the following formula to calculate
 the Pearson correlation coefficient r using the t-value and degrees of freedom:
 
 .. math::
 
   r = \sqrt{\frac{t^2}{t^2 + df}}
 
-Rosenthal :cite:p:`rosenthal1991` provided the following formula to calculate
+Rosenthal :footcite:p:`rosenthal1991` provided the following formula to calculate
 the Pearson correlation coefficient r using the z-value and N. This formula
 is used to calculate the r coefficient for the Wilcoxon ranked-sign test. Note,
 that N is the total number of observations.
@@ -177,7 +177,7 @@ that N is the total number of observations.
 
 Rank-Biserial correlation coefficient r (between or within subjects design)
 ---------------------------------------------------------------------------
-The Rank-Biserial r :cite:`Kerby2012` is also provided for the Wilcoxon signed-rank test as is
+The Rank-Biserial r :footcite:p:`Kerby2012` is also provided for the Wilcoxon signed-rank test as is
 calculated as:
 
 .. math::
@@ -651,6 +651,6 @@ Wilcoxon Signed-Rank Test
 
 References
 ==========
-.. bibliography:: refs.bib
+.. footbibliography:: refs.bib
    :cited:
    :list: bullet