imhr.Webgazer.model¶

Functions

imhr.Webgazer.model.anova(config, y, f, df, csv, path, effects, is_html=True)[source]¶

Run analysis of variance model using rpy2, seaborn and pandas.

Parameters:	y : str Response variable. f : str Formula to use for analysis. df : pandas.core.frame.DataFrame Pandas dataframe of raw data. f : str R-compatiable formula. csv : str Name of generated CSV file to run analysis in R. path : str The directory path to save the generated files. effects : list List of main effects. is_html : bool Whether html should be generated.
Returns:	model : rpy2.robjects.methods.RS4 Python representation of an R instance of class ‘S4’. df_anova : pandas.core.frame.DataFrame Pandas dataframe of model output. get_anova : str R script to run model. html : :class:`str Html output.

Notes

Resources

• https://rpsychologist.com/r-guide-longitudinal-lme-lmer
• https://sites.ualberta.ca/~lkgray/uploads/7/3/6/2/7362679/slides_- anova_assumptions.pdf
• https://rpubs.com/tmcurley/twowayanova
• https://rstudio-pubs-static.s3.amazonaws.com/158708_78d414c091fc47bd99f6f75e3bd8f4cb.html
• https://m-clark.github.io/docs/mixedModels/anovamixed.html
• http://dwoll.de/rexrepos/posts/anovaMixed.html
• https://stats.stackexchange.com/questions/247582/repeated-measures-anova-in-r-errorsubject-vs-errorsubject-day
• https://cran.r-project.org/web/packages/afex/vignettes/afex_anova_example.html#post-hoc-contrasts-and-plotting
• http://www.let.rug.nl/nerbonne/teach/rema-stats-meth-seminar/presentations/Wieling-MixedModels-2011.pdf

Definition:

A test that allows one to make comparisons between the means of multiple groups of data, where two independent variables are considered.

Assumptions of ANOVA

1. Normal distribution (normality)

   • Short: Samples are drawn from a normally distributed population (Q-Q Plot, Shapiro-Wilks Test)
   • Detailed Definition: Residuals in data are normally distributed.

2. Homogeneity of variance (homoscedasticity)

   • Short: Variances are equal (or similar).
   • Detailed: Varience for a DV is constant across the sample. (residual vs fitted plot, Scale-Location plot, Levene’s test)

3. Independent observations

   • Samples have been drawn independently of each other. No analysis needed.

Hypothesis Interpretation

• Null: The means of all levels of an IV groups are equal.
• Alternative: The mean of at least level of an IV is different.

imhr.Webgazer.model.lmer(config, y, f, df, exclude, csv, path, effects, is_html=True)[source]¶

Run linear mixed regression model, using rpy2, seaborn and pandas.

Parameters:

y : str Response variable. f : list of str Formula to use for analysis. df : pandas.core.frame.DataFrame Pandas dataframe of raw data. f : str R-compatiable formula. exclude : list List of participants to be excluded. csv : str Name of generated CSV file to run analysis in R. path : str The directory path to save the generated files. effects : list List of main effects. is_html : bool Whether html should be generated.

Returns:

model : rpy2.robjects.methods.RS4 Python representation of an R instance of class ‘S4’. df_lmer : pandas.core.frame.DataFrame Pandas dataframe of model output. get_lmer : str R script to run model. html : :class:`str Html output.

Notes

Resources

• https://rpsychologist.com/r-guide-longitudinal-lme-lmer
• https://stackoverflow.com/questions/47686227/poisson-regression-in-statsmodels-and-r
• https://tsmatz.wordpress.com/2017/08/30/glm-regression-logistic-poisson-gaussian-gamma-tutorial-with-r/
• https://stats.stackexchange.com/questions/311556/help-interpreting-count-data-glmm-using-lme4-glmer-and-glmer-nb-negative-binom

imhr.Webgazer.model.logistic(config, y, f, df, me, exclude, csv, path, is_html=True)[source]¶

Run logistic regression model, using rpy2, seaborn and pandas.

Parameters:	y : str Response variable. f : str Formula to use for analysis. df : pandas.core.frame.DataFrame Pandas dataframe of raw data. me : list of str List of main effects. exclude : list List of participants to be excluded. csv : str Name of generated CSV file to run analysis in R. path : str The directory path to save the generated files. is_html : bool Whether html should be generated.
Returns:	model : rpy2.robjects.methods.RS4 Python representation of an R instance of class ‘S4’. df_logit : pandas.core.frame.DataFrame Pandas dataframe of model output. get_logit : str R script to run model. html : :class:`str Html output.

Notes

Resources

• https://rpsychologist.com/r-guide-longitudinal-lme-lmer
• https://stats.idre.ucla.edu/r/dae/mixed-effects-logistic-regression/
• https://www.statisticssolutions.com/assumptions-of-logistic-regression/