{ "1st-stdev": "1st Standard Deviation", "2nd-stdev": "2nd Standard Deviation", "action-required": "Action Required", "actions": "actions", "add-elbow-plot": "Add elbow plot for choosing number of clusters", "addition": "Addition", "aggregation-mode": "Aggregation Mode", "alternate-color-scheme": "Alternate Color Scheme", "and": "and", "attach-clusters-table": "Attach clusters to table?", "axis-label-rotation": "Axis Label Rotation", "bandwidth-adjustment": "Bandwidth adjustment", "Bar Chart": "Bar Chart", "Bar Chart-description": "A bar chart is a graph that displays categorical data as rectangular bars with the bar heights being proportional to the frequency of each category. When grouping by a second variable, the bar chart becomes a grouped bar chart, in which multiple bars are shown for each category. An alternative would be to stack the bars on top of each other; in this case, the chart is called a stacked bar chart.", "bars-represent": "Bars represent:", "bin-quantitative": "Bin quantitative variables into categorical", "bin-transformer-header": "Create new variable by binning a quantitative variable into categories", "binning-strategy": "Binning Strategy:", "bins": "Bins", "boolean-and": "A && B evaluates to true if both A and B are true", "boolean-not": "!A evaluates to true if A is not true", "boolean-or": "A || B evaluates to true if either A or B are true", "Box Plot": "Box Plot", "Box Plot-description": "A box and whisker plot is a representation for quantitative data. For each variable, the box plot shows its 25% quantile (a value greater than 25% of the data), its median, and its 75% quantile as a box. The whiskers extend to the lower fence at the smallest value in the sample that is less than Q1 but greater than (Q1 - 1.5*IQR) and to the analogously defined upper fence.", "calculate": "Calculate", "categorical": "Categorical:", "categorical-transformer-header": "Create new variable by renaming or combining categories", "category-of-interest": "Category of Interest:", "center-values-subtract-the-mean": "Center values (= subtract the mean)?", "central-tendency-measures": "Central Tendency Measures", "change-tree-features": "Change tree features...", "Chi-square Independence Test-description": "A test determining if there is an association between two categorical variables.", "Chi-squared Independence Test": "Chi-square Independence Test", "Chi-squared-description": "A chi-squared distribution is a continuous probability distribution with a single parameter, an integer denoting its degrees of freedom.", "choose-category-labels": "Choose categorical labels for interval bins", "clear-all": "Clear All", "clear-data": "Clear Data", "clear-plots": "Clear Plots", "close": "Close", "close-tutorial": "Close Tutorial", "closing-parenthesis": "Closing parenthesis", "color": "Color", "column-to-sample-from": "Column to sample from", "column-variable": "Column Variable:", "columns": "Columns", "common-x-axis": "Common x-axis?", "common-y-axis": "Common y-axis?", "components-to-add": "# of components to add to data table", "confidence-level": "Confidence Level", "Contingency Table": "Contingency Table", "Contingency Table-description": "A contingency table displays either the raw absolute or relative frequencies of two categorical variable's values alongside their row and column totals.", "contingency-table-group-tooltip": "Generate a contingency table for each category of a chosen grouping variable", "Contour Chart": "Contour Chart", "Contour Chart-description": "A contour plot can be used to display the joint distribution of two quantitative variables. It plots a three-dimensional surface by plotting constant slices, called contours, on a two-dimensional grid.", "correlation": "correlation", "Correlation": "Correlation", "Correlation Matrix": "Correlation Matrix", "Correlation Test": "Correlation Test", "Correlation Test-description": "A test used to evaluate the Pearson correlation between two variables, which measures the linear association between them.", "correlation-matrix": "Correlation Matrix", "count": "Count", "counts": "Counts", "create-filtered-dataset": "Create filtered dataset", "create-filtered-dataset-tooltip": "Create new dataset from currently active filters", "create-groups": "Create groups (e.g., for training-test set split or cross-validation)", "create-new-variable": "Create new variable", "customize-color": "Customize color", "data": "Data", "data-driven": "Data-driven", "Data-driven-description": "A non-parametric kernel density estimate not derived from a statistical distribution with parameters but computed from the data.", "data-empty": "Data set is empty.", "data-explorer": "Data Explorer", "decimal-places": "decimal place(s).", "Decision Tree": "Decision Tree", "Decision Tree-description": "Grow a decision tree for either a regression or classification problem. For quantitative responses, at each iteration of the algorithm the data are split by the variable which leads to splits with the greatest reduction in variance for the response. For categorical responses, the data are split on the feature which leads to the largest information gain (measured either in terms of the Gini index or entropy)", "delete": "Delete", "description": "Description", "difference-means": "value for difference of means", "difference-proportions": "value for difference of proportions", "digits-after-decimal-snap": "digits after the decimal point to snap to", "direction": "Direction:", "display": "Display:", "display-density": "Display density instead of counts", "distance": "Distance", "division": "Division", "drag-red-bars": "Drag the red vertical bar(s) to change breakpoints", "drag-table": "Drag Table", "end": "End", "enter-formula": "Enter formula...", "entire-dataset-used": "Entire dataset used to create output.", "example": "Example", "example-description-calculation": "Multiply values of <1>{{variable}} by <3>9/5 and add <5>32", "example-description-exponential": "Natural exponential function of variable <1>{{variable}}", "example-description-multiply": "Multiply values of variables <1>{{first}} and <3>{{second}}", "Excess Kurtosis": "Excess Kurtosis", "excess-kurtosis": "Excess Kurtosis", "exp-tooltip": "`exp( x ):` Natural exponential function.", "explanatory-variable": "Explanatory Variable (X):", "Exponential-description": "An exponential distribution is a continuous probability distribution with a single parameter, the rate parameter, which is the inverse of the mean. It is often used to model the time between events in a system.", "expression": "Expression", "filtered-data": "Filtered Data", "filtered-data-tooltip": "Click to toggle display of active filters", "First Quartile": "First Quartile", "first-quartile": "First Quartile", "first-variable": "First Variable:", "Five-Number Summary": "Five-Number Summary", "five-number-summary": "Five-Number Summary", "flip-coordinates": "Flip Coordinates", "formula-transformer-example-intro": "Use the formula text area below to create a new variable. The following table illustrates a few use-cases:", "formula-transformer-header": "Create a new variable as a function of existing variables", "freq-table-group-by-tooltip": "Generate a frequency table for each category of a chosen grouping variable", "frequencies": "Frequencies", "Frequency Table": "Frequency Table", "Frequency Table-description": "A frequency table is a tabular display for either the raw absolute or relative frequencies of a categorical variable's values.", "fullscreen-display": "Fullscreen Display", "function": "Function", "generate": "Generate", "generate-random-data": "Generate Random Data", "greater-or-equal": "Greater than or equal to", "greater-than": "Greater than", "group-by": "Group By:", "group-by-statistics-tooltip": "Calculate the statistic(s) separately for observations from each category of either one or two grouping variable(s)", "group-proportion": "Group Proportion", "group-transformer-header": "Create group variables (e.g., for training/test set split or cross-validation)", "group-variable-must-be-different": "Please make sure that the group variable or second variable is not equal to your variable of interest.", "grouping-variable": "Group Variable:", "groups": "Groups:", "Heat Map": "Heat Map", "Heat Map-description": "A data display for quantitative variables in which data values are represented as colors. Regions with many observations are colored red, whereas regions without observations are colored in dark blue.", "hide-example-guide": "Hide Example Guide", "hide-toolbox": "Hide Toolbox", "Hierarchical Clustering": "Hierarchical Clustering", "Histogram": "Histogram", "Histogram-description": "A histogram allows one to visualize the distribution of a quantitative variable. In order to create a histogram, the observed range of values is divided into different, non-overlapping intervals called \"bins\"; the height of each bin corresponds to how many observations are in that bin range.", "history": "History", "impurity-measure": "Impurity Measure", "include-intercept": "Include intercept?", "initialization-method": "Initialization method", "insert-break-line": "Insert break line", "interaction": "Interaction", "interactions-functions": "Interactions, Transformations (e.g., sqrt), Functions", "Interquartile Range": "Interquartile Range", "interquartile-range": "Interquartile Range", "Interval Plot": "Interval Plot", "Interval Plot-description": "An interval plot displays the confidence intervals for group means and as such allows one to visually compare the averages of a quantitative variable across groups.", "jitter-x-axis": "Jitter X-Axis", "jitter-y-axis": "Jitter Y-Axis", "kmeans": "kmeans", "kmeans-description": "Algorithm to partition observations into k clusters by iteratively assigning them to the cluster with the nearest mean.", "Kruskal-Wallis Test": "Kruskal-Wallis Test", "Kruskal-Wallis Test-description": "The Kruskal-Wallis rank sum test evaluates for multiple samples the null hypothesis that their medians are identical. The Kruskal-Wallis test is a nonparametric test which does not require the data to be normally distributed.", "label": "Label", "labels": "Labels", "LASSO": "LASSO", "LASSO-description": "Fit a regression model in which non-zero regression coefficients are penalized using the L1 regularization penalty. The LASSO performs automatic model selection as it will shrink the regression coefficients of some variables to zero.", "latitude": "Latitude:", "leave-note": "Leave Note", "Line Plot": "Line Plot", "Line Plot-description": "A line plot can be used to display one quantitative variable or the relationship between two quantitative variables as a number line. If no variable is supplied for the x-axis, the values of the y-axis variable are displayed according to their indices in the data table.", "linkage": "Linkage", "ln-tooltip": "`ln( x ):` Natural logarithm.", "location-encoding": "Location encoding", "locations": "Locations:", "Logistic Regression": "Logistic Regression", "longitude": "Longitude:", "lower": "Lower", "Map": "Map", "Map-description": "Display geospatial information in a map using latitude and longitude or country / state names.", "max": "Max", "Max": "Max", "max-tooltip": "`max( a, b, ... )`: The largest of a, b, ...", "maximum-tree-depth": "Maximum tree depth", "mean": "Mean", "Mean": "Mean", "mean-tooltip": "`mean( a, b, ... )`: The average of a, b, ...", "median": "Median", "Median": "Median", "method": "Method", "min": "Min", "Min": "Min", "min-obs-leafs": "Minimum # of observations in leaf nodes", "min-tooltip": "`min( a, b, ... )`: The smallest of a, b, ...", "mode": "Mode", "models": "Models", "more": "More", "Mosaic Plot": "Mosaic Plot", "Mosaic Plot-description": "A mosaic plot can be used to visualize two or more categorical variables. The areas of the boxes in the plot are proportional to the cell frequencies of a contingency table of the selected variables.", "Multiple Linear Regression": "Multiple Linear Regression", "Multiple Linear Regression-description": "Predict a quantitative response variable using one or more explanatory variables.", "multiplication": "Multiplication", "Naive Bayes": "Naive Bayes", "name-new-variable": "Name of new variable", "new": "New", "new-variable-appended": "The new variable will be appended as a new column to the data table.", "no-plots-yet": "No plots have been created yet...", "Normal-description": "A normal distribution is a continuous probability distribution with a mean value and a standard deviation. It has a bell-shaped curve and is the most commonly used distribution for continuous variables.", "not": "not", "number-of-clusters": "Number of clusters", "number-of-groups": "Number of groups", "number-of-observations": "Number of observations", "number-of-observations-tooltip": "Generate a custom number of observations (starting at index 0)", "number-of-trees": "Number of trees", "old": "Old", "omit-missing": "Omit missing values", "omit-missing-tooltip": "If not ticked, result will be null if variable contains missing values", "One-Sample Mean Test": "One-Sample Mean Test", "One-Sample Mean Test-description": "A test for the mean of a quantitative variable.", "One-Sample Proportion Test": "One-Sample Proportion Test", "One-Sample Proportion Test-description": "A test for the proportion of a selected category of a qualitative variable.", "One-Way ANOVA": "One-Way ANOVA", "One-Way ANOVA-description": "A one-way analysis of variance tests for equality of means across several groups.", "open-parenthesis": "Open parenthesis", "open-shared-plots": "Open Shared Plots", "optional-second-variable": "Second Variable (optional):", "or": "or", "order-direction": "Order direction:", "order-outer-groups": "Order outer groups", "order-x-axis": "Order x-axis", "orientation": "Orientation:", "other-location-measures": "Other Location Measures", "others-actions": "Others' Actions", "outcome-y": "Outcome (Y):", "output": "Output", "output-model": "Model Output", "output-table": "Table Output", "output-test": "Test Output", "overlay-density-lines": "Overlay density line(s)", "overlay-observations": "Overlay Observations?", "overlay-points": "Overlay Points?", "overlay-regression-line": "Overlay regression line?", "own-actions": "Own Actions", "PCA": "Principal Component Analysis", "PCA-description": "Algorithm to convert observations of possibly correlated variables into linearly uncorrelated principal components.", "Pie Chart": "Pie Chart", "Pie Chart-description": "Statistical display for categorical data. The arc length of each slice in the pie is proportional to the quantity of the respective category. An alternative display for categorical data is a bar chart.", "pie-sizes-represent": "Pie sizes represent:", "plot-shared": "Plot shared.", "plot-shared-message": "You have successfully shared your plot.", "plots": "Plots", "power-tooltip": "`power( base, exponent )`: base raised to the power of exponent.", "predictors-to-check": "# of predictors to check at each split", "predictors-x": "Predictors (X):", "proportion": "proportion value", "proportions-add-one": "Proportions must add up to one.", "QQ Plot": "QQ Plot", "QQ Plot-description": "A QQ (quantile-quantile) plot allows one to compare the distribution of a sample to a reference distribution (usually a normal distribution). Deviations from the plotted 45 degree reference line on the plot indicate how much the sample deviates from the reference distribution.", "quantile": "Quantile", "Quantile": "Quantile", "quantiles": "Quantile(s):", "quantiles-placeholder": "Enter quantiles to compute...", "quantiles-tooltip": "Enter any numbers between zero and one", "quantitative": "Quantitative:", "questions": "Questions", "Random Forest": "Random Forest", "range": "Range", "Range": "Range", "relationship-measures": "Relationship measures", "relative-frequencies-inside-each-group": "Relative frequencies inside each group", "relative-frequency": "Relative Frequency", "rename-or-combine": "Rename or combine categories", "report": "Report", "report-relative-frequencies": "Report relative frequencies to", "restore-dataset": "Restore dataset", "restore-dataset-tooltip": "Restore dataset with the given filters in the data table", "restore-original-dataset": "Restore original dataset", "restore-original-dataset-tooltip": "Restore original dataset with all observations", "round-tooltip": "`round( x )`: Round a number to the nearest integer.", "row-variable": "Row Variable:", "sample-from-columns": "Sample from columns", "sample-with-replacement": "Sample with replacement", "scale-values": "Scale values (= divide by standard deviation)?", "Scatterplot": "Scatterplot", "Scatterplot Matrix": "Scatterplot Matrix", "Scatterplot Matrix-description": "A scatterplot matrix is a grid of scatterplots visualizing the relationships between any two variables from a chosen set of quantitative variables.", "Scatterplot-description": "A scatterplot is used to display the values of two quantitative variables inside a Cartesian coordinate system. Three additional variables can be displayed on the plot in this implementation: The color and type of the dots corresponding to each observation can represent categorical variables, and a quantitative variable can be chosen to govern the size of the dots. In cases where there is a textual identifier for each observation, it can be displayed as a label next to the dots. It is also possible to overlay a linear and/or smoothed regression line.", "scope": "Scope:", "score-threshold-for-split": "Score threshold for split", "second-variable": "Second Variable:", "second-variable-statistic-tooltip": "Second variable for computing bivariate statistic", "select-grouping-or-second-variable": "Please select either a grouping variable or a second variable to compare {{var}} against.", "select-name": "Please enter a name (no spaces or periods)...", "select-quantitative-categorical": "Please select which variables should be treated as quantitative and which ones as categorical", "select-row-and-column-variable": "You need to select a row and column variable for the contingency table", "select-variable-bin": "Please select a variable to bin...", "select-variables": "Select Variables", "set-slice-sizes": "Set slice sizes to sum of summary variable:", "shape-measures": "Shape Measures", "share": "Share", "show-boxplot": "Show Boxplot", "show-colors": "Show Colors", "show-dataset-info": "Show dataset info", "show-example-guide": "Show Example Guide", "show-land": "Show Land", "show-point-markers": "Show point markers?", "show-regression-model": "Show Regression Model", "show-toolbox": "Show Toolbox", "show-tutorial": "Show Tutorial", "significance-level": "Significance level ", "Simple Linear Regression": "Simple Linear Regression", "Simple Linear Regression-description": "Statistical model which estimates a best-fit line for a response variable of interest (Y) given exactly one predictor variable (X). The line is determined by its intercept (Y-value at X = 0) and slope (the increase in Y associated with a unit increase of X).", "size": "Size", "skewness": "Skewness", "Skewness": "Skewness", "smaller-or-equal": "Smaller than or equal to", "smaller-than": "Smaller than", "smoothing-parameter": "Smoothing Parameter", "specify-parameters": "Specify Parameters", "specify-parameters-tooltip": "Manually specify parameters for the selected distribution instead of estimating them from the data", "split-by": "Split By", "sqrt-tooltip": "`sqrt( x )`: Square root.", "stack-bars": "Stack bars", "Standard Deviation": "Standard Deviation", "standard-deviation": "Standard Deviation", "start": "Start", "statistics": "Statistics", "statistics-tooltip": "One or more statistics to compute for the variable of interest", "stdev-tooltip": "`stdev( a, b, ... )`: Standard deviation of a, b, ...", "submit": "Submit", "subtraction": "Subtraction", "success": "Success", "sum-tooltip": "`sum( a, b, ... )`: The sum of a, b, ...", "summary-function": "Summary function:", "summary-statistics": "Summary Statistics", "T-description": "A t-distribution is a continuous probability distribution with a single parameter, the number of degrees of freedom.", "tables": "Tables", "tests": "Tests", "Third Quartile": "Third Quartile", "third-quartile": "Third Quartile", "toggle-fullscreen": "Toggle fullscreen", "toolbox": "Toolbox", "total-percentages": "Total Percentages", "transform": "Transform", "transformation": "Transformation", "treat-as-categorical": "Treat as categorical", "treat-as-quantitative": "Treat as quantitative", "treat-labels-as-numbers": "Treat category labels as numbers (all new labels need to be digits)", "treat-labels-as-numbers-tooltip": "If the new values for all categories are numeric, you may tick this box to create a quantitative variable instead of a categorical one", "Tukey HSD Test": "Tukey HSD Test", "Tukey HSD Test-description": "Tukey's honestly significant difference (HSD) test is a post hoc test for pairwise comparisons of means in a one-way analysis of variance (ANOVA).", "Two-Sample Mean Test": "Two-Sample Mean Test", "Two-Sample Mean Test-description": "A test for equality of means across two groups.", "Two-Sample Proportion Test": "Two-Sample Proportion Test", "Two-Sample Proportion Test-description": "A test for equality of proportions for a selected category of a qualitative variable across two groups.", "type": "Type", "type-of-test": "Type of Test:", "Uniform-description": "A uniform distribution is a continuous probability distribution which has the same density for any value between the lower and upper limits of the distribution (i.e., its two parameters).", "unshare": "Unshare", "upper": "Upper", "value": "value", "variable": "Variable:", "variable-created": "Variable created", "variable-created-msg": "The variable with the name {{name}} has been successfully generated", "variable-exists": "Variable exists", "variable-exists-msg": "The original variables of the data set cannot be overwritten.", "variable-removed": "Variable removed", "variable-removed-msg": "The variable with the name {{variable}} has been successfully removed.", "variable-s": "Variable(s):", "variable-to-bin": "Variable to bin:", "variables": "Variables:", "variables-created": "Variables created", "variables-created-msg": "Variables with names {{name}} have been successfully generated", "variables-invalid-alert": "The <1>quantitative or <3>categorical data arrays contain variable names not present in the <5>data object.", "variables-statistics-tooltip": "Quantitative variable for which to compute statistic(s)", "variance": "Variance", "Variance": "Variance", "variation-measures": "Variation Measures", "vs": "vs.", "x-axis": "x-axis:", "x-axis-variable": "Variable on x-axis:", "y-axis": "y-axis:", "y-axis-variable": "Variable on y-axis:" }