Imputaties beoordelen: Over veel variabelen

Tot nu toe hebben we manieren besproken om naar afzonderlijke variabelen of paren van variabelen en hun geïmputeerde waarden te kijken. Soms wil je echter de imputaties voor veel variabelen tegelijk bekijken. Hiervoor moet je wat data munging en herindeling doen. Deze les laat zien hoe je die datatransformatie uitvoert, wat best pittig kan zijn in nabular data. De functie shadow_long() zet de data in de juiste vorm voor dit soort visualisaties.

Deze oefening maakt deel uit van de cursus

Omgaan met ontbrekende gegevens in R

Cursus bekijken

Oefeninstructies

Gebruik shadow_long() om de geïmputeerde data ocean_imp_mean te verzamelen, met focus op humidity en air_temp_c.
Print de data en bekijk deze.
Verken de imputaties in een histogram met geom_histogram(), zet de waarden op de x-as, kleur op basis van hun missingness en facet op variable.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

# Gather the imputed data 
ocean_imp_mean_gather <- shadow_long(___,
                                     ___,
                                     ___))
# Inspect the data
___

# Explore the imputations in a histogram 
ggplot(ocean_imp_mean_gather, 
       aes(x = value, fill = value_NA)) + 
  geom_histogram() + 
  facet_wrap(~variable)

Code bewerken en uitvoeren

Deze oefening maakt deel uit van de cursus

Omgaan met ontbrekende gegevens in R

SkillTag.level.beginnerSkillTag.label

4.8+

Begin de cursus gratis

Chapter 1 introduces you to missing data, explaining what missing values are, their behavior in R, how to detect them, and how to count them. We then introduce missing data summaries and how to summarise missingness across cases, variables, and how to explore across groups within the data. Finally, we discuss missing data visualizations, how to produce overview visualizations for the entire dataset and over variables, cases, and other summaries, and how to explore these across groups.

Exercise 1: Introduction to missing data Exercise 2: Using and finding missing values Exercise 3: How many missing values are there?Exercise 4: Working with missing values Exercise 5: Why care about missing values?Exercise 6: Summarizing missingness Exercise 7: Tabulating Missingness Exercise 8: Other summaries of missingness Exercise 9: How do we visualize missing values?Exercise 10: Your first missing data visualizations Exercise 11: Visualizing missing cases and variables Exercise 12: Visualizing missingness patterns

In chapter two, you will learn how to uncover hidden missing values like "missing" or "N/A" and replace them with `NA`. You will learn how to efficiently handle implicit missing values - those values implied to be missing, but not explicitly listed. We also cover how to explore missing data dependence, discussing Missing Completely at Random (MCAR), Missing At Random (MAR), Missing Not At Random (MNAR), and what they mean for your data analysis.

Exercise 1: Searching for and replacing missing values Exercise 2: Using miss_scan_count Exercise 3: Using replace_with_na Exercise 4: Using replace_with_na scoped variants Exercise 5: Filling down missing values Exercise 6: Fix implicit missings using complete()Exercise 7: Fix explicit missings using fill()Exercise 8: Using complete() and fill() together Exercise 9: Missing Data dependence Exercise 10: Differences between MCAR and MAR Exercise 11: Exploring missingness dependence Exercise 12: Further exploring missingness dependence

In this chapter, you will learn about workflows for working with missing data. We introduce special data structures, the shadow matrix, and nabular data, and demonstrate how to use them in workflows for exploring missing data so that you can link summaries of missingness back to values in the data. You will learn how to use ggplot to explore and visualize how values changes as other variables go missing. Finally, you learn how to visualize missingness across two variables, and how and why to visualize missings in a scatterplot.

Exercise 1: Tools to explore missing data dependence Exercise 2: Creating shadow matrix data Exercise 3: Performing grouped summaries of missingness Exercise 4: Further exploring more combinations of missingness Exercise 5: Visualizing missingness across one variable Exercise 6: Nabular data and filling by missingness Exercise 7: Nabular data and summarising by missingness Exercise 8: Explore variation by missingness: box plots Exercise 9: Visualizing missingness across two variables Exercise 10: Exploring missing data with scatter plots Exercise 11: Using facets to explore missingness Exercise 12: Faceting to explore missingness (multiple plots)

In this chapter, you will learn about filling in the missing values in your data, which is called imputation. You will learn how to impute and track missing values, and what the good and bad features of imputations are so that you can explore, visualise, and evaluate the imputed data against the original values. You will learn how to use, evaluate, and compare different imputation models, and explore how different imputation models affect the inferences you can draw from the models.

Exercise 1: De lege plekken invullen Exercise 2: Imputeer data onder het bereik met nabular-data Exercise 3: Gëimputeerde waarden visualiseren in een scatterplot Exercise 4: Maak een histogram van geïmputeerde data Exercise 5: Wat maakt een goede imputatie Exercise 6: Slechte imputaties beoordelen Exercise 7: Imputaties beoordelen: de schaal Exercise 8: Imputaties beoordelen: Over veel variabelen

Huidige oefening

Exercise 9: Imputaties uitvoeren Exercise 10: Gegevens imputeren met simputation Exercise 11: Imputaties evalueren en vergelijken Exercise 12: Imputaties beoordelen (meerdere modellen & variabelen)Exercise 13: Imputaties en modellen evalueren Exercise 14: Veel imputatiemodellen combineren en vergelijken Exercise 15: De verschillende parameters in het model evalueren Exercise 16: Laatste les