The Metropolitan Museum of Art

What characteristics do important artworks share?

Fabulous Hitmontop
Jerry Jang, Charlotte Ding, Fiona Yang
Kevin Chang, Richard Kelly

5/5/23

Topic and motivation

Topic question: For artworks that are considered popular and important in the Metropolitan Museum of Art Collection, what characteristics do they have?

  • Analysis 1 Research Question: completed before 1650 (pre-Renaissance) or after 1650 (post-Renaissance)?

  • Analysis 2 Research Question: on the art history timeline website or not on the art history timeline website?

Introduction to data

Rows: 477,804
Columns: 4
$ is_highlight      <chr> "False", "False", "False", "False", "False", "False"…
$ is_timeline_work  <chr> "False", "False", "False", "False", "False", "False"…
$ object_end_date   <int> 1853, 1901, 1927, 1927, 1927, 1927, 1927, 1927, 1927…
$ finished_recently <fct> yes, yes, yes, yes, yes, yes, yes, yes, yes, yes, ye…

Artworks from the Metropolitan Museum of Art, csv file

Key Variables after cleaning:

  • is_highlight: important artwork

  • object_end_date: the year the artwork was completed

  • is_timeline_work: on the Timeline of Art History website

  • finished_recently: pre-and-during vs. post-Renaissance

Highlights from Exploratory Data Analysis

Variables Explored: Artist Nationality, Gender, Dynasty, Period, Creation Year, Introduced on Timeline Website?

  • Gender, Nationality: Artworks by an Organization / Group

  • Dynasty, Period: Mutually Exclusive

Inference/modeling/analysis 1

  • Is proportion of artworks completed before 1650 that are highlighted different from the proportion completed after 1650 that are highlighted? \[ H_0 : p_{pre-1650} - p_{post-1650} = 0 \] \[ H_A :  p_{pre-1650} - p_{post-1650} \neq 0 \]

Hypothesis testing:

Response: is_highlight (factor)
Explanatory: finished_recently (factor)
# A tibble: 1 × 1
      stat
     <dbl>
1 0.000867
# A tibble: 1 × 1
  p_value
    <dbl>
1       0

Inference/modeling/analysis 2

  • Is proportion of artworks on the art history timeline website that are highlighted higher than the proportion not on the art history timeline website that are highlighted?

    \[ H_0: p_{timeline~highlight} - p_{non-timeline~highlight} = 0 \]

    \[ H_A: p_{timeline~highlight} - p_{non-timeline~highlight} > 0 \]

Hypothesis testing:

Response: is_highlight (factor)
Explanatory: is_timeline_work (factor)
# A tibble: 1 × 1
   stat
  <dbl>
1 0.160
# A tibble: 1 × 1
  p_value
    <dbl>
1       0

Conclusions + future work

Conclusion #1

There is sufficient evidence that the proportion of artworks completed before 1650 (pre-Renaissance) that are highlighted is different from the proportion of artworks completed after 1650  (post-Renaissance) that are highlighted.

Conclusion #2

There is sufficient evidence that the proportion of highlighted artworks included on the Timeline of Art History website is higher than the proportion of highlighted artworks not included on the website.

Fabulous Hitmontop