Observational studies and experiments Introduction to Data Types - - PowerPoint PPT Presentation

▶
observational studies and experiments
SMART_READER_LITE
LIVE PREVIEW

Observational studies and experiments Introduction to Data Types - - PowerPoint PPT Presentation

Mar 03, 2023 318 likes •511 views

INTRODUCTION TO DATA Observational studies and experiments Introduction to Data Types of studies Observational study: Collect data in a way that does not directly interfere with how the data arise Only correlation can be

slide-1
SLIDE 1

INTRODUCTION TO DATA

Observational studies and experiments

slide-2
SLIDE 2

Introduction to Data

Types of studies

  • Observational study:
  • Collect data in a way that does not directly interfere with

how the data arise

  • Only correlation can be inferred
  • Experiment:
  • Randomly assign subjects to various treatments
  • Causation can be inferred
slide-3
SLIDE 3

Introduction to Data

Design a study

Screens at bedtime and aention span

screens average attention span average attention span no screens

  • bservational

study

screens no screens average attention span average attention span

experiment

Association? Causation?

slide-4
SLIDE 4

INTRODUCTION TO DATA

Let’s practice!

slide-5
SLIDE 5

INTRODUCTION TO DATA

Random sampling and random assignment

slide-6
SLIDE 6

Introduction to Data

Random…

  • Random sampling:
  • At selection of subjects from population
  • Helps generalizability of results
  • Random assignment:
  • At selection of subjects from population
  • Helps infer causation from results
slide-7
SLIDE 7

Introduction to Data

Scope of inference

Random assignment No random assignment Random sampling Causal and generalizable Not causal, but generalizable Generalizable No random sampling Causal, but not generalizable Neither causal nor generalizable Not generalizable Causal Not causal

slide-8
SLIDE 8

INTRODUCTION TO DATA

Let’s practice!

slide-9
SLIDE 9

INTRODUCTION TO DATA

Simpson’s paradox

slide-10
SLIDE 10

Introduction to Data

Explanatory and response

x (explanatory) y (response)

slide-11
SLIDE 11

Introduction to Data

Multivariate relationships

x1 (explanatory) x2 (explanatory) x3 (explanatory) y (response)

slide-12
SLIDE 12

Introduction to Data

Multivariate relationships

calories (explanatory) age (explanatory) fitness (explanatory) heart health (response)

slide-13
SLIDE 13

Introduction to Data

Simpson’s paradox

  • 2

4 6 8 3 6 9

x1 y x2

  • 1
slide-14
SLIDE 14

Introduction to Data

Berkeley admission data

Admied Rejected Male 1198 1493 Female 557 1278

slide-15
SLIDE 15

INTRODUCTION TO DATA

Let’s practice!

slide-16
SLIDE 16

INTRODUCTION TO DATA

Recap: Simpson’s paradox

slide-17
SLIDE 17

Introduction to Data

Simpson’s paradox

  • Overall: males more likely to be admied
  • Within most departments: females more likely
  • When controlling for department, relationship

between gender and admission status is reversed

  • Potential reason:
  • Women tended to apply to competitive

departments with low admission rates

  • Men tended to apply to less competitive

departments with high admission rates

slide-18
SLIDE 18

INTRODUCTION TO DATA

Let’s practice!