(1) Concept Review
(2) Evaluating Descriptive Claims
(3) Variables
- Validity
September 25, 2025
define our terms in a way that is transparent and can be used systematically. If concepts are opaque or idiosyncratic \(\to\) STOP!
translate concepts into something that we can (in principle) observe. If variables do not correspond to the concept / correspond to other concepts \(\to\) STOP!
devise transparent and systematic procedures with known uncertainty to observe those attributes of specific cases. If measurement procedure is opaque, likely to suffer from bias, or has high degree of uncertainty \(\to\) STOP!
What is misinformation?
What is disinformation?
“Misinformation is know it when I see it”:
“Misinformation is factually inaccurate information OR whatever is on social media”:
concepts must be transparent, systematic, and about observable traits
What is misinformation?
What is disinformation?
How can we observe misinformation in a way that lets us evaluate whether:
“Misinformation has become more widespread in the past decade.”
How can we observe disinformation in a way that lets us evaluate whether:
“Disinformation has become more widespread in the past decade.”
A measurable property of cases that corresponds to a concept or part of a concept and can potentially take on different values across cases and time (it varies across cases).
A procedure for determining the value a variable takes for specific cases based on observation.
What is the tallest mountain on the North Shore?
Elevation (distance from peak to sea level)
Vertical distance in meters from mean sea level to the top of the peak
Use difference in barometric pressure at Burrard Inlet and peak to calculate difference in elevation
Are you going to climb the mountain? Prominence might be a better concept of height.
the elevation of a summit relative to the highest point to which one must descend before reascending to a higher summit
Vertical distance in meters from top of the peak to lowest contour line surrounding it and no other higher peaks.
Satellites using radar interferometry create topographical maps; computer algorithm to find lowest contour
Different concepts \(\to\) different variables
Different variables \(\to\) different measures
Different Answer:
Claim: “Canadian exposure to misinformation has increased in recent years.”
Concept: exposure to misinformation
Variable: Proportion of people who believe it is harder to distinguish between true and false information now compared to three years ago (Statistics Canada Report in 2023)
Measure: Ask a sample of Canadians to indicate their belief that distinguishing true vs. false information has gotten “harder”, “easier”, or “unchanged”
Claim: “Canadian exposure to misinformation has increased in recent years.”
Concept: exposure to misinformation
Variable: Proportion of people who believe it is harder to distinguish between true and false information now compared to three years ago (Statistics Canada Report in 2023)
Measure: Ask a sample of Canadians to indicate their belief that distinguishing true vs. false information has gotten “harder”, “easier”, or “unchanged”
Claim: “Conservative Twitter/X users are exposed to more misinformation.”
Concept: exposure to misinformation
Variable: The average falseness of messages by elite (e.g., politicians, bureaucrats, famous personalities, advocacy groups, and media organizations) X users followed by a person, weighted by the number of Tweets made by each elite.
Variables for one concept may depend on other concepts and their variables:
exposure to misinformation: variable requires:
Claim: “Conservative Twitter/X users are exposed to more misinformation.”
Concept: falseness of a message
Variable: rating of a statement on a scale of (True, Mostly True, Half True, Mostly False, False, Pants on Fire)
Measure: Ratings of Fact-checked statements on PolitiFact.com. Methodology Here.
Claim: “Conservative Twitter/X users are exposed to more misinformation.”
Concept: message exposure
Variable: Number of tweets posted by “elite” (e.g., politicians, bureaucrats, famous personalities, advocacy groups, and media organizations) accounts followed by the user
Claim: “Conservative Twitter/X users are exposed to more misinformation.”
Concept: political ideology
Variable: A score between -1 (liberal) to 1 (conservative) based on the accounts a user follows on Twitter (assuming that they are more likely to follow accounts with similar political views, less like to follow accounts with dissimilar views)
Two issues:
different variables take on different kinds of values \(\to\) depending on the claim, variables with different levels of measurement are appropriate
variables may not capture the concept \(\to\) variables lack validity
The kinds of values taken by a variable is called its level of measurement
nominal levels of measurement:
ordinal levels of measurement
interval levels of measurement
ratio levels of measurement
What is the level of measurement?
Discuss with your neighbors
What is the level of measurement?
claims about what exists (or has existed/will exist) in the world:
Even if we develop a concept that is transparent and systematic…
This may mean…
We have to develop variables that better match the concepts in the claim.
validity: Degree of “fit” between a variables the concept the variable is intended to capture.
“Country X isn’t the most politically corrupt”
Concept: Political Corruption or “the use of power by government officials for illegitimate private gain”
Variable: Fraction of political officeholders in a place prosecuted for corruption
Measure: Match criminal court defendants in corruption prosecutions to list of politicians.
“Country X isn’t the most politically corrupt”
Concept: Political Corruption or “the use of power by government officials for illegitimate private gain”
Variable: Fraction of political officeholders in a place prosecuted for corruption
Measure: Match criminal court defendants in corruption prosecutions to list of politicians.
“Country X isn’t the most politically corrupt”
Concept: Political Corruption or “the use of power by government officials for illegitimate private gain”
Variable: Fraction of political officeholders in a place prosecuted for corruption
Measure: Match criminal court defendants in corruption prosecutions to list of politicians.
If problems are real: Country \(X\) will not be found “most corrupt” even when it is. (Claim will not be found to be wrong even when it is wrong)
Claim: “The risk of being a victim of a violent crime is less in Canada than the United States”
Variable: Number of violent crimes
Stats Canada found that in 2023: 43% of Canadians said “it was becoming more difficult that it was three years earlier to distinguish between true and false information”
Can we conclude that “misinformation is getting worse”?
Claim: “Canadian exposure to misinformation has increased in recent years.”
Concept: exposure to misinformation
Variable: Proportion of people who believe it is harder to distinguish between true and false information now compared to three years ago (Statistics Canada Report in 2023)
Measure: Ask a sample of Canadians to indicate their belief that distinguishing true vs. false information has gotten “harder”, “easier”, or “unchanged”
Measuring exposure to misinformation from political elites on Twitter
Claim: “Conservative Twitter/X users are exposed to more misinformation.”
Concept: falseness of a message
Variable: rating of fact-checked statements on a scale of (True, Mostly True, Half True, Mostly False, False, Pants on Fire)
Measure: Ratings of Fact-checked statements on PolitiFact.com. Methodology Here.
Claim: “Conservative Twitter/X users are exposed to more misinformation.”
Concept: message exposure
Variable: Number of tweets posted by “elite” (e.g., politicians, bureaucrats, famous personalities, advocacy groups, and media organizations) accounts followed by the user
Claim: “Conservative Twitter/X users are exposed to more misinformation.”
Concept: exposure to misinformation
Variable: The average falseness of fact-checked statements by elite (e.g., politicians, bureaucrats, famous personalities, advocacy groups, and media organizations) X users followed by a person, weighted by the number of Tweets made by each elite.
Claim: “Conservative Twitter/X users are exposed to more misinformation.”
Concept: political ideology
Variable: A score between -1 (liberal) to 1 (conservative) based on the accounts a user follows on Twitter (assuming that they are more likely to follow accounts with similar political views, less like to follow accounts with dissimilar views)
It is not enough to just imagine that there might be a validity problem: