First Stage Results of Our Media Bias Research

Table of Links

Abstract and 1 Introduction 2. Data

3. Measuring Media Slant and 3.1. Text pre-processing and featurization

3.2. Classifying transcripts by TV source

3.3. Text similarity between newspapers and TV stations and 3.4. Topic model

4. Econometric Framework

4.1. Instrumental variables specification

4.2. Instrument first stage and validity

5. Results

5.1. Main results

5.2. Robustness checks

6. Mechanisms and Heterogeneity

6.1. Local vs. national or international news content

6.2. Cable news media slant polarizes local newspapers

7. Conclusion and References

Online Appendices

A. Data Appendix

A.1. Newspaper articles

A.2. Alternative county matching of newspapers and A.3. Filtering of the article snippets

A.4. Included prime-time TV shows and A.5. Summary statistics

B. Methods Appendix, B.1. Text pre-processing and B.2. Bigrams most predictive for FNC or CNN/MSNBC

B.3. Human validation of NLP model

B.4. Distribution of Fox News similarity in newspapers and B.5. Example articles by Fox News similarity

B.6. Topics from the newspaper-based LDA model

C. Results Appendix

C.1. First stage results and C.2. Instrument exogeneity

C.3. Placebo: Content similarity in 1995/96

C.4. OLS results

C.5. Reduced form results

C.6. Sub-samples: Newspaper headquarters and other counties and C.7. Robustness: Alternative county matching

C.8. Robustness: Historical circulation weights and C.9. Robustness: Relative circulation weights

C.10. Robustness: Absolute and relative FNC viewership and C.11. Robustness: Dropping observations and clustering

C.12. Mechanisms: Language features and topics

C.13. Mechanisms: Descriptive Evidence on Demand Side

C.14. Mechanisms: Slant contagion and polarization

C. Results Appendix

C.1. First stage results

C.2. Instrument exogeneity

In this Section, we follow Ash and Galletta (2023) to demonstrate that our instrument is unrelated to demographic characteristics that predict policy preferences or news channel viewership. We use linear regressions with demographic characteristics and state fixed effects as covariates to predict viewership and newspaper content. Specifically, we obtain predictions related to the endogenous regressor (viewership) and to the outcome (the probability of newspaper content to be Fox-like). These predictions capture the variation in viewership and news content due to pre-existing cultural, economic, and political county characteristics.

We then regress these predictions on different definitions of our instrument Positionjs. Table C.2 summarizes this identification check. Columns 1 and 2 document that there is no significant relationship between the absolute position of Fox News and the predicted values for viewership or newspaper content. Columns 3 and 4 show that there is no significant relationship between relative FNC channel position and the respective predicted values. Overall, these results suggest that channel positions are not associated with county characteristics otherwise important for our endogenous regressor or outcome.