Daniel Riffe

The Effectiveness of Random, Consecutive Day and Constructed Week Sampling in Newspaper Content Analysis.

This study compares 20 sets each of samples of four different sizes (n=7, 14, 21 and 28) using simple random, constructed week and consecutive day samples of newspaper content. Comparisons of sample efficiency, based on the percentage of sample means in each set of 20 falling within one or two standard errors of the population mean, show the superiority of constructed week sampling.

A Content Analysis of Content Analyses: Twenty-Five Years of Journalism Quarterly

Examination of the increasing number of articles employing quantitative content analysis in 1971–95 Journalism & Mass Communication Quarterly showed primary focus on news/editorial content in U.S. media. Nearly half examined newspapers, and half were coauthored. Most used convenience or purposive samples. Few involved a second research method or extra-media data, explicit theoretical grounding, or research questions or hypotheses. Half reported intercoder reliability, and two-fifths used only descriptive statistics. Analysis of trends shows growth in coauthorship and reporting of reliability, and increasing emphasis on more sophisticated statistical analysis. No parallel trend exists, however, in use of explicit hypotheses/research questions or theoretical grounding.

Sampling Error and Selecting Intercoder Reliability Samples for Nominal Content Categories.

This study views intercoder reliability as a sampling problem. It develops a formula for generating sample sizes needed to have valid reliability estimates. It also suggests steps for reporting reliability. The resulting sample sizes will permit a known degree of confidence that the agreement in a sample of items is representative of the pattern that would occur if all content items were coded by all coders.

Sample Size for Newspaper Content Analysis in Multi-Year Studies

This study examines the most efficient method of sampling content from five years of daily newspaper editions. Selecting nine constructed weeks (nine issues from a Monday, nine from a Tuesday, etc.) from five years is more efficient than the ten constructed weeks—two from each year—suggested by previous research on populations of a years newspaper content. This rule holds provided the variables being measured do not have large variances.

Mood Influence on the Appeal of Bad News

Respondents were placed into a bad or good mood and then provided with reading choices. They chose magazine articles that featured either bad or good news. In agreement with theoretical expectations, women in a bad mood were drawn to good news, sampling significantly more of it than women in a good mood. Men did not show this preference, however. Gender-specific selection of news stories was further evident in that women in a bad mood sampled less bad news than did men in a bad mood, whereas women in a good mood sampled more bad news than men in a good mood did.

Issues and Best Practices in Content Analysis

This article discusses three issues concerning content analysis method and ends with a list of best practices in conducting and reporting content analysis projects. Issues addressed include the use of search and databases for sampling, the differences between content analysis and algorithmic text analysis, and which reliability coefficients should be calculated and reported. The “Best Practices” section provides steps to produce reliable and valid content analysis data and the appropriate reporting of those steps so the project can be properly evaluated and replicated.

The Shrinking Foreign Newshole of the New York Times

The Times has fewer, but longer international stories than it did two decades ago, and the front page contains a higher proportion of international items.

Sample Size in Content Analysis of Weekly News Magazines

This study explores a variety of approaches to deciding sample size in analyzing magazine content. Having tested random samples of size six, eight, ten, twelve, fourteen, and sixteen issues, the authors show that a monthly stratified sample of twelve issues is the most efficient method for inferring to a years issues.

The Effectiveness of Simple and Stratified Random Sampling in Broadcast News Content Analysis

A comparison of simple random, monthly stratified and quarterly/weekly stratified sampling in content analyses of television news used annual “populations” of network newscasts. Different samples were drawn and sample statistics compared with annual parameters. Based on percentages of samples that included population means within one or two standard errors, the most efficient technique was two random days per month.

Sample Size in Content Analysis of Weekly Newspapers

Weeklies, although increasing in circulation, have rarely been studied as a source of information. These authors review the research on sampling for daily newspapers and explore various sampling techniques for weekly newspapers.