Quantitative Methods in Sociology

Quantitative Methods in Sociology

• Sociologists gather empirical information through quantitative methods.
• These methods measure naturally quantitative elements or translate social aspects into numerical data for statistical analysis.

Quantitative Methods in Sociology Process

• Utilizing quantitative methods in sociology involves a two-step process.
• The first step is data collection.
• The second step involves data analysis.

Methods for Collecting Quantitative Data

• Surveys are the most traditional method for collecting quantitative data.
• A survey is a questionnaire where research participants answer questions, and the answers are statistically analyzed.
• Research participants are those who agree to answer the survey.
• Considerations for collecting survey data include the research phenomenon, the types of questions, how to find participants, and the number of surveys to collect.

Research Questions & Quantitative Methods

• Research questions often involve concepts, which are abstract terms that are not directly observable.
• Example: the relationship between social media use, educational attainment, and mental health in North American teenagers.
• The example research question contains three concepts: social media use, educational attainment, and mental health.

Variables

• Quantitative methods measure the social world as a series of variables.
• A variable is a measurement of a phenomenon that has more than one value or score.
• Concepts in the research question must be developed into measurable variables for quantitative research.
• University major is a variable that applies to individual people and includes categories they can select from.

Operationalization

• Operationalization specifies how a concept will be measured.
• Operationalization translates a concept into a variable, or more often, a series of variables.
• Social media use can be operationalized into variables such as hours per day spent on social media, the number of times per day someone visits a social media site, and the number of social media sites someone engages with.

Sampling

• A sampling procedure is developed to decide who should be asked to take a survey.
• Population refers to the universe of cases the research question is relevant to.
• The research question defines the population.
• Sample refers to a subset of the population that is empirically investigated.
• The sample is the subset of the population that actually takes the survey, if using survey methods.
• Generalizability means the survey results give a good picture of what the population looks like.
• Quantitative methods give a good picture of some social phenomenon even when studying a small part of it empirically.

Factors Influencing Generalizability

• The first factor is the sampling procedure.
• The second factor is the sample size: a larger sample size results in more generalizable results.
• Random sampling gives each individual in the population an equal probability of being selected for the study.
• Representative sampling means the sample is a reproduction of the population along particular demographic characteristics.
• Convenient sampling means people are sampled based on their availability.
• Snowball sampling involves sampled people introducing the researcher to other possible study participants
• Limited to qualitative research and often the only way to sample difficult to access groups

Other Quantitative Methods in Sociology

• Secondary analysis
• Data scraping
• Quantitative content analysis

Secondary Analysis

• Secondary analysis involves researchers analyzing existing data in a novel way rather than collecting original data.
• Census, GGS, and CCHS, etc. are examples of secondary analysis.
• Advantages include lower cost, larger sample size, and sampling technique.

Data Scraping

• Data scraping uses computer algorithms to generate data about people's behavior by "scraping" information about their online activity.
• This data scraping procedure originated in marketing.
• It is a useful tool in sociology for overcoming social desirability bias.

Social Desirability Bias

• Social desirability bias describes the fact that people may answer questions on a survey based on how they wish to appear rather than how they actually behave.
• Social desirability bias can be conscious or unconscious.
• Example: 18% of GGS respondents say they attend a faith institution once per week, but results from cellphone data analysis show 3%.

Quantitative Content Analysis

• Content analysis is the systematic analysis of media that we consume.
• Quantitative content analysis involves counting how often something occurs within a set of textual, visual, or auditory media.

Kinds of Variables

• Nominal/Categorical: Numbers are used to represent different conditions, but the phenomenon itself is not quantitative, so variable values cannot be ranked.
  • Example: Race, Neighborhood, Marital Status, Religion, Favourite Kardashian.
• Ordinal: Different values of the variable can be ranked, but the precise difference between ranked values cannot be measured.
  • Example: Likert scales, SES/Class, Pain.
• Ratio: Differences between values are measurable, and there exists a real zero (limit).
  • Example: Number of siblings, Income, Hours spend on social media per day.

Nominal Variables

• The variable values do not reflect a natural ranking of the variable's categories and are arbitrary.

Ordinal

• Variable values have a natural ranking, and we don't know the precise difference between the variable values.
• Likert scale is a survey question that measures survey participants' opinions, attitudes, or motivations, and the variable values quantify some phenomena not naturally quantitative.

Ordinal vs Ratio Variables

• Operationalization affects variable type.
• Variable is ordinal if the variable asks approximately how many hours spent per week playing video games from 3 or less, 4-10, 10-15, 15-30 and more than 30
• If the question asked how many hours do you spend, per week, playing video games and participant write in specific number of hours, variable would be ratio variable

Descriptive Statistics

• Descriptive statistics tell us about the distribution of one variable and are univariate statistics.
• Central tendency refers to measures that attempt to give a quick picture of the content of one variable.
• Mode: The variable value that is the most common or has the highest count. For nominal-level variables, the mode is the only appropriate measure of central tendency.

Median

• The median is the value that separates the sample into two equal halves and represents the "middle value."
• The middle value is found with the formula (n+1)/2, where n is the sample.
• For quantitative data, the median is the only appropriate measure of central tendency.

Mean

• The mean represents the average value.
• It is calculated as the sum of variable values divided by n, which is the number of cases
• Σxi/n
• Outliers are extreme cases where variable values are extreme relative to the majority of the distribution.
• Outliers overinfluence the mean.
• Sometimes it is appropriate to remove outliers from analysis.

Measures of Central Tendency and Distribution Skew

• Variable distribution is the way a variable is distributed across its values.
• For ratio variables, the measures of central tendency can indicate how the variables are distributed.
• Proportion: Tells us the percentage of a variable that falls into particular variable value
• Related as a value between 0 and 1
• The proportion of high school seniors who did not read for pleasure in the past year is calculated by # of cases in the category of interest / n = 24 / 110 = 0.218

Inferential Statistics

• Inferential statistics measure the relationship between two or more variables.
• Knowing the value of one variable allows an inference about the likely value of another variable.
• Quantitative methods make inferences about the relationship between variables in the population, using inferential statistics calculated with data from a sample.
• Bivariate statistics describe the relationship between two variables.
• Multivariate statistics describe the relationship between three or more variables.
• Independent variable is hypothesized to influence the dependent variable.
• Dependent variable is hypothesized to be influenced by independent variable.

Bivariate Statistics

• A cross-tab, or cross-tabulation, is useful for calculating the relationship between two variables when at least one is nominal/categorical.
• Independent variable is the politcal/religious identification.
  • Dependent variable: level of support for sex education in schools.
• Correlation coefficient measures the relationship between two ratio level variables.
• Related as a number between – 1 and 1
  • The closer the correlation coefficient is to the absolute value of 1, the greater extent to which the variable values correspond to one another
• Positive correlation is when an increase in V1 is associated with an increase in V2.
• Negative correlation is when an increase in V1 is associated with a decrease in V2.
• For example, if we want to study the relationship between gender and income, we will consider gender to be the independent variable (because gender is logically prior to income)
• Sometimes, there is a logical reason to consider one variable to be the independent variable, and the other to be the dependent variable
• In many situations, however, is it not clear which variable is the "influencer" and which variable is the "influenced.
• Inferential statistics can tell us the extent to which two or more variables share a mathematical relationship
• For example, if a correlation coefficient shows that two variables, x and y, are related, then we know that a change in variable x gives us some predictive capacity with regard to the value of variable y (and visa versa.
• The correlation coefficient does not tell us about causation
• This means that we need to theorize the relationship
• This means that we need to theorize the relationship.
  • x causes y
  • y causes x
  • the relationship between x and y is spurious

Multivariate Statistics

• In sociology, quantitative research almost always uses multivariate analyses.
• Multivariate statistics describe the effect of several independent variables at once, on some dependent variable.
• It is necessary to use multivariate statistics because experiments lack random assignment.
• Multivariate analyses usually employ control variables, which are variables not directly related to the research question but are suspected to be related to the dependent variable.
  • Common control variables in sociology include gender, race, and social class.
  • Independent variables is GDP per capita and occupational category.
• Control variables include Age, education, martial status, religion, town size, religious composition of country