Skip to Main Content

× Indigenous People's Day: The Sherrill and Moriarty Libraries will be closed on Monday, October 14th.
Enjoy the holiday!

Research Methods & Studies

Studies that Could be Either Qualitative or Quantitative

Cross-Sectional Studies (or ‘prevalence studies’) examine the data on disease and exposure at one particular time point. Due to the lack temporal evidence, cross-sectional studies cannot assess the cause and effect relationship.

In a cross-sectional study, the investigator measures the outcome and the exposures in the study participants at the same time. Cross-sectional designs are used for population-based surveys and to assess the prevalence of diseases in clinic-based samples. A cross-sectional study involves looking at data from a population at one specific point in time.

They may be conducted either before planning a cohort study or a baseline in a cohort study. This method is often used to make inferences about possible relationships or to gather preliminary data to support further research and experimentation.

  • Example: Researchers can assess the prevalence of HIV and risk behaviors in male sex workers. They also evaluated the association between HIV and sociodemographic factors. The data were collected by interviewer-administered questionnaires (for sociodemographic and behavior data), clinical evaluation for sexually transmitted infections (STIs), including HIV. It allows researchers to look at numerous characteristics at once (age, income, gender, etc.)

Cross-sectional studies are observational in nature and are known as descriptive research, not causal or relational. Researchers record the information that is present in a population, but they do not manipulate variables. A cross-sectional study functions as a snapshot of a particular group of people at a given point in time. Unlike longitudinal studies, which look at a group of people over an extended period, cross-sectional studies are used to describe what is happening at the present moment.

Strengths of a Cross-sectional Study

  • Cross-sectional studies can usually be conducted relatively faster and are inexpensive
  • These study designs may be useful for public health planning, monitoring, and evaluation. For example, sometimes the National AIDS Programmed conducted cross-sectional sentinel surveys among high-risk groups and prenatal mothers every year to monitor the prevalence of HIV in these groups.

Limitations of a Cross-sectional Study

  • Since this is a 1-time measurement of exposure and outcome, it is difficult to derive causal relationships.
  • These studies are also prone to certain biases. For example, we wish to study the relation between diet and exercise and being overweight/obese. We conduct a cross-sectional study and recruit 250 individuals. We assess their dietary habits, exercise habits, and body mass index at one point of time in a cross-sectional survey. However, individuals who are overweight/obese have started to exercise more or altered their feeding habits (eat more salads). Hence, in a cross-sectional survey, we may find that overweight/obese individuals are also more likely to eat salads and exercise more. Thus, we have to be careful about interpreting the associations and direction of associations from a cross-sectional survey.
  • The prevalence of an outcome depends on the incidence of the disease as well as the length of survival following the outcome. For example, even if the incidence of HIV (number of new cases) goes down in one particular community, the prevalence (total number of cases – old as well as new) may increase. This may be due to cumulative HIV positive cases over a period. Thus, just performing cross-sectional surveys may not be sufficient to understand disease trends in this situation.

"Longitudinal studies employ continuous or repeated measures to follow particular individuals over prolonged periods of time—often years or decades. They are generally observational in nature, with quantitative and/or qualitative data being collected on any combination of exposures and outcomes, without any external influenced being applied. This study type is particularly useful for evaluating the relationship between risk factors and the development of disease, and the outcomes of treatments over different lengths of time" (Caruana et. al., 2015).

Longitudinal Studies v. Cross-Sectional Studies:

"A longitudinal study, like a cross-sectional one, is observational. So, once again, researchers do not interfere with their subjects. However, in a longitudinal study, researchers conduct several observations of the same subjects over a period of time, sometimes lasting many years. The benefit of a longitudinal study is that researchers are able to detect developments or changes in the characteristics of the target population at both the group and the individual level. The key here is that longitudinal studies extend beyond a single moment in time. As a result, they can establish sequences of events" (Institute for Work & Health, 2015). 

Further Reading: 

 

Bias:

  • "Attrition Bias. Over time, participants may cease to take part in a longitudinal study. This is known as attrition. Attrition can result from a range of factors, some of which are unavoidable, while others can be reduced by careful study design or practice" (Learning Hub, n.d.).

"A pilot study is a small feasibility study designed to test various aspects of the methods planned for a larger ,more rigorous, or confirmatory investigation. The primary purpose of a pilot study is not to answer specific research questions but to prevent researchers from launching a large-scale study without adequate knowledge of the methods proposed; in essence, a pilot study is conducted to prevent the occurrence of a fatal flaw in a study that is costly in time and money. 

A well-planned and executed pilot study also may help researchers identify potential confounding variables that were not  previously known and evaluate the strength of relationships among key variables to aid in the calculation of sample size (Polit&Beck,2017).In addition, researchers may use pilot studies to refine training strategies for research personnel and determine whether preliminary findings support a larger, more rigorous investigation" (Lowe, 2019).

Further Reading:

 

"Questionnaire surveys are a technique for gathering statistical information about the attributes, attitudes, or actions of a population by a structured set of questions. Administered by mail, in person, through the Internet, and over the telephone, questionnaire surveys provide broad coverage of populations enabling us to explore spatial and social variations in people's attributes, attitudes, and actions. The aim is to obtain information suitable for statistical analysis, so attention is paid to how respondents are selected, the extent to which questions relate to underlying concepts, and completion rates. The information obtained from questionnaire surveys is constructed through the process of designing and administering the questionnaire and compiling the data that result. The design of the questionnaire affects all subsequent stages of data collection and analysis" (Preston, 2009). 

Further Reading: 

Bias: "Survey bias is an aspect of a survey that has a negative effect on the outcome of the results. It essentially means that some aspect of your survey could have swayed respondents into answering a certain way or providing certain feedback" (Quantilope, 2023). 

  • "Sampling bias is a type of bias in which a researcher gathers a sample of respondents for a questionnaire that does not accurately represent the intended population (i.e. only surveying older generations about TikTok perceptions). As such, the survey results cannot accurately be used to make claims about a general consumer base."
  • "Non-response bias is a type of bias that happens when a group of non-responders to a survey represents a large portion of opinions that vary drastically from the opinions of those who have responded. This results in alternative opinions being missed, so the findings give the wrong impression of how a total population views an issue."
    • "A common example of non-response bias is seen during elections. Those who can’t make it to the polls due to polling location availability, work schedules, or childcare, may have opinions that are meaningfully different from those who show up to the polls - leading to a biased skew in the results."
  • "Acquiescence bias is where respondents have the tendency to lean toward positive responses more frequently than negative ones. It's also often known as agreement bias."
    • "For example, acquiescence bias might appear when a respondent feels indifferent toward a topic but they select ‘strongly agree’ because they may feel that’s the ‘right’ answer - even though it doesn’t actually reflect their sentiment."
  • "Social desirability bias is a form of survey bias in which respondents answer questions in ways they think will be viewed favorably by others. It is similar to acquiescence bias in that respondents report metrics that don’t necessarily reflect their true sentiments but for a different reason. While acquiescence bias is typically limited to agreement biases, social desirability bias is a bit broader - not limited to agree/disagree or yes/no."
    • "For example, survey respondents may underreport their alcohol intake or smoking frequency because society views high volumes of these activities negatively. Or, survey takers may give inaccurate answers about how frequently they work out at the gym."
  • "Question order bias is when the flow of survey questions influences how a respondent will react. Asking certain questions early on in your survey design can sway a respondent into how they later answer questions. As a simple example, asking respondents about Netflix and then in a later question asking them to name streaming platforms could show bias toward mentions of Netflix."
    • "You can think of question order bias almost as leading questions. It’s prepping a respondent so they already have something top of mind, rather than capturing their true conscious thoughts."
  • "Interviewer bias is a form of survey bias in which a moderator’s own opinions interfere with the feedback from a respondent during qualitative survey interviews (i.e. video surveys, focus groups, etc.). This type of bias could be positive or negative, intentional or not, but regardless it’s a form of bias to be aware of."

Further Reading: