Quantitative and Qualitative Research Methods

• Quantitative research collects numerical data to describe phenomena, investigate variable relationships, and explore cause-effect relationships.
• Qualitative research, also known as naturalistic research, uses nonnumeric data from natural settings through observation and interviews.
• The primary aim of qualitative research is the interpretation of phenomena and discovery of meaning.
• A goal of qualitative research is to learn more about topic variables for later use in quantitative research.

Quantitative Studies

• Quantitative studies are categorized mainly into observational and experimental types.
• The main aim of study designs is to generate/formulate a hypothesis, to test the hypothesis or to prove the hypothesis.
• Observational studies aim to generate or formulate a hypothesis.
• Analytical studies aim to test a hypothesis.
• Experimental studies aim to prove a hypothesis.
• The key difference between experimental and non-experimental research is the extent to which the researcher controls and manipulates variables and the environment (manipulation of independent variables).
• In experimental studies, researchers set up the environment and carefully control interested variables.
• Non-experimental (observational) research takes place in a real-life setting where the researcher cannot control all possible variables.
• Determining causality is harder in non-experimental studies, but they tend to be more flexible and allow for studying a greater range of topics.
• Observational studies are carried out in more natural settings versus experimental
• Observational studies have less control over the study resulting is more susceptible distorting influences

Study Design Differences

• Major study designs differ in several respects: -Unit of observation (group vs. individual). -Manipulation of exposure (experimental vs. observational). -Direction of investigation (retrospective/prospective). -Randomization (allocation to either group). -Timing of data collection (concurrent/historical). -Data collection methods (survey, interview).

Observational Studies

• An investigator observes the occurrence of conditions in "self"-assigned groups.
• Exposure is not assigned.
• Observational studies are practical, feasible and carried out in natural settings.
• Observational study situations have less control; results are more susceptible to distorting influence.

Types of Observational Studies

• Observational (non-experimental) studies are categorized into descriptive and analytical studies.
• Descriptive studies include case reports, case series, cross-sectional (prevalence) studies, and ecological (correlational) studies.
• Analytical studies include case-control (case-reference) studies, cohort follow-up (longitudinal individuals), and cross-sectional (prevalence) studies.

Descriptive Studies

• A descriptive study describes the characteristics of a situation, event, or case and can be carried out on a small or large scale.
• It always describes the event in time, place, and person.
• Descriptive studies answer research questions by asking what, when, where, who, and how for an event.
• An example study describes a disease in terms of time, place, and person.

Case Report Studies

• Case studies describe in-depth the characteristics of one or a limited number of 'cases'.
• A case report is a detailed description of the diagnosis, treatment, response, and follow-up of an individual patient, health center, or village.
• Case studies offer useful insight into problems.
• Case studies are common in social sciences, management sciences, and clinical medicine.
• In clinical medicine, case studies may document characteristics of unrecognized illnesses and form the first step towards building a clinical picture.
• Case reports consider human-based/clinical evidence at the lowest level.
• Case reports serve as the first line of evidence, where new issues and ideas emerge.
• The investigator describes observations occurring in a small number of patients.
• Multiple case reports showing similar findings will trigger more in-depth investigation.
• Case reports are most common in new or rare cases.

Case Series Studies

• A case series involves a group of case reports involving patients who were given similar treatment.
• Case series address unique cases that cannot be explained by known diseases or syndromes. Cases show an important variation of a disease or condition.
• Cases series reflect unexpected events that may yield new or useful information.
• It requires an objective and brief report of a clinical characteristic or outcome from a group of clinical subjects.
• Generalization is not possible due to biased selection or unrepresentativeness of subjects, lack of control group, etc.
• It tracks patients with known exposure given similar treatment or examines their medical records for exposure and outcome.
• Case series can be retrospective or prospective.
• Case series may be confounded by selection bias, which can limit the statements on causality of correlations observed.
• An example of selection bias can happen when physicians looking at patients with a certain illness and a suspected linked exposure have a selection bias because they have drawn their patients from a narrow selection (namely their hospital or clinic).

Cross-Sectional Studies

• Cross-sectional studies are also known as surveys, epidemiologic or prevalence studies.
• They analyze data collected on a group of subjects at one time, which gives data to identify "what is happening now?", and generally take a short time
• Possible uses include diagnosing or staging a disease (e.g., breast cancer).
• Cross sectional studies evaluate different methods of doing the same thing,
• An example of a cross sectional study is examining the relationship between histology slides and MRI findings of diseased carotid arteries.
• They can also be used to establish norms.
• An example of establishing norms is creating normal lab values from normal subjects.
• Establishing norms include surveys that may use preexisting validated surveys.
• Surveys help learn what people think and are sometimes combined with interviews.
• Cross sectional studies study prevalent and incident cases to identify a mix of incidental and prognostic risk factors.
• Cross sectional studies involve a dynamic population sample, efficiently generating new hypotheses and describing population characteristics to provide an outcome prevalence estimate.
• Cross sectional studies are inefficient for determining causal effects or rare/short-duration outcomes and cannot provide direct estimates of risk.
• They are particularly difficult to interpret temporality between exposure and outcome
• Cross sectional studies are relatively inexpensive and quick.
• Repeating cross-sectional surveys are useful for assessing the impact of a service.

Descriptive vs. Analytical Studies

• Descriptive studies aim to describe a situation (e.g., distribution of depression in relation to sex, age, and other characteristics).
• Analytical studies aim to test hypotheses or detect associations (e.g., identify factors that explain the higher rates of depression among women).
• Descriptive studies often have no a-priori hypothesis.
• Analytical studies must have clear and measurable hypotheses and include at least one dependent (outcome) variable and one independent ("exposure") variable.
• Analytical studies investigate assign exposures.
• If there is no comparison group, it is a descriptive study.

Ecological (Correlation) Studies

• Ecological studies use data from entire populations to compare disease frequency between different groups during the same period or in the same population at different points in time.
• An example of an ecological study is finding the correlation between per capita meat intake and colon cancer in women may show that a higher intake of meat was associated with an increased risk of colon cancer.
• it does not estimate an individual's risk but helps stimulate hypotheses for undertaking analytic studies.
• It can be done quickly and less expensively because data are readily available on demographic products and consumption related to disease incidence, mortality, healthcare utilization, etc.
• Unit of observation is a group based.
• Ecological fallacy leads to “Mistaken assumption that a statistical association observed between two group-level variables is equal to the association between the corresponding variables at the individual level".
• In other words, it assumes that what is true for a population is true for the individual members of that population.

Analytical Studies

Cohort Studies (Longitudinal)

• Cohort studies are also known as follow-up, longitudinal, prospective, and incidence studies.
• A cohort study is an observational epidemiological study that attempts to study the relationship between a purported cause (exposure) and the subsequent risk of developing disease.
• Conceptually longitudinal, the study groups are observed over a period of time to determine the frequency of disease among them.
• Cohort studies have a time and direction of inquiry.
• Cohort studies can be historical/retrospective/non-concurrent, prospective/concurrent, or combined.
• The distinction between retrospective and prospective cohort studies depends on whether the diseases have occurred in the cohort at the time the study begins.
• All relevant exposures and health outcomes in a retrospective cohort study have already occurred whe the study is initiated.
• In a prospective cohort study, the relevant causes may or may not have occurred at the time the study begins, but the diseases have not yet occurred, and following the cohort's selection, the investigator must wait for the disease to appear in the cohort members.
• Cohort studies can answer the question "What will happen?"
• Cohort studies are used for typical cohort studies, outcome assessment (patient outcomes: economic, functional, satisfaction, QOL), and retrospective cohort studies that rely on prospective records collected (if accurate) – still forward in time in the past.
• For statistical analysis, relative risk (RR) is used.
• The first step in a prospective study design identifies relevant people groups to collect information on their exposure history.
• These people are followed over time and the incidence of outcomes is measured.
• The main limitation of the prospective design is time and cost, especially when studying chronic diseases that may only become apparent after sufficient time.
• The main limitation of prospective studies is the loss of participants due to death or immigration.

Case-Control Studies

• Case-control studies are relatively simple and economical to carry out to investigate causes of diseases, especially rare diseases.
• Studies include cases (people with a disease of interest) and a suitable control group (people without that disease or outcome variable).
• Comparisons are made of occurrences of possible causes between cases and controls.
• Case-control studies are called retrospective studies given their backwards analysis from the disease to a potentially casual factor.
• Case-control studies require matching needed, as well as matching for age, gender and residence.
• Case-Control Studies may be difficult to differentiate from Case Series (both are after the fact).
• The design is often used in the study of rare diseases or as a preliminary study where little is known about the association between the risk factor and disease of interest
• One of the most significant successes of the case-control study was the demonstration of the link between tobacco smoking and lung cancer.
• Case-control studies were initially analyzed by testing whether or not there were significant differences between the proportion of exposed subjects among cases and controls.

Measurements in Observational Study Designs

• Measurement for various study designs in terms of prevalence, incidence, odds ratio, and relative risk are essential to arrive at conclusion of a study
• Prevalence indicates proportion of people in a population with disease and refers to the proportion of people with a condition at or during a particular time period.
• Prevalence rate can be measured by using cross sectional studies
• Incidince rate measures the rapidity with which newly diagnosed cases of the disease of interest develop
• Total number of new events over the sum of the person-time of the at-risk population.

Relative Risk or Risk Ratio:

• RR is the risk of an event (or of developing a disease) relative to exposure.
• Relative risk is a ratio of the probability of the event occurring in the exposed group versus a non-exposed group.
• RR > 1 = positive association
• RR = 1 = no association
• RR < 1 = negative association

Odds Ratio

• An odds ratio (OR) is a measure of association between an exposure and an outcome and represents the odds that an outcome will occur given a particular exposure, compared to the odds of the outcome occurring in the absence of that exposure

• Odds ratios are particularly used in case-control studies, but can also be used in -sectional and cohort study designs (with certain modifications and/or assumptions). Odds ratios are used to compare the relative odds for the occurrence of disease/disorder given aspects of med history.

  OR Formula: OR = (a/c) / (b/d) OR = (ad) / (bc)

  OR = 1 Exposure does not affect odds of outcome OR greater than 1: Exposure associated with higher odds of outcome OR less than 1: Exposure associated with lower odds of outcome(preventive).

• Sport is a statistically Sport with obesity OR = 0.56, CI (0.1 – 0.8) Sport is a statistically significant preventive variable of obesity ( negatively associated with obesity.