Lecture 24-25: Cross-Sectional Studies Flashcards
Give the definition of a cross-sectional study
- Cross-Sectional studies are OBSERVATIONAL studies that examine relationships of health/disease to other variables of interest AT THE SAME TIME
- a.k.a.; a PREVALENCE study
- Entire population or a subset is selected for study
- Called CROSS-SECTIONAL because information gathered represents what is occurring at a point in time or time-frame A-CROSS a large population. A “snap-shot” in time
- Focuses SIMULTANEOUSLY on disease & population characteristics, including exposures, health status, health-care utilization, etc… (depending on study)
- Seeks associations (NOT Causation)
- Generates and tests hypotheses
- By repetition in different time periods, can be used to measure change/trends (not in same patients)
- Most Cross-Sectional studies are SURVEYS or DATABASESE capturing different aspects of US pop.
- Data from different perspectives (e.g., inpatient vs. outpatient) or via different study/survey methodologies and information captured
Describe the two possible cross-sectional approaches
- Collect data on each member of the population
- Pregnancy-Smoking data from KC Health Dept.
- More frequently utilized in city/state-level evaluations, if data already tracked (ongoing collection)
- Pregnancy-Smoking data from KC Health Dept.
- More frequently utilized in city/state-level evaluations, if data already tracked (ongoing collection) - Take a sample of the population & draw inferences to the remainder (generalizable)
- More frequent approach (for U.S.-level data)
What is the most common sampling scheme?
- Probability samples (most common)
- Every element in the population has a known (non-zero) probability of being included in sample
What are the 6? Examples of Probability Schemes?
- Simple
- Systematic
- Stratified Simple
- Stratified Disproportionate
- Multi-Stage
- Custer Multi-Stage
Describe Simple Random Sampling
- Simple Random sampling
- Assign random numbers, then take randomly selected numbers to get desired sample size, OR
- Assign random numbers, then sequentially-list numbers and take desired sample size from top (or bottom) of listed numbers
Describe Systematic Random Sampling
Assign random numbers, then randomly sort these random numbers, then select highest (or lowest) number, then SYSTEMATICALLY , then by a pre-determined sampling-interval take every Nth numbers to get desired sample size
Describe Stratified Simple Random Sampling
STRATIFY Sampling Frame by desired characteristic (e.g., Gender), then use SIMPLE Random sampling to select desired sample size
Describe stratified disproportionate random sampling
- Disproportionately utilizes STRATIFIED SIMPLE random sampling when baseline population is not at the desired proportional percentages to the referent population
- Stratified sample ‘weighted’ to return sample population back to baseline population
- Useful for ‘Over-Sampling’
Describe Multi-Stage Random Sampling
- Uses SIMPLE Random sampling at MULTIPLE-STAGES towards patient selection
- Counties (Primary Sampling Unit; PSU)
- City Blocks/Zip Codes (Secondary Sampling Unit; SSU)
- Clinic/Hospital/Household
- Individual/Individual Chart
Describe custer multi-stage random sampling
- Same as Multi-Stage Random sampling but ALL ‘elements’ clustered together (at any stage) or selected for inclusion
- ALL Clinics in a zip code
- ALL Households in a community
Describe Non-Probability Sampling Schemes
- ‘Quasi-Systematic’ or ‘Convenience’ samples (not really, Completely Random or fully Probabilistic)
- Decide on what fraction of population is to be sampled and how they will be sampled
- Example: All persons whose last name begins with “M-Z”
- Example: All members of a professional business association
- Example: All persons attending clinic every M/W/F for 6 months
- Example: All persons referred by selected-peers
- Concern: There is some known or unknown order to the sample generated by selected scheme which may introduce bias (SELECTION BIAS)
Describe Two Common Broad Approaches to Collection of Study Data/Information
- Questionnaires/Surveys
- Either directly from patients/caregivers or their medical records - Physical assessments (which might involve laboratory, clinical, or psychological tests)
- Great for assessing health/disease in similar population as time changes
- NOT likely to be the same individuals year-to-year
- Many U.S. Cross-Sectional studies are survey-based products of National Center for Health Statistics (NCHS), division of the Centers for Disease Control & Prevention (CDC)
What are advantages of cross-sectional studies
- Quicker & easier for the RESEARCHER when using data already collected (compared to original data collection)
- Data already collected & deidentified (Exempt IRB approval)
- Less expensive for RESEARCHER than any form of prospective study
- Can be analyzed like a Case-Control or Cohort study (group allocation)
- Useful for estimating PREVALENCE rates
- Useful for answering research questions about a myriad of elements
What are disadvantages of cross-sectional studies?
- Prevalent cases may represent survivors
- Difficult to study diseases of low frequency
- Unable to generate Incidence rates
- Problems in determining temporal relationship of presumed cause & effect
- Due to the fact that exposure & disease histories are taken at the same time
What are Some Examples of Cross-Sectional Surveys from the NCHS? (National Center for Health Statistics)
** Kind of a big one
- National Health and Nutrition Examination Survey (NHANES)
- National Health Interview Survey (NHIS)
- National Ambulatory Medical Care Survey (NAMCS)
- National Hospital Care Survey (NHCS)
- Behavioral Risk Factor Surveillance System (BRFSS)
