Cross Sectional Study Design
The cross sectional study design
The important elements of a cross sectional study
- Across a specified population
- In a given geographical location(s)
- In a specified time period
When do we do a cross sectional study?
We do a cross sectional study when
- We want to estimate the prevalence of the outcome or condition of interest in a given population in a given period of time.
Examples:
a) What is the prevalence of gestational diabetes in population of pregnant women in the state of Karnataka in 2011?
b) What is the prevalence of cardiac diseases in an urban population of pregnant women aged 30 years and younger in the state of Andhra Pradesh in 2011?
c) What is the prevalence of low birth weight babies among elderly pregnant women who delivered live babies at an advanced tertiary care center in the state of Andhra Pradesh in 2011?
STOP. TAKE A MOMENT TO CONSIDER YOUR RESEARCH QUESTION.
IS A CROSS SECTIONAL DESIGN THE MOST APPROPRIATE DESIGN?
Is your research question focused on determining the proportion of subjects with a certain condition?
Basic components of a cross sectional study
| ITEM | COMMENTS |
| Define the geographical location(s) of the study | Where is the study conducted? An example will be “The study was conducted in Guntur, a semi rural district of the state of Andhra Pradesh in India” |
| Define the time period of the study | When is the study conducted? Describe the relevant dates including periods of recruitment, exposure, follow up and data collection |
| Define the population of the study | How is the population identified? |
| Describe the strategies used to identify the population for the study | From outpatient clinics, hospitals, inpatient wards, labour rooms, communities etc |
| What sampling strategy is used? | Random selection of subjects, convenience selection etc |
| What is the sample frame? | A community, A village, District, etc |
| Describe the strategies used to identify the study subjects | Identify subjects for the study from within the population of interest |
| What sampling strategy, if any, is used? | Random sampling, cluster sampling, systematic sampling |
| What are the inclusion criteria? | Define each inclusion criteria |
| What are the exclusion criteria? | Define each exclusion criteria |
| Has informed consent been obtained? | Procedure to collect written informed consent, who collects the consent and when |
| Is informed consent verbal or written? | Can be verbal or written. Written is more preferred |
| Define the variables of interest | |
| How are the variables defined? | Describe all variables- exposure, disease, predictor, outcomes, potential confounders and effect modifiers. Give diagnostic criteria if applicable |
| How are the variables ascertained? | Describe how the variables are measured and ascertained |
| Who and how many people ascertain the variables? | How are procedures and observers standardized |
| Describe comparability of assessment methods or assessors if there are more than 1 | Describe in detail |
| Describe standardization procedures for assessment methods | Describe in detail |
| Describe standardization training for assessors | Describe in detail |
| Describe potential sources of bias | Describe sources of bias and steps to minimize bias |
| Describe the study size | |
| Assumptions used to estimate the sample size | |
| The sample size including specific subgroup sample size if any | Describe the inputs and assumptions used to estimate the sample size |
| Describe statistical analysis | What software will be used, what variables will be compare, what tests will be used |
| How are missing data dealt with | |
| Describe groupings of quantitative variables with justification | |
| Describe all statistical methods including sub group analysis and interactions, sensitivity analyses, and adjustments for sampling strategy | |
| How are confounders dealt with? | |
| Mention software package used for analysis | |
| Ethics committee and IRB approval | Ethics Committee Approval or IRB approval before study starts |
