the cross-sectional study - university of...

The Cross-Sectional Study:Investigating Prevalence and Association

Ronald A. Thisted

Departments of Health Studies and StatisticsThe University of Chicago

CRTP Track I Seminar, Autumn, 2006

Lecture Objectives

1. Understand the structure of the cross-sectional study design,

2. Understand the advantages and disadvantages of this design,and

3. Understand the kinds of questions that can be addressed usingcross-sectional data.

OutlineA Clinical Scenario: Are Kidney Stones and HypertensionConnected?

The Cross-Sectional StudyThe LogicThe StructurePros and Cons

Conducting a Cross-Sectional StudySteps in building a cross-sectional studyPractical Issues

Discussion of clinical exampleThe data setThe questionsConfounding and interaction

Data analysis issues

Suggested Reading

Are Kidney Stones and Hypertension Connected?

Background

I Women age 34–59 with history of kidney stones more likely toalso have prior diagnosis of hypertension. (Madore, 1998)

I Men age 40–75 with stone history: same direction ofassociation, but weaker. (Madore, 1998b)

I Multiple studies report relationship between BP and stones;wide variability in size of relationship.

The Gap: What is really going on?

Hypotheses:

I Some subgroups may be more susceptible to increased BPwhen stones are present than others.

I Heterogeneity of previous results may be due to differences inrepresentation of high-risk subgroups.

I Association of BP and stones varies with (a) sex and (b) bodysize.

How to test these hypotheses?

I Need to be able to identify and study subgroups of interest.

I Need to avoid selection by stone status or blood pressure (soclinic-based samples are probably out)

I Would like to say something about subgroups as they exist inthe adult population.

Investigated by Gillen, Coe, and Worcester using NHANES III: TheThird National Health and Nutrition Examination Survey.






Suggested Reading

The Logic of Cross-Sectional Studies

I Looks at a “slice” of the population at a single point in time.I If the selected sample is appropriately selected, composition of

the sample reflects that in the population.I Simple random sampleI Cluster sampleI Stratified random samplesI Multi-stage sample

I Perform pre-defined measurements and ascertainments.Often include questionnaire/survey questions

I What can we do with this sample? We can estimateI Prevalence. What fraction of the population has a particular

characteristic?[History of kidney stones? Diagnosed hypertension?

SBP > 140?]I Association. What is the correlation between an “exposure”

and an “outcome?”[Relationship of kidney stone history to HTN history]

The Structure of a Cross-Sectional Study

[People with disease/outcome]

[People without disease/outcome]

Begin Compare

Now

Risk Factor +

Risk Factor -

Risk Factor -

Risk Factor +

Study Population

The Structure of a Cross-Sectional Study, Continued

Begin Compare

[People with risk factor]

[People without risk factor]

Now

Outcome +

Outcome -

Outcome -

Outcome +

Study Population

Pros and Cons

I AdvantagesI Cheaper/easier than longitudinal study: no follow-up required!I Afford good control over the measurement/ascertainment

processI Can maximize completeness of key data (compared to

retrospective study)I Have greater control over precision of estimates in subgroups

(stratified sampling)I Often can be accomplished as secondary data analysis, that is,

data collected by someone else (possibly for another purpose)

Pros and Cons, Continued

I DisadvantagesI In secondary data analysis, no control over purpose, choice, or

method of data collectionI Cannot tell us about causal relationships (only correlation)I Generalizability limited by sampled population, population

definitionI Sample size requirements may be very large (especially when

looking at rare outcomes or exposures)I Potential for selection bias.

Example. “Length-biased sampling” results from the fact thatindividuals with long courses of a disease are more likely to bethe ones identified as prevalent cases than people with coursesof short duration.






Suggested Reading

How to conduct a cross-sectional study

I Identify (and define) population of interest[Adults aged 17–90 with knowledge of stone hx].

I Define outcomes[Previous diagnosis of HTN; SBP].

I Define exposures (for correlational analysis)[Lifetime history of kidney stones]

I Create data collection “instruments”[Surveys, interviews, physical measurement procedures: SBP]Data collection forms are very useful for

I StandardizationI Protocol adherence

I Insure consistent ascertainment[Training of staff]

How to conduct a cross-sectional study, Continued

I Sample from population appropriately[Multistage sample of households].

I Obtain consent, then “measure”I Analyze using appropriate statistical methods

I May require special techniques to account for sampling design.I Statistical adjustment for confounders is usually necessary; we

are (usually) after relationships that remain after adjusting forother factors[Age, race, sex are differentially associated with both stone

formation and blood pressure]

OR. . .Ask NORC.

Practical Issues for the Primary Cross-Sectionalist

I Non response

I Representativeness

I Logistics issues: cluster sampling, household contact

I Defining eligibility (target population)

I Defining measures in advance; respondent burden

I Data collection forms






Suggested Reading

Kidney Stones and BP

Gillen, et al, used NHANES III data (publicly available) to addresstheir research questions.

I Conducted 1988–1994 by NCHS

I National population-based sample

I Noninsitutionalized persons aged > 2 months

I n = 33 994

I Stone history available on n = 20 029.

Answering key questions

Have you ever had a kidney stone?919 answer Yes (4.6%)This is a simple prevalence calculation

BP outcomes:

1. Have you ever been told you have high blood pressure?

2. SBP, DBP, Pulse pressure

Relationship of sex to stone formation:Kidney stone Hx −: 54% womenKidney stone Hx +: 40% women p < 0.001

Odds of stone history 1.73 higher in men than women

Relation of stone formation to hypertension:“SFs were more likely to report a previous diagnosis of

hypertension compared with non-SFs (32.7% vs 24.6%;P = 0.001).”[Univariate relationship]

Confounding: An Issue

I African-Americans less likely to form stones

I African-Americans more likely to have hypertension

I Want to “hold constant” AA effects when exploringstone-HTN effects

I Similarly for other confounders

Regression is one approach to confounders

Regression analysistherapy, and 19% were estimated to have under-gone surgery to remove a stone.

Prior Diagnosis of HypertensionModel-based estimates of the association be-

tween history of nephrolithiasis and self-re-ported diagnosis of hypertension are listed inTable 2. After adjustment for age, race, smokingstatus, history of CVD, and diabetes, a margin-ally significant interaction between stone historyand sex was found (P ! 0.056). In women, it wasestimated that SFs experienced a 69% increase inodds of reporting a prior diagnosis of hyperten-sion (95% CI, 1.33 to 2.17; P " 0.001). In men,odds of reporting a previous hypertension diagno-sis were 20% greater for SFs compared withnon-SFs; however, this association was not statis-tically significant (95% CI, 0.88 to 1.64; P !0.237). No additional interactions between stonehistory and age, race, or diabetes were observed.In addition, subanalyses of SFs did not showsignificant associations between stone treatmentand self-reported hypertension.

SBP, DBP, and Pulse PressureFigures 1 and 2 show estimates of mean differ-

ences in SBP and DBP comparing SFs withnon-SFs. Given potential differences in the asso-

Table 2. Logistic Regression Results ModelingSelf-Reported Diagnosis of Hypertension in the

NHANES III Sample

CovariateAdjusted OddsRatio* (95% CI) P

History of renal stones(yes v no)†

Women 1.69 (1.33-2.17) "0.001Men 1.20 (0.88-1.64) 0.237

Age (/5 y) 1.22 (1.20-1.24) "0.001African-American race 1.48 (1.29-1.69) "0.001BMI (/kg/m2) 1.10 (1.09-1.12) "0.001Ever smoker (yes v no) 1.04 (0.89-1.22) 0.600History of CVD (yes v no) 2.00 (1.66-2.41) "0.001Diabetes (yes v no) 1.51 (1.25-1.82) "0.001

*Adjusted for all covariates listed.†P for interaction between history of renal stones and

sex ! 0.056.

Table 1. Population Characteristics by History of Stone Disease From NHANES III

CharacteristicHistory of RenalStones (n ! 919)

No History of RenalStones (n ! 19,110) P*

Mean age at time of interview (y) 54.1 # 0.7 43.1 # 0.4 "0.001Women (%) 40.4 # 2.4 54.0 # 0.5 "0.001African American (%) 3.8 # 0.5 10.7 # 0.6 "0.001Smoking (ever v never) 60.3 # 2.3 53.8 # 0.8 0.007CVD† (%) 6.2 # 0.8 4.0 # 0.3 0.001Diabetes (%) 6.4 # 1.0 5.0 # 0.2 0.112Mean BMI (kg/m2) 27.7 # 0.3 26.6 # 0.1 0.001Dietary intake (mg/d)

Calcium 816.1 # 23.7 817.6 # 9.9 0.951Sodium 3,504.9 # 92.7 3,414.3 # 35.1 0.372Potassium 2,950.7 # 68.6 2,852.3 # 22.5 0.184Magnesium 307.3 # 7.1 299.5 # 2.5 0.322

Alcohol intake (g/d) 7.7 # 1.3 9.5 # 0.5 0.169Mean SBP (mm Hg) 128.8 # 0.8 127.2 # 0.3 0.049Mean DBP (mm Hg) 77.4 # 0.6 75.7 # 0.3 0.023Pulse pressure (mm Hg) 51.4 # 0.7 51.4 # 0.3 0.977Self-report of hypertension (%) 32.7 # 2.3 24.6 # 0.7 0.001Treatment for stones (%)

Medication 39.4 # 2.7 — —Extracorporeal shock-wave lithotripsy 7.7 # 1.5 — —Surgery to remove stones 18.9 # 2.1 — —

NOTE. Statistics expressed as mean or percentage # SE and weighted to account for the stratified multistage samplingdesign of NHANES III. With the exception of age, all estimates are age adjusted and represent the estimated mean for a50-year-old participant.

*P are age adjusted and account for the stratified sampling design of NHANES III.†CVD is defined as any history of myocardial infarction, stroke, or congestive heart failure.

KIDNEY STONES, HYPERTENSION, AND OBESITY 265

What if degree of association depends on values of anothervariable?

Interaction effectsI SFs have higher BP than non-SFs

I This is stronger for heavier people

I This is more true for women than for men

ciation between stone history and BP, presentedresults are stratified by sex (P ! 0.002 and 0.005for SBP and DBP outcomes for the interactionbetween SF and sex, respectively). The associa-tion between BP (both SBP and DBP) and SFsalso varied with BMI (P ! 0.002 for SBP; P !0.065 for DBP). Point estimates are presented foreach BMI quintile. All estimates were adjustedfor age, race, BMI, smoking status, history ofCVD, and diabetes.

No differences in SBP or DBP were apparentcomparing SFs with non-SFs in nonoverweightindividuals. However, Figs 1 and 2 suggest anincreasing trend in BP differences between SFsand non-SFs with respect to BMI. As shown inFig 1, it was estimated that for women in BMIquintiles 4 and 5, history of nephrolithiasis wasassociated with 7.62–mm Hg (95% CI, 1.04 to14.2; P ! 0.024) and 4.36–mm Hg (95% CI,0.30 to 8.42; P ! 0.036) increases in SBP,

respectively. As shown in Fig 2, it was estimatedthat women SFs in BMI quintiles 4 and 5 hadDBPs 4.67 mm Hg (95% CI, 0.41 to 8.93; P !0.032) and 2.92 mm Hg (95% CI, –0.60 to 6.43;P ! 0.102) higher than those of similar womennon-SFs. Although similar trends in BP differ-ences between SFs and non-SFs were observedin men, the magnitude of these differences wassmaller and not statistically significant. No signifi-cant difference in pulse pressure was observed,regardless of sex or BMI level (data not shown).

DISCUSSION

We compared BP in persons with a history ofnephrolithiasis with those without this historyand found that the relationship varied with re-spect to sex and body size. After adjustment forpotential confounders, we observed that a historyof stone disease was associated with significantlyincreased odds of self-reported hypertension in

Fig 1. Multiple linear regression estimates (and corresponding 95% CIs) of the average difference in SBPcomparing SFs with non-SFs by sex and BMI quintile. All estimates are adjusted for age, race, BMI, smoking status,history of CVD, and diabetes.

GILLEN, COE, AND WORCESTER266






Suggested Reading

Data Analysis/Statistics/Limitations

I Causality cannot be directly assessedI Do stones cause high BP, or does high BP predispose to

stones?I Can view as “hypothesis generating” studiesI Causality implies time course assessmentI No experimental intervention

I Generalizability always an issueI Less so for population-based studiesI Sampling method is key to generalizabilityI Relevance of defined population

[NHANES: noninstitutionalized population]I Particularly important for smaller-scale cross sections: “Cross

section of what?”I Convenience samples are especially problem-prone since it is

hard to know how people “select in” to the population: chartreview, clinic waiting rooms, callers to a help line.

I Confounders

Data Analysis/Statistics/Limitations, Continued

I ConfoundersI Statistical adjustment possible, if confounders are measured!I Regression methods are most common, although stratification

can also be usedI Unmeasured confounders

I A major worry, but need to identifyI Ingenuity may lead to suitable proxiesI Unrecognized confounders = land mine






Suggested Reading

Suggested Reading

1. Kantor J, Bilker WB, Glasser DB, Margolis DJ (2002).“Prevalence of erectile dysfunction and active depression: ananalytic cross-sectional study of general medical patients,”Am J Epidemiol 2002 Dec 1;156(11): 1035–42.

An example of a community-based prevalence and correlation study.

2. Delgado-Rodriquez M, Llorca J (2004). “Bias,” Journal ofEpidemiology and Community Health 2004;58: 635–641.

A useful paper cataloging important sources of bias.Available on the course website:

http://health.bsd.uchicago.edu/thisted/epor/

the cross-sectional study - university of...

Documents