Understanding and Using

NAMCS and NHAMCS Data

Data Tools and Basic Programming
Techniques

Donald Cherry
Ambulatory and Hospital Care Statistics Branch
Division of Health Care Statistics

U.S. DEPARTMENT OF HEALTH AND HUMAN SERVICES

Centers for Disease Control and Prevention
National Center for Health Statistics

1
 Overview
 Some important features of NAMCS & NHAMCS
 File structure
 SETS
 Exercises using SAS Proc Surveyfreq/Proc Surveymeans,
SUDAAN, STATA
 Downloading data & creating a SAS dataset
 Simple frequencies with/without standard errors

 Creating a new variable-Asthma

 Visit rates for asthma-male/female

 Total number of digestive write-in

procedures
 Time spent with physician

 Considerations
 Summary

2
NAMCS and NHAMCS
 National Ambulatory Medical Care
Survey (NAMCS)
 Visits to nonfederal, office-based
physicians
 CHC’s sampled beginning in 2006

 National Hospital Ambulatory Medical

Care Survey (NHAMCS)
 Visits to hospital outpatient and
emergency departments

3
NAMCS Sample Design
 Three stage design
 112 PSUs

 Physician practices within PSUs

 Patient visits within practices

 One-week reporting period

 About 30 visits per doctor are typically sampled
 For 2006—3,350 doctors sampled
 104 CHC’s sampled & physician visits included in
sample
 Total visits 29,392

4
Scope of the NAMCS
 Basic unit of sampling is the
physician-patient visit
 In scope visits:
 Must occur in physician’s office

 Must be for medical purposes

 Administrative visits not sampled

 House calls, emails, phone calls

not sampled
5
Scope of the NAMCS (cont.)
 Physicians must be:
 Classified by AMA or AOA as primarily
engaged in office-based patient care
 nonfederally employed
 not in anesthesiology, radiology, or
pathology
 64 percent unweighted response rate in
2006
 CHC’s are Federally Qualified or “look
alike”

6
NHAMCS Sample Design
 Multistage probability design
 First stage sample of 112 PSUs
 Hospitals within PSUs
 Clinics within OPDs, Emergency
Service Area (ESA) within EDs
 Patient visits within clinics, ESAs
 4-week reporting period
 382 hospitals sampled in 2006; 35,849
ED visits and 35,105 OPD visits
7
Scope of the NHAMCS
 Basic unit of sampling is patient visit
 Emergency and outpatient departments
of noninstitutional general and short-
stay hospitals
 Not Federal, military, or Veterans
Administration facilities
 Located in 50 states and D.C.

8
 Sample Weight

 Each NAMCS record contains a

single weight, which we call Patient
Visit Weight
 Same is true for OPD records and ED
records
 This weight is used for both visits and
drug/procedure mentions

9
 Data Items
 Patient characteristics
 Age, sex, race, ethnicity

 Visit characteristics
 Source of payment, continuity of care,
reason for visit, diagnosis, treatment
 Provider characteristics
 Physician specialty, hospital
ownership…
 MULTUM drug characteristics added in
2006

10
 Coding Systems Used

 Reason for Visit Classification (NCHS)

 ICD-9-CM for diagnoses, causes of
injury and procedures
 Drug Classification System-MULTUM

11
 File Structure
 Download data and layout from
website
http://www.cdc.gov/nchs/about/major/ahcd/ahcd1.
htm
 Flat ASCII files for each setting and
year:
NAMCS: 1973-2006
NHAMCS: 1992-2006
 STATA files on Web:
NAMCS: 2003-2005
NHAMCS: 2003-2005
12
 Creating a usable STATA dataset
 Two options:
1) Use the self-extracting file in STATA
folder to open a complete dataset
for the 2003-2005 NAMCS,
NHAMCS-ED, & NHAMCS-OPD
2) Use the DO file (*.do) and the
dictionary file (*.dct) along with the
flat data file (*.exe) to create a
dataset
3) StatTransfer

13
 Organizational structure-NAMCS data
Provider
provider info
practice info
geographic info

Write-in scope procedure 1

Visit
Write-in scope procedure 2
patient & visit info
treatment & outcome info
medications Other test/service 1

Other test/service 2
Medications 1-8 Primary reason for Visit Primary diagnosis

Surgical procedure 1

Other Reason for Visit

Surgical procedure 2
MULTUM Categories Other diagnosis

Other Reason for Visit Non-surgical procedure 1

Other diagnosis Non-surgical procedure14

2
SETS-Statistical Export and
Tabulation System

15
 Hands-on Exercises
STATA Users SAS/SUDAAN Users
 Double-click: My  Double-click: My
Computer\Local Disk Computer\Local Disk
C:\DUC_08 C:\DUC_08
 Open STATA  Double-click: Final Exercises
 In the command window
type:
 Set mem 1000m

 Set matsize 5000

 Under the “File” icon-double-

click namcs05.dta
 Under “New Do File Editor”-
double-click: STATA
exercises.do

16
 Visit rate estimates
Female population=800 Calculation* New variable
Phycode Sex Patwt (Patwt/Pop)*10 Sexwt
0

1401 1 100 (100/800)*100 12.5

1820 1 300 (300/800)*100 37.5

1001 1 50 (50/800)*100 6.25

500 1 120 (120/800)*100 15

Sample Visits=570 71.25 visits per

size=4 100 persons

17
*Note: Rate=est/pop=Σ patwt/pop=1/pop*Σ patwt.
Calculating Total Number of Write-in Procedures
Record Proc1 Proc2 Proc3 Proc4 Proc5 Proc6 Proc7 Proc8 Totproc

1 1911 0000 0000 0000 0000 0000 0000 0000 1

2 2182 2186 0000 0000 0000 0000 0000 0000 2

3 5490 0000 0000 0000 0000 0000 0000 0000 1

4 0000 0000 0000 0000 0000 0000 0000 0000 0

5 8192 0000 0000 0000 0000 0000 0000 8200 2

18
Note: 0000=No procedure recorded.
Data Considerations

19
 NAMCS vs. NHAMCS

 Consider what types of settings are best

for a particular analysis
 Persons of color are more likely to
visit OPD’s and ED’s than physician
offices
 Persons in some age groups make
disproportionately larger shares of
visits to ED’s than offices and OPD’s

20
 Procedures

Program Categorical Continuous

Variables Variables
SAS PROC PROC
SURVEYFREQ SURVEYMEANS

STATA SVY: TAB SVY: MEAN

SUDAAN PROC CROSSTAB PROC

DESCRIPT

21
How Good are the Estimates?

 Depends … In general, OPD estimates

tend to be somewhat less reliable than
NAMCS and ED.
 Since 1999, our Advance Data reports
include standard errors in every table so
it is easy to compute confidence
intervals around the estimates.

22
 RSE improves incrementally with
the number of years combined
 RSE = SE/x

 RSE for percent of visits by persons

less than 21 years of age with
diabetes
 1999 RSE = .08/.18 = .44 (44%)
 1998 & 1999 RSE = .06/.18 = .33 (33%)
 1998, 1999, & 2000 RSE = .05/.21 = .24
(24%)
23
Some User Considerations

 NAMCS/NHAMCS sample visits, not

patients
 No estimates of incidence or
prevalence
 No state-level estimates
 May capture different types of care for
solo vs. group practice physicians
 Data is only as good as what is
documented in the medical record

24
If nothing else, remember…The
Public Use Data File
Documentation is YOUR FRIEND!
 Each booklet includes:
 A description of the survey

 Record format

 Marginal data (summaries)

 Various definitions

 Reason for Visit classification codes

 Medication & generic names

 Therapeutic classes

25