Diabetes: Diabetes data

In CARE1: Statistical package for population size estimation in capture-recapture models.

Description

Data set on diabetes in a community in Italy.

Usage

data(Diabetes)

Format

A four lists data with 15 variables.

Details

An epidemiological data with four distinct types of sources, which contains: diabetic clinic and/or family physician visits (1754 cases); hospital discharges (452 cases); prescriptions (1135 cases), and purchases of regent strips and insulin syringes (173 cases). A total of 2069 cases were identified.

References

Bruno G, LaPorte R, Merletti F, Biggeri A, McCarty D, Pagano G. 1994. National diabetes programs. Application of capture-recapture to count diabetes? Diabetes Care 17(6): 548.

Examples

data(Diabetes)
CARE1.print(Diabetes)

Example output

(1) NUMBER OF IDENTIFIED CASES IN EACH LIST: 
  n1   n2   n3   n4 
1754  452 1135  173 

(2) ESTIMATES BASED ON ANY PAIR OF SAMPLES: 
     Petersen Chapman se  cil  ciu
pa12     2353    2351 58 2250 2478
pa13     2185    2185 22 2146 2233
pa14     2264    2261 88 2117 2468
pa23     2060    2057 77 1922 2224
pa24      806     803 47  725  913
pa34     1558    1555 67 1445 1712


Note1: Refer to Seber(1982,pages 59 and 60) for Petersen estimator
       and Chapman estimators as well as s.e formula.
Note2: A log-transformation is used is used to obtain the confidence
       interval so that the lower limit is always greater than the
       number of ascertained. Refer to Chao(1987,Biometrics,43,783-791)
       for the construction of the confidence interval.

(3) SAMPLE COVERAGE APPROACH: 
          M       D  Chat  est se  cil  ciu
Nhat-0 2069 1825.25 0.803 2272 27 2226 2331
Nhat   2069 1825.25 0.803 2609 85 2467 2802
Nhat-1 2069 1825.25 0.803 2458 46 2378 2559

Parameter estimates: 
         u1   u2   u3   u4   r12  r13  r23  r14  r24  r34
Nhat-0 0.77 0.20 0.50 0.08 -0.03 0.04 0.10 0.00 1.82 0.46
Nhat   0.67 0.17 0.44 0.07  0.11 0.19 0.27 0.15 2.24 0.67
Nhat-1 0.71 0.18 0.46 0.07  0.04 0.12 0.19 0.09 2.05 0.58


Definitions for the sample coverage approach:
M: number of individuals ascertained in at least one list.
D: the average of the number of invididuals listed in the combination 
   of any two lists omitting the other one.
C^: sample coverage estimate, see Equation (14) of Chao and Tsay(1998).
    est: population size estimate.
se: estimated standard error of the population size estimation based on
    bootstrap replications. 
cil: 95% confidence interval lower limit(using a log-transformation).   
ciu: 95% confidence interval upper limit(using a log-transformation).
Nhat: Population size estimate for sufficiently high sample coverage 
      cases, see Equation (20) of Chao and Tsay (1998).
Nhat-1: One-step population size estimate for low sample coverage cases;
        see Equation (2.21) of Chao et al. (1996). This estimator is 
        suggested for use when the estimated se of Nhat is relatively large.
u1,u2,u3: estimated mean probabilities depending on the estimate of N.
r12,r13,r23 etc.: estimated coefficient of covariation(CCV) depending on the 
                  estimate of N.
 Warning messages:
1: In ni/nhat :
  Recycling array of length 1 in vector-array arithmetic is deprecated.
  Use c() or as.vector() instead.

2: In ni/nhat :
  Recycling array of length 1 in vector-array arithmetic is deprecated.
  Use c() or as.vector() instead.

3: In ni/nhat :
  Recycling array of length 1 in vector-array arithmetic is deprecated.
  Use c() or as.vector() instead.

CARE1 documentation built on May 2, 2019, 4:06 p.m.