28
some of the effect stems from less exposure to risks related to the work environment.
However, with the full set of controls included in the regression model (see column (c)),
the only effect that remains statistically significant is the estimate for diagnosis group
“other”. We tried to single out a specific diagnosis from this group, without any success.
Thus, all things considered, we cannot disentangle a single cause from the collective
causes that make up the effect on this morbidity outcome. The main problem is that the
occurrence of single diagnoses is a rare event (see column d), which influences the
power of the tests.
Table 8. Effects of the offer to receive occupational pensions on number of days in
inpatient care during the period of 56 to 70 years of age: Subdivided into different
causes for the visit
(a)
(b)
(c)
(d)
Mean number of
days [SD]
Acute myocardial infarction
-0.2787
-0.1865
-0.1361
0.65 [3.30]
(0.2498) (0.2512) (0.3427)
Ischemic heart diseases
0.2065
0.2848
0.2641
1.04 [4.71]
(0.2396) (0.2389) (0.2803)
Mental and behavioral disorders
0.1805
0.6234
0.1065
1.66 [22.05]
(0.6562) (0.6643)
(0.704)
External causes (e.g., injury, poisoning)
-0.8855** -0.7587*
-0.2879
1.04 [7.80]
(0.3171) (0.3151) (0.3881)
Stroke
-0.4532
-0.3332
-0.3714
1.11 [9.71]
(0.5686) (0.5754) (0.6913)
Neoplasms (tumors)
-0.4238† -0.3747
-0.4095
3.68 [16.79]
(0.2452) (0.2449)
(0.289)
Other
-0.5971* -0.4421† -0.3932*
10.19 [38.33]
(0.2565) (0.2504) (0.1818)
County
No
Yes
Yes
Income and education
No
Yes
Yes
“Full interaction”
No
No
Yes
Notes: Estimation is performed with the Poisson maximum likelihood estimator. Robust standard errors in () and
standard deviation (SD) in [ ]: † p<.1; * p<.05; ** p<.01. Each cell represents estimates from a separate model. All
models include a military dummy and dummy for cohort 1938-1939. Control variables are income, education, cohort,
and military. “Full interaction” means interactions between military, income, and education, and interactions between
cohort, income, and education. Column (d) gives the mean and standard deviation in the number of days per
diagnosis group. Number of observations is 19,986. ICD-codes (International Statistical Classification of Diseases
and Related Health Problems) are:
Acute myocardial infarction
: ICD10 I21-I22, ICD9 410;
Alcohol
: an alcohol-
related diagnosis is mentioned among causes of death (as main or contributing diagnosis);
Ischemic heart diseases
except acute myocardial infarction
: ICD10 I20, I23-I25, ICD9 411-414;
Narcotics
: a narcotics-related diagnosis is
mentioned among causes of death (as main or contributing diagnosis);
Mental and behavioral disorders
: ICD10 F00-
F99, ICD9 290-319;
Injury, poisoning and certain other consequences of external causes
: ICD10 S00-T98, ICD9
E810-E999;
Stroke
: ICD10 I63-I64, ICD9 433, 434, 435;
Neoplasms (tumors)
: ICD10 C00-D48, ICD9 140-239.
