Supplement to Chapter on Propensity Scoring
Presentations
Assignment
Question 1: The
following data provide the length of stay of patients seen by Dr. Smith
(Variable Dr Smith=1) and his peer group (variable Dr. Smith = 0).
Answer following questions:
-
Balance the data by propensity to seek care from Dr. Smith.
Graphically show that the weighting procedure results in same number
of patients treated by Dr. Smith or his peer.
-
Report the unconfounded impact of Dr. Smith on length of stay. Data► Kanfer's
Teach One► Solution► Kanfer
and Lavanya's Answer►
Question 2: The
following data provide the survival among cancer patients. The
data provides 35 common comorbidities for patients who have or don't
have stomach cancer. Use both logistic and ordinary regression to
analyze these data and report the difference of the findings, in
particular:
-
Using logistic regression, calculate the propensity to have cancer.
-
Group the diagnoses using SQL. Within the naturally occurring
groups of diagnoses, calculate probability of cancer. Calculate the
logit of the probability. Regress the logit function on the
diagnoses using ordinary regression. SQL►
Report how the coefficients for the comorbidities of stomach cancer.
How do these coefficients change across the two methods? Data► Answer
by Shukri►
Question 3: The
objective of this analysis is to find response to antidepressants.
You can select one of the antidepressants.
-
These data come from STAR*D experiment conducted
by National Institute of Medicine. Read
about the study protocol. Protocol►
-
Download data. Use instructor's last name as password. Data►
- The
data are report bi-weekly or monthly. There are 22,254 records for
about 4,000 patients. Organize the data so there is one row for each
patient. SQL►
-
Focus: The
enclosed data report on citalopram, bupropion, mirzapine,
buspirone, lithium, nortriptyline, sertraline, thyroid,
tranylclypromine, and venlafaxine. Please focus the analysis on
only one of the antidepressants or a combination of two
antidepressants taken simultaneously. For the time being
ignore the dose of the medication.
-
Exclusions: Patients who did not receive
bupropion are assumed to have received the alternative
antidepressant. The unit of the analysis is antidepressant
trials and not necessary unique person. So the ID that should
be used is the combination of patient ID and Concat_Levels.
-
Treatment: If
the patient has taken the antidepressant at any time during the
study period, then mark it as 1, otherwise 0. Notice that some
patients have taken the medication and others have not. Within
the combination of ID and Concat_levels look for any occasion of
use of bupropion.
-
Covariates: For
the covariates, include gender, risk of suicide, heart,
vascular, haematopoietic, eyes ears nose throat larynx,
gastrointestinal, renal, genitourinary, musculoskeletal
Integument, neurological, psychiatric illness, respiratory,
liver, endocrine, alcohol, amphetamine, cannibis use, opioid
use, panic, specific phobia, social phobia, OCD, PTSD, anxiety,
borderline personality, dependent personality, antisocial
personality, paranoid personality, personality disorder,
anorexia, bulimia, and cocaine use. If the covariate is ever
present assume that it is present. Exclude covariates that are
not present for any of the patients. Combine covariates that
occur occasionally.
Outcome: The
medication is considered to have caused the remission, if while
on the medication, the patient is discharged to follow-up
portion of the study, then "Treatment_plan_equal_3" is set to
1. Use "Treatment_Plan_Equal_3" and not "Remission" variable as
an indication of effectiveness of the antidepressant, since the
remission variable does not indicate that the clinician was in
agreement that the patients symptoms are well managed.
Balance the data to remove the effects of covariates. Show visually
that you have successfully balanced the data. Use the following
steps to accomplish this:
-
Calculate Propensity Score: Calculate the
propensity of taking the antidepressant. Regress taking of the
antidepressant on the covariates.
-
Weights: Calculate inverse propensity weights
-
Verify Balance: Verify
that weighted regression removes the effects of all covariates.
Regress the antidepressants on the covariates and verify that
none have a statistically significant effect on selection of the
antidepressant. Visually show that the data have been
balanced.
-
Estimate Impact on Response: Regress
response to the antidepressant on the covariates and taking the
antidepressant.
Describe how well the model was balanced and how well the impact of
antidepressant was estimated.
Solutions can be obtained
using different software. Answer►
Question 4:
The following problem was first created by Morgan and Harding and we
have adjusted it to fit within health care. In this example, the outcome
are length of stay in the hospital, the treatment is the clinician/his
peer group and the strata are a mix of medical history and demographic
variables that account for the pattern of self-selection into treatment.
This mix have been divided into 3 strata: low, medium and high
risk. What is the impact of clinician on length of stay, after removing
confounding associated with severity of the patients' illness?
Strata |
Probability |
Total |
|
Strata |
Length of Stay |
Net Impact |
Untreated |
Treated |
Untreated |
Treated |
Low |
0.36 |
0.08 |
0.44 |
Low |
2 |
4 |
2 |
Med |
0.12 |
0.12 |
0.24 |
Med |
6 |
8 |
2 |
High |
0.12 |
0.20 |
0.32 |
High |
10 |
14 |
4 |
Total |
0.60 |
0.40 |
1 |
|
Solution by Morgan and Harding Read► Answer►
Question 5:
The following data have been taken from nurses rounding in a facility.
The time they spent with patients has been recorded. In addition,
several characteristics of the patients have also been recorded and
standardized. Do any of the nurses have a significant impact on
overall satisfaction in the unit? Data► Yamani's
answer►
Question 6: In
a nursing home, data were collected on residents' survival and
disabilities. The data are listed in the following order: ID, age,
gender (M for male, F for Female), number of assessments completed on
the person, number of days followed, days since first assessment, days
to last assessment, unable to eat, unable to transfer, unable to groom,
unable to toilet, unable to bathe, unable to walk, unable to dress,
unable to bowel, unable to urine, dead (1) or alive (0), and assessment
number. Predict
from the patient's assessments (i.e. their age and disabilities at time
of assessment) if the patient is likely to die and should be admitted to
the hospice program. Data►
More
For additional
information (not part of the required reading), please see the following
links:
- A
practical guide to propensity scoring using R Read►
-
Guide to propensity scoring Read►
|