RBH-1 Student name: ___________________
Day 10
In exercises 1-3 you can find real-life examples of how researchers use statistical
techniques to describe and analyze their work.
Exercise 1
Read the abstract below and answer the following questions:
1. What statistical methods were used and why?
2. What do the results mean?
Abstract
Diggle, L. and Deeks, J. (2000). Effect of needle length on incidence of local reactions
to routine immunisation in infants aged 4 months: randomised controlled trial. BMJ
321: 931–933.
Objective: To compare rates of local reactions associated with two needle sizes used
to administer routine immunisations to infants.
Design: Randomised controlled trial.
Setting: Routine immunisation clinics in eight general practices in Buckinghamshire.
Participants: Healthy infants attending for third primary immunisation due at 16
weeks of age: 119 infants were recruited, and 110 diary cards were analysed.
Interventions: Immunisation with 25 gauge, 16 mm, orange hub needle or 23
gauge, 25 mm,
blue hub needle.
Main outcome measures: Parental recordings of redness, swelling, and tenderness
for three days after immunisation.
Results: Shown in Table 9.
Exercise 2
Read the abstract below and answer the following questions:
1. What statistical methods were used and why?
2. What do the results mean?
Abstract
Priest, P., Yudkin, P., McNulty, C. and Mant, D. (2001). Antibacterial prescribing and
antibacterial resistance in English general practice: cross sectional study. BMJ 323:
1037–1041.
Objective: To quantify the relation between community based antibacterial prescribing
and antibacterial resistance in community acquired disease.
Design: Cross sectional study of antibacterial prescribing and antibacterial resistance of
routine isolates within individual practices and primary care groups.
Setting: 405 general practices in south west and north west England.
Main outcome measures: Correlation between antibacterial prescribing and resistance
for urinary coliforms.
Results: Antibacterial resistance in urinary coliform isolates is common but the
correlation with prescribing rates was relatively low for individual practices (ampicillin
and amoxicillin r=0.20, P=0.001).
Exercise 3
Read carefully and interpret the results.
1. Would you recommend Bioflex magnets to your patients suffering from post-polio
pain syndrome?
Background
Magnetic fields have been shown to have an effect on living tissue as early as the 1930's.
Plants have been shown to have an improved growth rate when raised in a magnetic
field1. More recently, doctors and physical therapists have used either static or fluctuating
magnetic fields to aid in pain management, most commonly for broken bones. In the
case study presented here, Carlos Vallbona1 and his colleagues sought to answer the
question "Can the chronic pain experienced by postpolio patients be relieved by magnetic
fields applied directly over an identified pain trigger point?"
Experimental Design
Summary
Patients experiencing post-polio pain syndrome were recruited. Half of the patients were
treated with an active magnetic device and half were treated with an inactive device. All
patients rated their pain before and after application of the device. To simplify the
presentaton, only the rating after the treatment will be analyzed here. In the raw data,
this rating is referred to as "Score_2." The treatment condition is indicated by the
variable "Active." Subjects receiving treatment with the active magnet have a "1" on this
variable; subjects treated with the inactive placebo have a "2."
Details
The experimenters recruited 50 patients who not only had post-polio syndrome but also
reported muscular or arthritic pain. These patients had significant pain for at least 4
weeks and had not taken any pain killers or anti-inflamatories for at least 3 hours before
the study. The subjects all had a trigger point or painful region and had a body weight of
less than 140% of the predicted weight for their age and height, and had a trigger point
or circumscribed painful area.
The magnets and placebos (described under Materials) were supplied in equal numbers
from Bioflex. Each magnet or placebo was placed in number coded envelopes and
delivered according to its shape. The code for placebos and magnets was not broken until
the end of the study.
One site of reported pain was evaluated and a trigger point for this pain was found by
palpitation. The patient was asked to subjectively grade pain at the trigger point under
palpitation on a scale from 0 to 10 (0 is the least pain, increasing to 10).
Following the initial pain assessment, an envelope containing a device was randomly
selected from the box containing active and inactive devices. This device was applied to
the pain area for 45 minutes and then removed. The patient then evaluated his or her
pain again at the region or trigger point. This second pain rating is the score analyzed
here.
1
Mericle, R. P. et al. "Plant Growth Responses". in : Biological effects of magnetic fields. New York: Plenium
Press 1964. p183-195.
Vallbona, Carlos et. al., "Response of pain to static Magnetic fields in postpolio patients, a double blind Pilot
study" Archives of Physical Medicine and Rehabilitation. (1997) Vol 78, American congress of rehabilitation
medicine, p 1200-1203.
Materials
The magnets used in the study were Bioflex magnets. The magnetic field consists of
concentrically arranged circles of alternating magnetic polarity. Seventy active devices
identical inactive devices were used.
Results
Researchers got the following results describing the difference in pain rating between the
control and the treatment group.
Descriptive Statistics
Result of the statistical test
Test
statistics
-5.264
df
P-value
48
< 0.001
Mean
Difference
(treatmentcontrol)
-4.049
95% Confidence Interval of
the Mean Difference
Lower
-5.596
Upper
-2.503
Exercise 4
J.C. is a 57-year-old plump asymptomatic postmenopausal female with a family history
of coronary artery disease. J.C. has familial hypercholesterolemia (treated with
simvastatin) but is otherwise a healthy and very active woman. Her friend is taking
conjugated estrogens–medroxyprogesterone acetate (Prempro), and J.C. wonders
whether she should start on it to increase her energy. Following your review of the article
entitled, "Risks and Benefits of Estrogen Plus Progestin in Healthy Postmenopausal
Women: Principal Results from the Women's Health Initiative Randomized, Controlled
Trial," by the Writing Group for the Women's Health Initiative (WHI) Investigators and
published in the Journal of the American Medical Association (JAMA) in 2002, you
estimate the cardiovascular protection effect of Prempro. Using the following table, select
the correct absolute risk reduction and corresponding number needed to treat (NNT).
a. The absolute risk reduction for
translates to an (NNT) of 400
b. The absolute risk reduction for
to an NNT of 233
c. The absolute risk reduction for
of 5
d. The absolute risk reduction for
NNT of 33
hip fracture in this study is 0.25%, which
coronary artery disease is 0.43%, which translates
all fractures is 2.09%, which translates to an NNT
colorectal cancer is 0.3%, which translates to an