Classroom Response Systems at Duke

Tools for Learning
Classroom Response
Systems at Duke
Mine Çetinkaya-Rundel
Karen Murphy
Statistical Science
Psychology and Neuroscience
Sta 101
100 - 120 students
i>clicker2
- multiple choice &
numerical answer
questions
(participation)
- readiness
assessments
(accuracy)
- data collection
look familiar?
source: Google images
engaging
lectures
“I like [the clicker
questions] -- they
keep your mind from
wandering too far off
during lecture.”
active
learning
peer
instruction
“[...] clicker questions
really do force you to
work and understand
what is going on.”
“I like [...] the opportunity
to discuss the answers
with our classmates after
submitting the answers.”
immediate
feedback
“[the clicker questions]
enable us to see where
were at/figure out if we
need to study or work
harder to catch up.”
anonymous
participation
“[I like being] able to
participate without other
people seeing what I
answered.”
source: Google images
active
learning
Difference of two proportions
HT for comparing proportions
Difference of two proportions
HT for comparing proportions
Clicker question
Clicker question
Which of the following is the correct set of hypotheses for testing if the
proportion of all Duke students who would be bothered a great deal
by the melting of the northern ice cap differs from the proportion of all
Americans who do?
Which of the following is the correct set of hypotheses for testing if the
proportion of all Duke students who would be bothered a great deal
by the melting of the northern ice cap differs from the proportion of all
Americans who do?
(a) H0 : pDuke = pUS
(a) H0 : pDuke = pUS
(b) H0 : p̂Duke = p̂US
(b) H0 : p̂Duke = p̂US
(d) H0 : pDuke = pUS
(d) H0 : pDuke = pUS
HA : pDuke , pUS
HA : pDuke , pUS
HA : p̂Duke , p̂US
(c) H0 : pDuke pUS = 0
HA : pDuke pUS , 0
HA : p̂Duke , p̂US
(c) H0 : pDuke pUS = 0
HA : pDuke pUS , 0
HA : pDuke < pUS
HA : pDuke < pUS
Both (a) and (c) are correct.
Statistics 101 (Mine Çetinkaya-Rundel)
U5 - L1: Inf. for prop.s - theoretical
March 19, 2013
22 / 29
Statistics 101 (Mine Çetinkaya-Rundel)
U5 - L1: Inf. for prop.s - theoretical
March 19, 2013
22 / 29
source: Google images
peer
instruction
1
Review
Bayesian inference
Design
of studies
Clicker question
Exploratory
data
analysis
Which of the following is true?
Inference
Probability
Frequentist inference
(CLT & simulation)
numerical
one mean & median
two means & medians
many means
categorical
one proportion
two proportions
many proportions
Modeling (numerical response)
1 explanatory
many explanatory
2
(a) If the sample size is large enough, conclusions can be generalized to the
population.
(b) If subjects are randomly assigned to treatments, conclusions can be generalized
to the population.
(c) Blocking in experiments serves a similar purpose as stratifying in observational
studies.
(d) Representative samples allow us to make causal conclusions.
(e) Statistical inference requires normal distribution of the response variable.
Statistics 101 (Mine Çetinkaya-Rundel)
Final Review
April 23, 2013
3 / 19
source: Google images
elf‐Paced Polling Student Guide lling Student Guide olling Student Guide tiple choice (A‐E) questions using the i>clicker2 remote: olling Student Guide tiple choice (A‐E) questions using the i>clicker2 remote: E) questions using the i>clicker2 remote: E) questions using the i>clicker2 remote: E) questions using the i>clicker2 remote: ange button 4. ange button 4. Press the A‐E buttons to Press the A‐E buttons to he i>clicker2 select your answer for 4. Press the A‐E buttons to he i>clicker2 select your answer for 4. Press the A‐E buttons to 4. select your answer for Press the A‐E buttons to question 1. question 1. select your answer for select your answer for question 1. question 1. question 1. self paced
polling
5. 5. 5. 1
ppears with ppears with und it und it he question he question 6. 6. 6. 2
5. Your answer choice and a 5. Your answer choice and a checkmark will appear Your answer choice and a checkmark will appear Your answer choice and a Your answer choice and a on the screen, indicating checkmark will appear on the screen, indicating checkmark will appear checkmark will appear that your answer for on the screen, indicating that your answer for on the screen, indicating on the screen, indicating question 1 was received. that your answer for question 1 was received. that your answer for that your answer for question 1 was received. question 1 was received. question 1 was received. Recommended: Press Recommended: Press SEND to confirm your Recommended: Press SEND to confirm your Recommended: Press Recommended: Press answer choice. SEND to confirm your answer choice. SEND to confirm your SEND to confirm your answer choice. answer choice. answer choice. 6. 6. Press the UP button on Press the UP button on the cross navigation to Press the UP button on the cross navigation to Press the UP button on Press the UP button on advance to the next the cross navigation to advance to the next the cross navigation to the cross navigation to question. advance to the next question. advance to the next advance to the next question. question. question. Continue answering Continue answering questions until you reach Continue answering questions until you reach Continue answering Continue answering the final question and questions until you reach the final question and questions until you reach questions until you reach can’t advance further. the final question and can’t advance further. the final question and the final question and can’t advance further. can’t advance further. Use the UP and DOWN can’t advance further. Use the UP and DOWN buttons to review your Use the UP and DOWN buttons to review your Use the UP and DOWN Use the UP and DOWN answers. Confirm that buttons to review your answers. Confirm that buttons to review your buttons to review your you see a checkmark next answers. Confirm that 5
ed polling ed polling ears. ears. Readiness Assessment
Unit 2
1. Which of the following states that the proportion of occurrences with a particular outcome converges to the
probability of that outcome?
(a) Bayes’ theorem
(b) General addition rule
(c) Law of large numbers
2. Shown below are four Venn diagrams. In which of the diagrams does the shaded area represent
A and B but not C?
4
Dr. Çetinkaya-Rundel
(d) Law of averages
ue ue esh” button resh” button at you are in at you are in olling mode. olling mode. 3
Sta 101: Data Analysis and Statistical Inference
(a)
(b)
(c)
(d)
3. Which of the following is false about probability distributions?
(a) Each probability should be greater than or equal to 0.
(b) The outcomes listed must be independent.
(c) Each probability should be less than or equal to 1.
(d) The probabilities must total 1.
4. Last semester, out of 170 students taking Sta 101, 71 students were social sciences majors (primary major),
53 students were premed, and 6 were both premed and social sciences majors. What is the probability that
a randomly chosen student is premed, given that s/he is a social sciences major?
(a)
6
170
(c)
6
53
(b)
71+53 6
170
(d)
6
71
5. Which of the following is false?
(a) If two events (both with probability greater than 0) are mutually exclusive, they could be independent.
(b) When computing the probability that a card drawn randomly from a standard deck is either a Jack or
a 4, you can use the addition rule.
(c) If two events (both with probability greater than 0) are mutually exclusive, they are not necessarily
complements.
(d) If the probabilities of two events add up to 1, they are complements.
source: Google images
motion and gender?
data
collection
Gender
Male
Female
Total
Promotion
Promoted Not Promoted
21
3
14
10
35
13
Case study: Gender discrimination
Total
24
24
48
Testing via simulation
Simulation setup
1
Statistics 101
We’ll let a face card represent not promoted and a non-face card
represent a promoted. Consider aces as face cards.
Set aside the jokers.
Take out 3 aces ! there are exactly 13 face cards left in the deck
(face cards: A, K, Q, J).
Take out a number card ! there are exactly 35 number
(non-face) cards
left
in thevia
deck
(number cards: 2-10). January 22, 2013
(Mine Çetinkaya-Rundel)
U1 - L3:
Inference
simulaion
2
Shuffle the cards and deal them intro two groups of size 24,
representing males and females.
3
Count and record how many files in each group are promoted
(number cards).
4
Calculate the proportion of promoted files in each group and take
the difference (male - female).
5
Use your clicker to submit your result.
Statistics 101 (Mine Çetinkaya-Rundel)
U1 - L3: Inference via simulaion
January 22, 2013
13 / 17
source: Google images
5
PROs:
- easily track student
responses for grading
(compatible with
Sakai roster)
- self paced polling
- no internet access
on gadget
CONs:
- “i forgot my clicker”
- numeric response
capabilities not great
- hefty price for item
that has no other use
source: Google images
best
practices
grading
- participation only, not
for accuracy
- 5% - 10% of overall
grade
- automatically drop few
days of absences/forgot
clickers/etc.
peer
instruction
- spend time going over
the question, even if on
the second try majority
of the students got it
right
cost
- Google Doc where
outgoing students can
leave their information if
they want to resell their
clickers the following
semester
source: Google images