INF 397C
Fall 2010
Student Number _______________
CALCULATIONS (30 points):
Please use pencil, and put all of your answers on this paper. You must do all of the questions,
and show all appropriate work. Draw a circle around each answer unless otherwise instructed.
1. (22 points)
A sample of users of a particular information retrieval system retrieved this
number of documents in response to their first queries about art historical
questions:
14, 13, 0, 13, 8, 13, 8, 13, 8.
(a) In the space above, generate the full frequency distribution of the sample using class
examples as models. Do not circle the frequency distribution. (4 points)
(b) What is the variable of interest? (1 point)
(c) What is the unit of analysis? (1 point)
(d) What is the mean of the distribution? (1 point)
(e) What is the standard deviation of the distribution? (2 points)
(f) Generate a 95% confidence interval on µ. Do not circle the CI on µ. (5 points)
(g) Generate a stem plot for this dataset, including the six-figure summary. Do not circle the plot
or the summary. (8 points)
2.
(8 points)
ND (100, 15)
(a) How many standard deviations from the mean is a score of 111 on this test? (2 points)
(b) Would the percentile rank for the observation 111 be greater or less than the median of the
distribution? Why? Do not circle your response. (2 points)
(c) What is the percentile rank of the observation 111 in this distribution? (4 points)
INF 397C
Fall 2010
Student Number _______________
CONCEPTS (30 points): use pen, and put your answers on this paper in the space provided.
I. (5 points) Please define five (5) of the following terms (1 point each).
Positivism
Confidence intervals on µ
Statistical inference
Standard deviation
External validity
Oral history
Data quality
II. (4 points)
Indicate if the following four (4) statements are true (T) or false (F) by circling
the correct letter. (1 point each):
a. In normal populations, the median is often larger than the mean.
T
F
b. Random sampling and probability theory help us generalize
from samples to populations.
T
F
c. N and n tell us how many standard deviations x is from µ.
T
F
d. Qualitative research is empirical.
T
F
III. (6 points)
Discuss the relationship(s) between the terms in three (3) of the following pairs (2
points each):
a. statistics and parameters
b. H0 and hypothesis testing
c. reliability and validity
d. Q1 and Q3
IV. (15 points) Respond to three (3) of the following questions or statements in
the space provided. (5 points each)
a.
The mean is a non-resistant measure of central tendency. What implications does this
statement have for the standard deviation and inferential statistical techniques that rely on
the mean?
INF 397C
Fall 2010
PLEASE DO NOT WRITE BELOW THIS LINE
Student Number _______________
b.
Why do constructivist researchers use member checking and peer debriefing?
c.
Why does ethical research with people demand informed consent?
d. How do stem plots contribute to our understanding of a distribution?
PLEASE DO NOT WRITE BELOW THIS LINE