Study Questions:
OU, variable Frequency distribution- descriptive statistics
1) Construct a table presenting a frequency distribution which is trimodal and symmetric. Also
give the relative cumulative frequencies for the same outcomes.
2)
a) Give the descriptive statistics of the following data:
22,3
34,2
21,6
28,8
29,3
31,1
32,2
33,3
27,6
30,0
b) Illustrate the above data by a box plot
3) Draw asymmetric, unimodal, discrete frequency distribution such that sum of the frequencies
for x>8 is 5.
4) Number of plants found in 450 unit areas (quadrats) are given in the following frequency
distribution table.
No. of plants / quadrats
0
1
2
3
4+
Observed frequency
181
118
97
54
0
a) What is the variable?
b) What type of a variable is this?
c) Illustrate this frequency distribution on a graph. Calculate the cumulative frequencies
of this data.
5) There is an asymmetric bimodal distribution where
Median < Mean < Mode 1 and Mode 2
a) Draw a histogram which satisfies the above conditions.
b) Draw another frequency distribution, now for a discrete variable, and has a higher
degree of scatter when compared with the first one.
6) Provide the graphical illustrations of two frequency distributions such that
a) in the first one n=5, mean=median=mode=3, variable is discrete, s is determined by
you.
b) in the second one the first distribution is shifted on the x-axis such that now
the mean=median=mode=5.
How the values of dispersion measures are affected by this shift?
7) Draw a discrete frequency distribution where mode > mean and median = 2, n= 4.
Furthermore 25% of the total observations are at < 2.
8) When do we use CV? What are the advantages and disadvantages of using probability
distribution? What is the other name of probability distribution? What type of frequency
distribution is tabulated by the Binomial Distribution Table?
OU- Variables- Theoretical Distributions
9) Give examples of experimental and theoretical distributions. First identify their OU. Then,
contrast them in terms of their power in formation of expected probability distribution. Why do
we need to know expected probability distribution? What if we do not know the expected
probability in an experiment?
10) In the following data distribution of parasite (Azuki bean weevils) in 112 azuki beans is
shown:
a)
C
the
Number of weevils Emerging per bean
X
Observed frequencies
f
61
50
4+
frequencies. State the assumptions.
b)
c)
Calculate the coefficient of variations and coefficient of dispersions.
(i.e s2 / x) for both of the dist.
Comment about the fitness between the expected and observed frequencies.
alculate
expected
11) From the pool of eggs of Drosophila, 100 tubes of 5 egg each are set. In each case eggs are
randomly chosen. Mortality of the eggs are observed and shown on the following fq. table:
Number of eggs hatched
0
Number of tubes
10
20
30
30
a) Determine hatchability of the eggs in the above experiment.
b) Calculate the expected frequencies.
c) Compare with the observed ones and comment about the similarities or dissimilarities.
12) Assume that in the first midterm exam of the course Bio 400, completing the midterm
examination is normally distributed with ( = 60 min, = 30 min). This year we have 80
students in the class.
a) How many students are expected to return the answers in the first half hour?
b) How many of them will still be in the exam after 90 min.?
c) If I will wait for each student to finish the exam, for how long will I stay in the class?
13) Illustrate this frequency distribution Albino rats are used to study the hormonal regulation of
a metabolic pathway and they are injected with a drug that inhibits synthesis of protein.
Generally 4 out of 20 rats die from the drug before the experiment is over. If 10 animals are
treated with the drug, what is the probability that at least 8 will be alive at the end of
the experiment.
14) Assume 600 apple seeds are distributed randomly over 600 m2.
a) How many 1 m2 plots would contain no apple seeds?
b) How many 1 m2 plots would contain apple seeds?
c) Give the expected mean and variance of the apple seeds in the above scenario.
d) What is the sampling unit (observational unit) and possible outcomes for the above
experiment?
e) If there is deviation in observation compared to expectation in no apple seeds class how
would you explain this?
15) 20% of the METU students are involved in sports; 10% in football playing and the rest
(10%) in other sports. If I choose 6 students from the campus what are the expected outcomes
and their probabilities in terms of
a) football players
b) students being involved in any one type (football included) of sports?
c) For (a) part of question:
What is the sampling unit (observational unit)?
What is the variable?
What type is the variable?
Which is the least likely outcome, which is the most likely outcome among the
possible outcomes?
d) If I have examined 150 groups of 6 students and observed that there are excess observations
for 3 football players/group what will be your interpretation?
16) Give a name of a rare event which is in the interest area of biology. Let this rare event, on the
average, is observed once in observational units. Specify your observational unit. Each year you
are examining 20 observational units and you are continuing to this research for 5 years. Provide
the expected frequencies for the possible outcomes at the end of the research. Calculate the
mean, variance and coefficient of dispersion from this expected frequency distribution. If in the
observed frequency distribution CDobs> CDexpected what is your interpretation?
17) If the grades of the present midterm examination were distributed as N (70,10) and
if 0.5 defined the range of grade CC
a) Which grades will be considered as CC?
b) How many students out of 81 will get CC?
Test if the following data fits into a Poisson distribution.
18) Table: Men killed by being kicked by a horse in 10 Prussian army corps in the course of
20 years.
Number of men killed per
year per army corps
0
1
2
3
4
5+
Observed
frequencies
109
65
22
3
1
0
Poisson Expected
freq.
Deviation from
expectation
19) Aphids are distributed on the leaves of a plant as given in the table below.
# aphids / leaf
Frequency
100
6+
a) Are they distributed randomly? Explain.
b) If you visit the site, sample one observation unit and find 6 aphids on it, what would be your
conclusion?
20) Busses have 60 seats each. On the average 1 passenger gets sick at each trip.
a) What are the possibilities that there will be: no, 1, 2 passenger(s) will be sick in the
next trip? Calculate these probabilities by using two DIFFERENT theoretical distributions.
Compare the results.
b) Give the probabilities of the events in the binomial population.
c) I. How many possible outcomes in this experiment?
II. How one can find the probabilities of these outcomes?
21) It is known that for a women between the age interval 60-65 p of dying is 0.05. Women aged
60-65 received the flu vaccine. Next year out of 10, 2 of them died. What is the OU? Outcomes?
Is this an unusual observation?
22)
a)
If the events are independent and samples are random what is
the expected (theoretical) probability distribution for the above
experiment?
b)
What is the expected probability for observing two or fewer
relieved/six ?
c)
Compare the calculated expected value with the result obtained
in part (e) of the first question. Comment about the difference.
23) I would like to compare the mean cholesterol levels of vegetarians and nonvegetarians. The data that I had is as follows:
x veg = 183.7
nveg = 33
x nonveg = 235
nnonveg = 48
sveg = 3
snonveg = 5
If both of the groups have the same mean, how likely it is to find such an observed
differences?
24) Can we say that the group means of the following teo groups are different from
each other?
Group 1
Group 2
12,1
11,8
11,7
12,5
8,2
13,4
9,4
14,1
10,6
18,6
12,1
17,5
Find the confidence intervals for the means of the two populations from which these
samples were drawn. Compare the confidence intervals. The results of the confidance
intervals and t-test, do they confirm each other.