CMN 102 - MIDTERM 2 EXAM
QUESTIONS AND ANSWERS 2026
Sampling as a part of everyday life - ANSWERS-eating at a restaurant
*bad experience at Applebees
-we seek to know something about a whole group of similar objects or things
-we observe these objects
-then extend findings
Sampling: Potential problems - ANSWERSOver-generalization
Why sample: practical reasons - ANSWERS-want to make generalizations about a
broad range of people, but hard to actually observe or ask everyone
*ex: survey all 32,653 UCD students?
Why sample: heterogeneity of population - ANSWERScan't assume population is
homogenous (i.e. identical) in social science, as you can in the physical or natural
sciences
Sampling: Cons - ANSWERSCons:
-trying to observe or question everyone might be worse than just using a sample
*ex: US Census hired tons of interviewers, spent $$, missed people, and counted some
people twice
target population - ANSWERSpopulation to which generalizations want to be made
element - ANSWERScases or units of which a target population is comprised
frame population - ANSWERSactual population from which a sample is taken
*ex: Target - college kids; Frame: UC Davis
Probability Theory: Random Selection - ANSWERSeach element has as equal chance
of selection independent of any other event in the selection process
(NOT colloquial sense of random, which typically means haphazardly or by accident)
Probability Theory: parameters - ANSWERSactual characteristic of a given variable in a
population
*ex: true mean height of US Citizens;
Probability Theory: statistics - ANSWERSsample estimates of population parameters
Sampling Distribution - ANSWERScalculating a statistic, searching for the mean: for all
of the possible samples of a particular size results in a sampling distribution
, -larger sample, smaller std. deviation
-larger sample, more accurate
sampling error - ANSWERSthe amount of a given sample statistic
*deviates from population parameter it estimates
*the smaller the population, the higher the error; the larger the sample, the lower the
error
confidence level - ANSWERSthe estimated probability that a population parameter lies
within a given confidence interval
-the confidence level is higher with a larger sample
-confidence level is always a %
-the range within which the population is likely to fall
confidence interval - ANSWERSthe range of values within which a population
parameter is estimated to lie
-decreases as number of people in your sample increase
simple random sample - ANSWERS-every possible combination of cases has an equal
chance of being included in the sample
*need:
-a complete list of population
-random selection of cases to be included in sample
stratified random sample (probability sample) - ANSWERSsteps:
1. subdivided into strata (at least two groups depending on variable i.e. age or sex)
2. draw random sample from each stratum
3. combine subsamples
look for sampling error
Multistage Cluster sampling - ANSWERSUsed when impractical/impossible to list all
members
Steps:
1. Create clusters
*clusters are natural groupings like colleges, churches, geographic areas
2. Make subclusters
3. randomly select from subcluster
Systematic Sampling - ANSWERSSteps:
1. Obtain complete list of everyone in population
2. Number everyone on list
3. Choose a sampling interval of every Kth case
4. randomly choose 1 person between 1st-Kth interval
-Make sure to get the number needed
-Make sure not to start with an organized list
QUESTIONS AND ANSWERS 2026
Sampling as a part of everyday life - ANSWERS-eating at a restaurant
*bad experience at Applebees
-we seek to know something about a whole group of similar objects or things
-we observe these objects
-then extend findings
Sampling: Potential problems - ANSWERSOver-generalization
Why sample: practical reasons - ANSWERS-want to make generalizations about a
broad range of people, but hard to actually observe or ask everyone
*ex: survey all 32,653 UCD students?
Why sample: heterogeneity of population - ANSWERScan't assume population is
homogenous (i.e. identical) in social science, as you can in the physical or natural
sciences
Sampling: Cons - ANSWERSCons:
-trying to observe or question everyone might be worse than just using a sample
*ex: US Census hired tons of interviewers, spent $$, missed people, and counted some
people twice
target population - ANSWERSpopulation to which generalizations want to be made
element - ANSWERScases or units of which a target population is comprised
frame population - ANSWERSactual population from which a sample is taken
*ex: Target - college kids; Frame: UC Davis
Probability Theory: Random Selection - ANSWERSeach element has as equal chance
of selection independent of any other event in the selection process
(NOT colloquial sense of random, which typically means haphazardly or by accident)
Probability Theory: parameters - ANSWERSactual characteristic of a given variable in a
population
*ex: true mean height of US Citizens;
Probability Theory: statistics - ANSWERSsample estimates of population parameters
Sampling Distribution - ANSWERScalculating a statistic, searching for the mean: for all
of the possible samples of a particular size results in a sampling distribution
, -larger sample, smaller std. deviation
-larger sample, more accurate
sampling error - ANSWERSthe amount of a given sample statistic
*deviates from population parameter it estimates
*the smaller the population, the higher the error; the larger the sample, the lower the
error
confidence level - ANSWERSthe estimated probability that a population parameter lies
within a given confidence interval
-the confidence level is higher with a larger sample
-confidence level is always a %
-the range within which the population is likely to fall
confidence interval - ANSWERSthe range of values within which a population
parameter is estimated to lie
-decreases as number of people in your sample increase
simple random sample - ANSWERS-every possible combination of cases has an equal
chance of being included in the sample
*need:
-a complete list of population
-random selection of cases to be included in sample
stratified random sample (probability sample) - ANSWERSsteps:
1. subdivided into strata (at least two groups depending on variable i.e. age or sex)
2. draw random sample from each stratum
3. combine subsamples
look for sampling error
Multistage Cluster sampling - ANSWERSUsed when impractical/impossible to list all
members
Steps:
1. Create clusters
*clusters are natural groupings like colleges, churches, geographic areas
2. Make subclusters
3. randomly select from subcluster
Systematic Sampling - ANSWERSSteps:
1. Obtain complete list of everyone in population
2. Number everyone on list
3. Choose a sampling interval of every Kth case
4. randomly choose 1 person between 1st-Kth interval
-Make sure to get the number needed
-Make sure not to start with an organized list
