Week 6

Question 1

Define sample and population

Answer 1

S-Subgroup of the population i.e. the participants.

P-Entire group of people of interest.

Question 2

Define Sampling Frame

Answer 2

■The group from which the sample is chosen.
■Not always the same as the population of interest.

E.g. NHS wanted to follow up people who had been treated at the Royal. Telephone interview of 1000 former patients between 9.30am and 5pm. (the frame)

Question 3

What does generalisation from a sample to a population depend on?

Answer 3

representativeness (similar % to population group % e.g. gender)

can be prevented by selection and response bias

Question 4

Define selection bias

Answer 4

Over-representation of a segment of the population.
Sampling method:
–Population of interest = psychology and sociology students. Sample = 70% psychology, 30% sociology.

Question 5

Define response bias

Answer 5

Problem for questionnaire studies or surveys.
Unrepresentative participants.
–End-of-semester module evaluations (Mostly students who have complaints!)

Question 6

Give an example of self-sampling

Answer 6

E.g. Advertisement for volunteers for a study into the effect of stress on cognition.
–People who see the advert.
–Interested in doing research or interested in the effects of stress.
–Free during the day.

Question 7

What 3 sampling methods can be used in Probability Sampling?

Answer 7

– Random sampling.
– Stratified sampling.
– Cluster sampling.

Question 8

What 3 sampling methods can be used in Non-probability Sampling?

Answer 8

– Opportunity/Convenience
sampling.
– Purposive sampling.
– Quota sampling.

Question 9

Explain Probability Sampling

Answer 9

■Random selection.
■ Each member of the population has a specific probability of being chosen as a participant.
■Estimate the likelihood that sample findings will differ from the population.
■High degree of representativeness.

Question 10

Explain random sampling

Answer 10

Sample chosen by chance.

Question 11

Explain Systematic random sampling

Answer 11

–Sample selected at a fixed, periodic interval. (Interval = population divided by sample size.)

■ Everyone in the population of interest has an equal
chance of selection.

■ True random sample very difficult to achieve and not
very practical.

Question 12

Explain Stratified Probability Sampling

Answer 12

■Divide population into subgroups/strata.
■Random sampling within each group.
■Divide into subgroups according to variables likely to affect the DV E.g. Age, gender, ethnicity.

Question 13

Explain Cluster Probability Sampling

Answer 13

■Divide population into groups or clusters, then select random sample of clusters.
■Every member of selected cluster is part of the sample.

Question 14

Define Non-Probability Sampling

Answer 14

The probability of any member of the population being chosen is unknown.
■Is it Representative + has Generalisation?

Question 15

Explain Opportunity/Convenience Sampling

Answer 15

■Participants are conveniently
available.
■Is it a restricted sample?

Question 16

Explain Purposive Sampling

Answer 16

■Participants belong to a specific group e.g., people diagnosed with ADHD, people under 30 etc.
■ Selection is not random.

Question 17

Explain Quota Sampling

Answer 17

■Population divided into subgroups and P’s selected to fill a quota.
–Population: over 60s. Sample: 50 males and 100 females.
■ Keep sampling until quota is filled.
■Non-random sample - Selection is left to researcher.
■High potential for bias:
– Friendly looking people?
– Convenient location?

Question 18

Explain Observation Sampling

Answer 18

■When and where.
■Representative:
– Population - Time -
Place.
■Time sampling.
■Event sampling.
■Situation sampling.

Question 19

Explain Time Sampling

Answer 19

■Choose various time intervals for observations e.g., observe children in class for 2 hours per
day. (is doing it the same day representative?)

■Random or systematic.

Question 20

Explain Event Sampling

Answer 20

■Selecting specific events and behaviours E.g., Student behaviour during exams.
■Natural disasters.
■Event defines when.

Question 21

Explain Situation Sampling

Answer 21

■Specific behaviour in different locations.
■Increases external validity.
Examples:
–LaFrance & Mayo (1976) - Gaze direction during conversation.
–Observing vigilance behaviour in cafes, bars, parks etc.

Question 22

Importance of Correct Sampling: Explain ecological validity

Answer 22

–How much a method of research
resembles ‘real life’.
–Lab based = artificial.
–Representative sample -
Students?

Question 23

Importance of Correct Sampling: Explain reliability

Answer 23

Reliability:
–Same/similar results each
time.
–Sampling correctly.
–Repeat findings multiple times.
–If not - biased sample?

Question 24

What’s the impact of having a larger sample size AND too many participants?

Answer 24

more likely to have a normal distribution = more powerful statistical tests.
the greater the power of the statistical test = increased likelihood of finding statistical
differences between groups.
–Too many participants - very small differences may become significant.

Question 25

Define Exclusion criteria

Answer 25

–Variables which may have a large effect on the DV.
 Age limit?
 Pre-existing mental disorders?
 Dyslexia?

Question 26

Define WEIRD Sampling

Answer 26

Western
Educated
Industrialised
Rich
Democratic
96% of participants were from Western industrialized countries — which house just 12% of the world’s population. (Arnett, 2008).

Question 27

Explain IQ

Answer 27

-100 times the mental age over chronological age (Terman, 1916)
■The average score of the population is 100 – most people have a mental age similar to their chronological age.
–To test this instead of measuring the whole population I could ask you to be my sample by taking an online IQ test and noting your score.
–Should I take your mean IQ to be the mean IQ of the population?

Question 28

True or false: Different samples may give us different parameters
(means).

Answer 28

True, by gathering more samples, we have found the population
mean.

Question 29

How can we understand the population in terms of measures of central tendency and measures of spread

Answer 29

–with many different samples, the spread is potentially more
important than the central tendency.
–our sample mean may be different to the population mean, but is the population mean contained somewhere within our data?
–our measure of spread will tell us.

Question 30

Explain Measures of Spread

Answer 30

■Always present measures of spread along with measures
of central tendency.
■Normally, we might test a sample and find the means
(±SDs).
■Other measures of spread/dispersion/variability:
– Standard Error
– Confidence Intervals

Question 31

Explain Standard Error

Answer 31

■The standard deviation of multiple sample means.
■Standard error measures the accuracy with which a sample represents a population.
■How much a sample mean deviates from the actual mean of a population.

Question 32

What does The Central Limit Theorem state?

Answer 32

states that the sampling distribution of the sample means is likely to be normally distributed as long as the sample size is large enough (>30).

Question 33

Explain Confidence Intervals

Answer 33

■Use the estimate of the standard error to create acceptable
boundaries where we believe the population mean will fall.
■When we have a sample mean, we can calculate confidence
intervals around that mean.

Question 34

Explain Z Scores

Answer 34

■Z scores are measures of standard deviation (SD).
–SD=the average amount of variation or dispersion from the
mean of a set of data values.

–If the z score is 0 your score is identical to the mean score.
–Positive and negative scores show the number of standard
deviations that the score is either above or below the mean.
–E.g. a z score of +2.5 means the score is 2.5 standard
deviations above the mean.

Question 35

What do Z scores allow?

Answer 35

■Z scores also allow us to compare different data sets i.e., they use standardised scores.
■Z scores rely on means and SDs:
–Scores don’t need to be in the same units of measurement.
–E.g. different tests with different maximum scores, different means and different SDs.