Research methods Flashcards
What are the sampling techniques?
- Volunteer
- Random
- Opportunist
- Systematic = Selecting every “Nth” person
- Stratified = Selecting people that are proportionate to the sample as a whole (so it is representative of the population)
What are the pros and cons of each sampling technique?
-Random:
Pro = Less biased
Con = Could have a smaller a range of people
-Random:
Pro = Less biased
Con = Impractical
-Systematic:
Pro = Less biased
Con = Not representative of population/ whole sample
-Stratified:
Pro = Representative of population/ whole sample and the amount from each group of people
Con = Can be inaccurate if the sample size is small
-Opportunist:
Pro = Convenient, easy
Con = Can be susceptible to researcher bias
What are the types of experiment?
- Lab, IV is manipulated
- Field, natural environment but IV is manipulated
- Quasi, IV is not manipulated, it has happened due to naturally occurring events
- Natural, studies where the experimenter cannot manipulate the IV, so the DV is simply measured and judged as the effect of an IV
What is meant by a self report technique?
- Self reports are a method of gathering data where participants provide information about themselves without interference from the experimenter.
- Such techniques can include questionnaires, interviews, or even diaries, and ultimately will require giving responses to pre-set questions.
What is a type 1 error? [:(]
- A type 1 error is when a researcher incorrectly rejects a null hypothesis that is actually true
- This means that you report that your findings are significant when in fact they have occurred by chance
- This usually happens when the significance levels are too high (10%)
What is a type 2 error? [:)]
- A type II error is when a researcher accepts a null hypothesis which is really false
- Here a researcher concludes there is not a significant effect, when actually there really is
- This usually happens when the significance levels are too low (1%)
What is a P-value?
-The level of statistical significance is often expressed as a p-value between 0 and 1
-The smaller the p-value, the stronger the evidence that you should reject the null hypothesis
-For example: P0.05 = The hypothesis is very valid
P0.1 = The hypothesis is not as valid
What is the table that shows the inferential statistical tests|? CSCMWSURP
|Unrelated | Related | Correlation
|Nominal | Chi2 | Sign test | Chi2
|Ordinal |Mann-Whitney U| Wilcoxon | Spearman’s Rho
|Interval | Unrelated T | Related T | Pearsons
Which experimental design is used for unrelated and related tests?
Unrelated = Independent groups Related = Repeated measures & Matched pairs
What are the levels of measurement?
Nominal = Categorical (Smoker/Non-smoker) [Discrete] Ordinal = Ordered data (Rating scales) [No equal intervals, subjective as it is ordered] Interval = Data based on numerical scales (Weight, size, scores) [Objective and intervals are equal]
What is the correct order for referencing?
-Name, Date, Book name, Place, Publisher
-For example:
Duck, S. (1992) Human Relationships, London: Sage
What are descriptive statistics
- Descriptive statistics analyse data to help describe, show or summarise it in a meaningful way
- Examples are: Measures of central tendency and measures of dispersion
What are measures of central tendency?
- Measures of central tendency are examples of descriptive data statistics that depict an overall ‘central’ trend of a set of data:
- The mode
- The median
- The mean
What are measure of dispersion?
- Measures of dispersion describe the spread of data around a central value (mean, median or mode)
- They tell us how much variability there is in the data
- There are two measures of dispersion:
- The range
- The standard deviation
What is standard deviation?
- Standard deviation is a measure of dispersion that shows the spread of scores around the mean
- The greater the standard deviation the great the spread of scores around the mean
What are correlation co-variables?
-The two variables that are measured/collected by the researcher and then compared to each other
What is a correlation coefficient?
- A number used to represent the strength and the direction of the relationship between the co-variables as a number between -1 and +1
- A perfect positive correlation is +1
- A perfect negative correlation is -1
Why are correlations not a good way of analysing data?
- Correlation does not show causation
- This means that although a relationship may exist, it doesn’t show which co-variable caused the change
- Doesn’t show other extraneous variables which may be the cause
How can investigator effects be avoided?
- Have an interviewer who had not witnessed the event
- Have an interviewer who doesn’t know the aims of the study so that they would not be affected by their own perception of the event
- Use open-ended questions so the interviewees are able to give a more detailed and accurate version of what they saw
- Use a questionnaire (Or other means) to collect data without face to face interaction