Demand Characteristics can lead to the participant:
- Guessing the purpose of the research and trying to please the researcher by giving the right answers.
- Guessing the purpose of the research and trying to annoy the researcher by giving the wrong answers (Srew you effect).
- Acting unnaturally out of nervousness or fear of being evaluated.
- Acting unnaturally due to social desirability bias (wanting to look good).
- In theory it is the best sampling method to be able to generalise results because it is unbiased and is representative.
- It is difficult to acheive in a large sample because it is hard to get details from the population.
- The sample may still be unrepresentative because it does not assure an unbiased selection because there may be a small sample.
- It is easier and more convenient than random sampling as it is not time consuming.
- It is not likely to be representative because only people in that particular place are being asked, e.g. people who shop at Tesco.
- People can choose not to approach you so it becomes self picked.
Volunteer Sampling (Self-Selected)
- It is easier and more convenient than random sampling because it can be done by sending an email or a survey or by making a poster.
- The participants want to take part so they are less likely to sabotage the study.
- It is not likely to be representative because only certain people will reply to the advert e.g. more intelligent people or people who do not work so have more free time.
- There is a problem with demand characteristics as the participants are eager and want to please the researcher.
- The results have a high chance of being generalisable because the sample is small so it is unbiased.
- The sample may still be unrepresentative because it does not assure an unbiased selection.
- A large population is hard to work out every 5th person.
- The results are unbiased because certain types of people haven't been selected.
- Detailed knowledge about the population is needed, however this may not be available and it is too time consuming to collect the information.
- It is time consuming to collect the participants information.
This is calculated by adding the scores together and then dividing by the number of values.
- It uses all of the scores and is therefore the most powerfull and sensitive measure of central tendency.
- The mean can be used with interval data.
- It can be distorted by extreme scores (scores which are much higher or lower compared to the others) making it unrepresentative. These scores are called outliers or anomalies.
- The mean score may not actually be one of the actual scores from the set of data.
This is calculated by putting the data in order and then finding the middle score. If there is an even number of scores then add the middle two together and divide it by two.
- It is unaffected by extreme values. Therefore if a set of data has extreme values, the median would be more appropriate.
- Easier to calculate than the mean.
- The median can be used with ordinal data.
- It only takes into account one or two scores (the middle values), therefore it is not as sensitive as the mean.
- It is unrepresentative in a small set of data.
This is calculated by a frequency count.
- It is unaffected by extreme values. Therefore if a set of data has extreme values, the mode would be more appropriate.
- It is easier to calculate than the mean.
- It is not useful in small sets of data or when there are too many modes.
- It deosn't take into account the other scores.
- There can be more than one mode (e.g. bimodal).
This is calculated by subtracting the lowest value from the highest value in a set of data.
- Fairly easy and quick to work out.
- It takes full account of extreme values.
- It can be distorted by anomalies.
- It does not show whether data are clustered or spread evenly around the mean.
These are worked out by:
- Adding all of the frequencies together.
- 360 / the total frequency
- This value is then for 1 person.
- Multiply that number by the frequency to get the amount for that segment.
These are worked out by using the calculation:
Frequency = Class Width x Frequency Density
This is worked out by:
- Work out whether the hypothesis is one tailed or two tailed.
- Record the data with the participant, score before, score after, difference, sign ( + or - ).
- Work out the calculated value/observed value by adding all the plus signs and then all the minus signs. S is the smaller value so if there were 3 + and 5 - , S would be S = 3.
- Work out the critical value using the critical value table. You need N (the number or participants). Get rid of a participant if they have a difference value of 0.
- The calculated value of S must be equal to or less than the critical value for the results to be significant.