statistics: general information

Question 1

what do measures of dispersion examine?

Answer 1

measures of dispersion examine variability in data sets
help us to understand whether scores in a data set are very similar or very different

Question 2

what is does the range tell us?

Answer 2

tells us over how many numbers a distribution is spread

Question 3

what is standard deviation?

Answer 3

it’s a measure of dispersion, tells us how far on average each score is from the mean
smaller the SD = more scores around the mean
larger the SD = more spread out the scores

Question 4

what are characteristics of the normal distribution curve (gaussian curve)?

Answer 4

it’s bell shaped
it’s symmetrical
mean median mode fall on same central point
the two tails never touch the horizontal axis

Question 5

how to differentiate between a negatively and positively skewed distribution

Answer 5

negatively skewed distribution has tail at negative end
mean closest to tail then median then mode

positively skewed distribution has a tail at positive end
mean closest to positive tail then median then mode

Question 6

what is the appropriate graph for correlational data?

Answer 6

scatter graph
show each participants scores on the two variables

Question 7

what are descriptive stats?

Answer 7

measures of central tendency and measures of dispersion (range, variants, standard deviation)

Question 8

why isn’t descriptive analysis as useful?

Answer 8

it doesn’t allow a researcher to be sure of the significance of their findings.

Question 9

what factors need to be taken into account when selecting the appropriate inferential statistical test?

Answer 9

level of data collected, association or difference, design choice

Question 10

what does inferential statistics allow us to do?

Answer 10

allows us to conclude a significant difference or relationship in data

Question 11

what is nominal data?

Answer 11

least precise/objective/mathematical/powerful level of data, weak level of measurement
simply involves researcher collecting and coding behaviours into categories
eg tallying number of times a person conforms or not

Question 12

what’s ordinal data?

Answer 12

involves numbers that can be put into some sort of order but are not necessarily an objective mathematical measure
eg ask participants to rate x factor finalists 1-5 strongly agree to strongly disagree but the difference between the values here is subjective. doesn’t have a specific set of mathematical properties
better as you can do the mean but still subjective

Question 13

what is interval data?

Answer 13

this level of measurement is objective and precise and does have more mathematical properties
difference between each measurement is exactly the same
NO ZERO VALUE can go into minus values

Question 14

what’s ratio data?

Answer 14

most precise objective powerful mathematical level of measurement
same as interval but ratio data does have a zero value
data can be put into order and there’s a set difference
eg time people running, mathematically the person who took 40 seconds ran twice as slow than the person who took 20 seconds

Question 15

what’s probability in psychological research?

Answer 15

at what level of probability researchers would agree that a finding is not due to chance

Question 16

how is probability expressed?

Answer 16

the probability of a difference between groups being due to change is expressed as p = 0.05
there’s a 5% probability that the results are due to chance factors and a 95% probability that the differences are due to the effect of the manipulation of the IV
sometimes researchers want to set more stringent level of significance so set the level at p = 0.01 meaning probability that the difference is due to manipulation of IV is 99%

Question 17

if results are significant at p = 0.05 what can we accept?

Answer 17

can accept that the difference is significant so researcher rejects the null hypothesis and accepts the alternate hypothesis

Question 18

what is a type 1 false positive error?

Answer 18

if we accidentally accept the alternate hypothesis wrongly as we used a weak level of probability this may mean we didn’t operate a stringent enough measure of probability

Question 19

what’s a type 2 false negative error?

Answer 19

if we reject the alternate hypothesis and wrongly accept the null hypothesis this means we’ve operated too stringent a level of probability and the result is a false negative

Question 20

what are parametric tests and when can they be used?

Answer 20

they are more powerful than non parametric tests and can be only used when

the data collected is interval or ratio
data is normally distributed
standard deviations for the two sets of data are similar