Intro to statistics

Question 1

What is a null hypothesis?

Answer 1

Difference between scores is so small that it is likely caused by chance.

Question 2

What is an experimental/alternative hypothesis?

Answer 2

Any difference in scores between conditions is large enough that it is likely not caused by chance.

Question 3

What is considered statistical significance?

Answer 3

1 occasion in 20, or P<0.05, or 5%.

Question 4

What is a type 1 error?

Answer 4

Result is declared statistically significant where there is not a significant difference.

Question 5

What is a type 2 error?

Answer 5

Result is declared not statistically significant where there is a significant difference.

Question 6

What is a one-tailed hypothesis?

Answer 6

Predicts the direction of outcome.

Question 7

What is a two-tailed hypothesis?

Answer 7

Does not predict the direction of outcome but still predicts statistical significance.

Question 8

What is nominal data?

Answer 8

Data split into different categories with no order or direction e.g male/female, colours of sweets in a pack.

Question 9

What is ordinal data?

Answer 9

Data has ordered categories where differences between them are not known e.g rankings/scales, places in a competition, you cannot assume the difference between 1st and 2nd place is the same as the difference between 3rd and 4th.

Question 10

What is interval data?

Answer 10

Data measured on a numerical scale with equal distances between values e.g time, weight.

Question 11

What are pairwise comparisons?

Answer 11

Comparing things in pairs to see if they are statistically different to each other.

Question 12

What is effect size?

Answer 12

The magnitude of the relationship between variables.

Question 13

What is the alpha criterion?

Answer 13

Probability of making a type 1 error.

Question 14

What are post-hoc analyses?

Answer 14

Done after the data has been collected and analysed. Control for type 1 errors.

Question 15

What are a-priori analyses?

Answer 15

Done before the experiment begins.

Question 16

What is a chi-square stats test used for?

Answer 16

Analysing nominal data to compare the distribution of observations with those expected to be by chance.

Question 17

When would you use a Yates correction?

Answer 17

When performing a chi-square test with 1 degree of freedom. Due to overestimation of the test statistic.

Question 18

What is a T-test used for?

Answer 18

To compare means. Using interval or ratio data.

Question 19

What is the standard error?

Answer 19

The standard amount by which a sample mean is in error when estimating the mean of the population.

Question 20

What do T scores tell us?

Answer 20

In an independent they tell us how different our sample mean is from the population mean. In a related, they tell us the mean difference between two sets of scores.

Question 21

What is a correlation?

Answer 21

A measure of the linear relationship between two variables.

Question 22

When would a Pearson’s correlation be used?

Answer 22

For interval variables.

Question 23

When would a Spearman’s Rho correlation be used?

Answer 23

For ordinal variables.

Question 24

What is a correlation coefficient?

Answer 24

The amount of variance shared by the variables.

Question 25

What do ANOVA's tell us?

Answer 25

If there are statistical differences between independent groups. Then you can understand which independent variable(s) has a connection to your dependent variable.

Question 26

What is a one-way ANOVA?

Answer 26

Compares the effects of an independent variable on one or multiple dependent variables.

Question 27

What is a two (or more)-way ANOVA?

Answer 27

Compares the effects of more than one independent variable on one or multiple dependent variables.

Question 28

What does a 'factorial' ANOVA mean?

Answer 28

Any ANOVA that has two or more independent categorical variables.

Question 29

Why would ad-hoc tests be needed for an ANOVA?

Answer 29

As they do not tell you which groups are different from each other.

Question 30

What are the assumptions of an ANOVA?

Answer 30

1. Interval data 2. Normality 3. Homogeneity of variance 4. Independence

Question 31

What is the meaning of normality in stats?

Answer 31

Each ps supplies one piece of data and it is organized according to its numeric quantity, so the mean is accurate.

Question 32

What is the meaning of homogeneity of variance?

Answer 32

The dependent variable scores have the same degree of variability across conditions

Question 33

What is the meaning of independence in stats?

Answer 33

The absence of systematic bias from nuisance variables across and within conditions.

Question 34

What are the methods of mediating the negative impacts of a repeated-measures experimental design?

Answer 34

1. Counterbalancing 2. Randomization

Question 35

What is counterbalancing?

Answer 35

Half of participants do condition A then B, the other half do B then A.

Question 36

What is randomization?

Answer 36

Different order of conditions is generated randomly for each participant.

Question 37

Would using counterbalancing and randomization fix carryover effects?

Answer 37

No.

Question 38

What are carryover effects?

Answer 38

The changes in participants that can be caused by a condition.

Question 39

What is statistical power?

Answer 39

Probability of correctly rejecting a false null hypothesis, and finding an effect if it actually exists.

Question 40

What is the minimum desired statistical power?

Answer 40

0.80 or an 80% chance of finding a true effect.

Question 41

What can influence statistical power?

Answer 41

1. Sensitivity of the study 2. Size of effect of interest 3. Alpha criterion

Question 42

How can you know what statistical power to expect?

Answer 42

1. Look at previous studies 2. Run a pilot study 3. Use Cohen's ranges

Question 43

How should power be calculated for factorial designs?

Answer 43

Required power should be calculated separately for all main effects and interactions.

Question 44

When should non-parametric tests be used?

Answer 44

When assumptions for the parametric tests fail.

Question 45

What is kurtosis?

Answer 45

The thinness of a distribution.

Question 46

What are the 3 types of kurtosis?

Answer 46

leptokurtic = very thin/high to the top of the graph mesokurtic = middle thinness platykurtic = very fat/low to the bottom of the graph

Question 47

What is the interquartile range?

Answer 47

three values that split the sorted data into 4 parts.

Question 48

What are the quartiles?

Answer 48

Second = median Lower = median of lower half of data Upper = median of upper half of data