Week 7 Descriptive & inferential stats

Question 1

What is statistics?

Answer 1

Practice or science of collecting & analysing numerical data in large quantities, especially to make inferences on a population based on a representative sample

Question 2

Descriptive stats

Answer 2

Make descriptions & summaries of population through numbers,graphs: central tendency, data spread, count, proportion, skewness etc

Question 3

Inferential stats

Answer 3

1. Provide meaningful inferences/conclusion on population, based on sample data
2. To make generalisations & predictions

Question 4

What are the types of statistics?

Answer 4

1. Descriptive
2. Inferential

Question 5

What are the measures of central tendency?

Answer 5

Mean, Median, Mode

Question 6

When is mean usually used?

Answer 6

Suitable for symmetric distribution, often with SD

Question 7

When is median usually used?

Answer 7

Suitable for skewed distribution, often with IQR

Question 8

Why is median most used in skewed distribution?

Answer 8

It is less sensitive to extreme values unlike mean where it is pulled with the direction of skew

Question 9

What is variance?

Answer 9

Average of squared differences of each data point from mean, squared unit of mean

Question 10

What is standard deviation?

Answer 10

Square root of a variance

Question 11

What does a small & large SD mean?

Answer 11

Small - data points are closer around the mean
Large - data points are further to mean

Question 12

What does small & large variance mean?

Answer 12

Small - data are close to mean & each other
Large - data are far from mean & each other

Question 13

What is the empirical rule?

Answer 13

68% - within 1 SD from mean
95% - within 2 SD from mean
99.7% - within 3 SD from mean

Question 14

What is the purpose of inferential stats?

Answer 14

1. To generalise sample characteristics to population parameters where they are just estimations & have to account for inaccuracies & errors using confidence interval (CI)
2. Test hypotheses

Question 15

What is confidence interval?

Answer 15

a range of values where the true mean lies

Question 16

What is the distribution assumed for parametric tests?

Answer 16

Normal (Gaussian) distribution

Question 17

What are the limitations of inferential stats?

Answer 17

1. Can never be fully accurate bc using sample data to estimate that of a population
2. Interpretation of data is subjected to researchers reasoning

Question 18

What is non parametric test based on?

Answer 18

No need to follow normal distribution mostly based on rank order or how common data is

Question 19

What central tendency does parametric & non parametric measure?

Answer 19

Para - mean
Non para - median

Question 20

What type of variables does parametric measure?

Answer 20

Continuous

Question 21

What type of variables does non parametric measure?

Answer 21

Continuous and discrete

Question 22

Assumptions for parametric test?

Answer 22

1. DV is continuous
2. DV follows normal distribution
3. Homogenity of variance between groups (same)
4. Comparison groups are independent
5. Preferably no significant outliers

Question 23

How to check for normality?

Answer 23

1. Visualisation - Q-Q plot or histogram
2. Statistical hypothesis testing: Shapiro Wilk test

Question 24

T-test

Answer 24

Determine whether there is a significant difference between the means of two groups. It is widely used in hypothesis testing when comparing sample means to make inferences about population mean

Question 25

F-test: ANOVA

Answer 25

To compare variances or equality of means among 3 or more groups/conditions

Question 26

What is analysis of variance (ANOVA) for?

Answer 26

Analyses how entire set of group means are spread out regardless of group differences

Question 27

What does a measure of linear association mean?

Answer 27

Produces a coefficient used to quantify the strength & direction of a rs/association between 2 or more variables where value of coefficient is -1 to +1

Question 28

Examples of non parametric tests

Answer 28

Wilcoxon signed rank test Mann-Whitney U test Kruskal Wallis test Friedman's test

Question 29

Bivariate correlation

Answer 29

Focuses on relation between 2 variables, need best fit line for continuous variable - not applicable to curvilinear or discontinuous rs

Question 30

Chi square test of independence

Answer 30

Measure significance of association between 2 categorical variables e.g no numerical meaning

Question 31

Linear regression

Answer 31

An estimation of association between a continuous DV and more than 1 IV

Question 32

What are the measures of linear association?

Answer 32

1. Bivariate correlation 2. Chi square test 3. Regression

Question 33

Assumptions of linear regression

Answer 33

1. Linear rs 2. Independence 3. Homoscedasticity - variance of scores are similar 4. Normality

Question 34

What are the types of regression?

Answer 34

1. Simple linear 2. Multiple linear 3. Nonlinear

Question 35

Simple linear

Answer 35

Compare 2 variables only y=a +bx + c

Question 36

Multiple linear regression

Answer 36

Multiple IV and DV - best fit line

Question 37

Logistic regression

Answer 37

An estimation of association between a binary DV (yes/no) and more than 1 IV