Testing a hypothesis

Question 1

Heuristics

Answer 1

Mental shortcuts or rules of thumb that help us to streamline our thinking and make sense of the world

Question 2

Representativeness heuristic

Answer 2

We judge the probability of an event by its superficial similarity to a prototype or stereotype (e.g. judge a book by its cover)

Question 3

Availability heuristic

Answer 3

We estimate the likelihood of an occurrence based on the each in which it comes to our minds (how available it is in our memories)

Question 4

Cognitive biases

Answer 4

Overconfidence (our tendency to overestimate our ability to make correct predictions. 
Hindsight Bias (the tendency to overestimate how we could have successfully foretasted know outcomes)

Question 5

Hypothesis testing steps

Answer 5

1) state the research hypothesis
2) state the null hypothesis
3) choose level of statistical significance (alpha level)
4) Select and compute the test statistic
5) make a decision regarding whether to accept or reject the null hypothesis

Question 6

Theory

Answer 6

A ‘model’ that describes how certain phenomenon work (theory must be testable via scientific method Observable and measurable) (theories try to tell the whole story of what affects what and why)

Question 7

Hypothesis

Answer 7

Statement derived from a theory/theories about the relationship between variables or differences between groups (hypothesis are specific and focus on details of the theory that can be tested empirically)

Question 8

Hypothesis is about the population

Answer 8

we use a sample to draw inferences about the population via the hypothesis (a population that is unknown)

Question 9

Inferential statistics

Answer 9

• Go beyond description of data, they are used to interpret data and draw conclusions.
• They permit researchers to decide whether their data supports their hypothesis (are findings real or due to chance)

Question 10

Null hypothesis

Answer 10

(H little 0) - findings are due to chance

Question 11

Research or alternative hypothesis (H little 1)

Answer 11

finding are real.

Question 12

Population

Answer 12

(complete set) sample taken from population for sample

Question 13

Sample

Answer 13

(subset of the population used to inference population)

Question 14

Two tailed

Answer 14

Allots half of your alpha (0.5) to testing the significance of one direction and half of your alpha ti testing significance in the other direction. (this means that 0.025 is in each tail of the distribution of you test statistic)

Question 15

One tailed

Answer 15

Allots all of your alpha to testing the statistical significance in the one direction of interest (this means that 0.05 is in one tail of the distribution of your test statistic

Question 16

Error types

Answer 16

Type I,II,III

Question 17

Type I error

Answer 17

reject the null hypothesis when it is TRUE

Question 18

Type II error

Answer 18

Accept the null hypotheses when it is FALSE

Question 19

Type III error (only applicable to a direction hypothesis; (H little 1)

Answer 19

predicting the inverse of a true relationship

Question 20

When we reject the null hypothesis, we conclude we have found a

Answer 20

Statistically significant result

Question 21

Statistical significance

Answer 21

When the probability that the observed findings are due to chance is very low.

• very low = less that 5 chances in 100 (.05 level) = p < .05
• this, the findings support the research hypothesis (H little 1)

Question 22

P IS LOW

Answer 22

NULL MUST GO

Question 23

P value less that 0.5 means

Answer 23

There is evidence of an effect

Question 24

P value of more that 0.5 means there is no evidence of an effect

Answer 24

P IS HIGH, NULL WONT DIE

Question 25

what does the p value tell you

Answer 25

if the results are statistically significant or not according to the alpha criterion

Question 26

Factors that affect the p value

Answer 26

Size of the mean difference
- Increases the probability of rejecting null hypothesis
Variability of scores
- Decreases the probability of rejecting null hypothesis
Sample size
- Increases the probability of rejecting null hypothesis