Inferential Statistics

Question 1

Inferential Statistics Use

Answer 1

• Help us to infer and deduce conclusions from data: whether the null hypotheses can be rejected and if findings are significant, due to chance or caused by something else
• Different tests are used in different situations and the aim is to reject the null hypotheses by showing that results weren’t by chance and this depends on probability

Question 2

Negatively Skewed Distribution Curve

Answer 2

• Measures of central tendency increase in value

Question 3

Normal Distribution Curve

Answer 3

• Perfectly symmetrical distribution

- All measures of central tendency are the same

Question 4

Positively Skewed Distribution Curve

Answer 4

• Measures of central tendency decrease in value

Question 5

Probability & Significance

Answer 5

• Results that don’t occur by chance are significant
• An observed value is calculated from the study
• This is compared with the critical value on the table, which helps to see whether it is significant or not
• This is based on probability through the use of a p-value

Question 6

Level Of Significance

Answer 6

• The level at which psychologists will reject the null hypotheses is when there is a p-value of less than or equal to 0.05
• This means there is 95% or more probability of the IV having an affect on the DV so the null hypotheses is rejected
• And there is a 5% or less probability of results being due to chance

Question 7

Non-Parametric Tests

Answer 7

• These tests allow for an observed value to be calculated from the study, which is then compared with a critical number that helps to check for significance
• In Chi-square and Spearman’s Rho Correlation Coefficient the observed value must be greater than or equal to the critical value for these tests
• In Binomial Sign Test, Mann Whitney-U Test and Wilcoxon Signed-Rank Test the observed value must be equal to or smaller than the critical value for these tests
• No Entering In Reserved Cubicles Because Men Women Separate

Question 8

Mann Whitney U Test Example

Answer 8

• A Mann Whitney-U Test is used as the test of significance of the difference between two conditions
• When an independent measures design has been used
• And the level of data collected is ‘at least’ ordinal

Question 9

Parametric Tests

Answer 9

• They have very stringent (strict) conditions:

1. Equal interval data
2. From an evenly distributed population
3. With an even spread

Question 10

Type 1 Error

Answer 10

• A possibility with significant results is that the null hypothesis is rejected when it shouldn’t be
• This results in the operationalised hypothesis being accepted despite the results being due to chance and caused by a false positive

Due To:

• Poor research design
• Using a level of significance that is too lenient

Question 11

Type 2 Error

Answer 11

• A possibility with insignificant results is that the null hypothesis is accepted when it shouldn’t be
• This results in the operationalised hypothesis being rejected when it’s actually correct and the results are due to a false negative

Due To:

• Poor research design
• Using a level of significance that is too stringent (strict)