BMS2043 Spring 2024 Lecture 2: Inferential Statistics and Hypothesis Testing

Podcast

Play an AI-generated podcast conversation about this lesson

Questions and Answers

What is the fundamental concept in inferential statistics?

Hypothesis testing (correct)

Descriptive statistics

Correlation analysis

Probability distribution

In inferential statistics, what is an essential step before performing a statistical test?

Creating a scatter plot

Formulating null and alternative hypotheses (correct)

Collecting qualitative data

Conducting a t-test

Which type of statistical test is suitable for evaluating the relationship between a categorical and a continuous variable?

Chi-square test

Linear regression

Mann-Whitney U-test

ANOVA (correct)

What does the P-value obtained from a statistical test indicate?

Whether the difference is of statistical significance Signup and view all the answers

Which type of test looks for either an increase or decrease in a parameter?

One-tailed test Signup and view all the answers

What is the statement that is considered to be true unless the data provides sufficient evidence to reject it?

Null hypothesis Signup and view all the answers

In which type of test do we look for change, which could be a decrease or an increase?

Two-tailed test Signup and view all the answers

What do we conduct to show whether the mean of the sample is significantly greater than and significantly less than the mean of a population?

Two-tailed test Signup and view all the answers

What type of data is suitable for Spearman correlation?

Quantitative or ordinal data Signup and view all the answers

What type of relationship does the Pearson correlation measure?

Linear relationship Signup and view all the answers

What is the range of the correlation coefficient 'r'?

$-1 \leq r \leq 1$ Signup and view all the answers

Which measure does not require a linear relationship between variables?

Spearman correlation Signup and view all the answers

Rejecting a null hypothesis is often easier than proving it.

True Signup and view all the answers

A null hypothesis is always considered to be true unless proven otherwise by the data.

True Signup and view all the answers

The null hypothesis always states that there is a significant difference between groups or factors being compared.

False Signup and view all the answers

If a study reports a P-value of 0.07, it indicates a highly significant difference and sufficient evidence that there is a real difference between the groups being compared.

False Signup and view all the answers

Study Notes

Youngchan Kim, PhD lectures on inferential statistics in the BMS2043 course at University of Surrey.
Inferential statistics is the process of using data to test hypotheses about populations.
Different statistical tests are used depending on the nature of the data and research question.
Tests include χ2 test, t-test, Mann-Whitney U-test, analysis of variance (ANOVA), linear and logistic regression, and survival analysis.
The results of the statistical tests are evaluated in terms of statistical significance.
A null hypothesis is a statement that is considered true unless the data provides sufficient evidence to reject it.
A one-tailed test is used when the research question specifies a particular direction of the effect, while a two-tailed test is used when the research question does not specify a direction.
A large P-value does not prove the absence of an effect but rather indicates insufficient evidence of the effect.
The cut-off of 0.05 for significance is arbitrary and does not guarantee the absence or presence of an effect.
Pearson correlation and Spearman correlation are measures of correlation between two variables.
Pearson correlation measures the linear relationship between quantitative traits, while Spearman correlation measures the monotonic relationship between quantitative or ordinal data.
Rejecting a hypothesis is often more feasible than proving it.
Statistical significance refers to the observed result not being by chance, while the P-value is the probability of observing the result or more extreme result given the null hypothesis is true.
The scientist in the provided example has an a priori hypothesis that body mass index (BMI) in Europeans is increased due to variations in FTO gene.
The null hypothesis is that BMI in Europeans is not changed due to variations in FTO gene.
The alternative hypothesis is that BMI in Europeans is increased due to variations in FTO gene.
Since the alternative hypothesis specifies an increase, a left-sided one-tailed test is used.
The scientist obtained a test statistic with a P-value of 0.004.
Based on the P-value, the alternative hypothesis is accepted, indicating that BMI in Europeans is indeed increased due to variations in FTO gene.
In the second example, the scientist has a hypothesis that BMI in Europeans is not changed due to variations in FTO gene.
The alternative hypothesis is that BMI in Europeans is changed due to variations in FTO gene.
Since the alternative hypothesis specifies a change, a two-tailed test is used.
The conclusion from the second example would depend on the results of the statistical test.

Studying That Suits You

Use AI to generate personalized quizzes and flashcards to suit your learning preferences.

Description

This quiz covers the concepts of inferential statistics, with a focus on hypothesis testing and the relationships between variables. It is part of the Statistics & Data Analysis course in Analytical and Clinical Biochemistry (BMS2043) for the Spring 2024 semester, taught by Youngchan Kim, PhD.