Quantitative stof leren deels

Podcast

Play an AI-generated podcast conversation about this lesson

Questions and Answers

What are the two types of quantitative research?

Descriptive - what?
Inferential - why?

Why do we need quantative research?

In essence, quantitative research methods provide us with a toolbox to study the (social) world around us by the use of the scientific method.
Helps in minimizing cognitive assumptions that may distort our interpretation.
Depending on the state of prior theory and research on the topic you have to use quantitative methods to make a useful contribution to our understanding of the world.
Only way to establish causal relationships

Good research questions:

Can be answered and need answering
Improve our understanding of how the world works
Inform theory

What is a theory?

A theory is an explanation of relationships among concepts or events within a set of boundary conditions. Signup and view all the answers

What is a GOOD theory?

A good theory simplifies and explains complex real world phenomena Signup and view all the answers

Elements of a good theory - Whetten 1989

<ul> <li>What: Constructs and variables that logically should be considered part of the explanation of the phenomenon of interest</li> <li>How: Propositions and hypotheses that indicate the “links” between constructs and variables. Indicate causality</li> <li>Why: The “glue” that justifies the selection of constructs/variables and their proposed relationships</li> <li>Who, where, when: The conditions under which the theory should hold. Set the limitations of the generalizability of the theory wrt context, time and space</li> </ul> Signup and view all the answers

A good research design helps us achieve this by:

<ol> <li>Using theory, paint the most accurate picture possible of what the data generating process looks like</li> <li>Use the data generating process to figure out the reasons our data might look the way it does that don’t answer our research question</li> <li>Find ways to block out those alternate reasons and so dig out the variation we need. To do so, we want to optimize the validity and reliability of our study</li> </ol> Signup and view all the answers

Internal vs External validity

<ul> <li>Internal validity is the extent to which you are able to draw the correct conclusions about the causal relationships between variables</li> <li>External validity is the extent to which your findings are generalizable to the broader populations (of individuals firms,...) and different settings</li> </ul> Signup and view all the answers

Threats of validity

<ul> <li>Omitted variables</li> <li>Reverse causality</li> <li>Sample selection</li> <li>Measurement error</li> </ul> Signup and view all the answers

Omitted variable bias

<ul> <li>Omitted variable bias occurs when you leave out (omit) an independent variable that is a determinant of the dependent variable and correlated with one or more of the included independent variables.</li> <li>In the case of leaving out this independent variable will lead to an over-or underestimation of the relation between your variables of interest.</li> <li>In our analysis we need to control or adjust for these variables.</li> </ul> Signup and view all the answers

What is reverse causality

Reverse causality occurs when the direction of the arrow in our theoretical model goes the other way. Signup and view all the answers

(Sample) selection bias is

the selection of data for analysis in such a way that proper randomization is not achieved, leading to an unrepresentative sample of the population intended to be analzed Signup and view all the answers

Random sample

<ul> <li>Identically distributed means that there are no overall trends- the distribution doesn’t fluctuate and all items in the sample are taken from the same probability distribution.</li> <li>Independent means that the sample items are all independent events. In other words, they aren’t connected to each other in any way.</li> </ul> Signup and view all the answers

What is reliability?

Reliability is the degree to which a measure produces stable/repeatable and consistent results Signup and view all the answers

What is correlation?

Correlation coefficients measure the strength and direction of a linear relationship between two continuous variables. Correlation coefficients range from -1 to 1. A coefficient close to 1 indicates a strong positive relationship. Close to -1 indicates a strong negative relationship, and around 0 indicates no linear relationship. Signup and view all the answers

Summary Good research Summary good theory

Good theory simplifies and explains complex real world phenomena Good research question can and need to be answered by means of statistics Signup and view all the answers

When is a measure valid?

A measure is valid to the degree that it represents what you are trying to measure Signup and view all the answers

Measurement error can occur when

<ul> <li>Data analyst makes a random mistake when putting in the data</li> <li>Survey respondents consistently underreport the education level of the independent variable</li> <li>Diffeculties in measuring skill level of dependent variable</li> </ul> Signup and view all the answers

To which type of reliability coefficient belongs Cronbach's Alpha

Inter-item Signup and view all the answers

What are the 7 types of variables

<ol> <li>Binary</li> <li>Interval</li> <li>Categorical</li> <li>Continous</li> <li>Ordinal</li> <li>Discrete</li> </ol> Signup and view all the answers

What is the difference between linear regression. and correlation coefficient?

They are very similar, in fact identical when using standarilized variables. The difference is that correlation quantifies the strength and direction of a linear relationship between two variables, whereas the regression estimates how one variable affects another and predicts values based on this relationship. Signup and view all the answers

What is LOESS

Locally estimated scatterplot smoothing Signup and view all the answers

What is regression/line lifting?

Instead of predicting the outcome (dependent) variable using local values of the explanatory (independent) variable, we could assume that their relationship is represented by a certain shape (straight line) Signup and view all the answers

What is the formula of simple linear regression?

y = B0 + B1x + e Signup and view all the answers

What is BLUE

Best Linear Unbiaed Estimator Signup and view all the answers

Assumptions of OLS to be BLUE

<ol> <li>Exogeneity</li> <li>Linearity</li> <li>Independence of observations</li> <li>Homoscedasticity</li> </ol> Signup and view all the answers

When does Omitted variable bias occur?

When you leave out (omit) an independent variable that is a determinant of the dependent variable and correlated with one or more of the included independent variables. Signup and view all the answers

What to do if you have variables with multiple categories?

Simple, make a binary variable for all but one of the different categories, else we fall in the dummy variable trap) Signup and view all the answers

What is the formula for logistic regression

p = 1 / 1 + e^ -(B0+B1x) Signup and view all the answers

Hypothesis testing...

Hypothesis testing consists of a test between two competing hypotheses about the population parameter: <ul> <li>H0: B1 = 0 (generally hypothesis of no difference)</li> <li>H1: B1 ... (research hypothesis) It is not about mean difference it is about the slope being different from zero.</li> </ul> Signup and view all the answers

What does standard error measure?

Standard error measures the uncertainty around the estimated regression coefficient Signup and view all the answers

DPG - Data generating process

<ul> <li>Our theoretical model is only a (small) part of the broader, more complex data generating process</li> <li>We need to make credible claims about the complete DPG so that we can identify the variation in the data that answers our research question.</li> </ul> Signup and view all the answers

Study Notes

Types of Quantitative Research

There are two types of quantitative research:
Quantitative research is necessary to provide precise and accurate measurements of phenomena, allowing for generalizations and predictions.

Research Questions

Good research questions are specific, concise, and testable.

Theory

A theory is a set of interrelated concepts, definitions, and propositions that explain a phenomenon or set of phenomena.
A good theory is one that is clear, concise, and has predictive power.
According to Whetten (1989), elements of a good theory include:
- Clear definitions of key concepts
- Logical coherence among propositions
- Consistency with empirical observations
- Parsimony
- Utility

Research Design

A good research design helps achieve internal validity by ensuring that the causal relationship between variables is isolated and measured accurately.
A good research design helps achieve external validity by ensuring that the results can be generalized to other populations and contexts.

Validity

Internal validity refers to the extent to which the research design ensures that the causal relationship between variables is accurately measured.
External validity refers to the extent to which the results can be generalized to other populations and contexts.
Threats to validity include:
- Omitted variable bias
- Reverse causality
- Selection bias
Omitted variable bias occurs when a relevant variable is omitted from the analysis, leading to incorrect conclusions.
Reverse causality occurs when the causal relationship between variables is incorrectly assumed.
Selection bias occurs when the sample is not representative of the population.

Sampling

A random sample is a sample that is selected using a random process, ensuring that every member of the population has an equal chance of being selected.

Reliability

Reliability refers to the consistency of a measure over time or across different observers.
Correlation refers to the strength and direction of the relationship between two variables.

Measurement

A measure is valid when it accurately measures the concept or phenomenon it is intended to measure.
Measurement error can occur when:
- The measure is not valid
- The measure is not reliable
- There are errors in data collection or data entry

Variables

There are 7 types of variables:
- Nominal
- Ordinal
- Interval
- Ratio
- Dichotomous
- Continuous
- Categorical

Regression

Linear regression is a statistical technique used to model the relationship between a dependent variable and one or more independent variables.
The correlation coefficient is a measure of the strength and direction of the relationship between two variables.
LOESS (Locally Weighted Scatterplot Smoothing) is a statistical technique used to model the relationship between a dependent variable and one or more independent variables.
Regression/line lifting is a technique used to visualize the relationship between variables.
The formula for simple linear regression is: Y = β0 + β1X + ε
BLUE (Best Linear Unbiased Estimator) refers to the property of an estimator that is linear, unbiased, and has the minimum variance.
Assumptions of OLS to be BLUE include:
- Linearity
- Independence
- Homoscedasticity
- Normality
- No multicollinearity
Omitted variable bias occurs when a relevant variable is omitted from the analysis, leading to incorrect conclusions.
When dealing with variables with multiple categories, one can use techniques such as dummy coding or effects coding.

Logistic Regression

The formula for logistic regression is: p = 1 / (1 + e^(-z))

Hypothesis Testing

Standard error measures the variability of the sample statistic.
DPG (Data Generating Process) refers to the underlying mechanism that generates the data.

Studying That Suits You

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

Description

Identify the two main types of quantitative research, an essential concept in research methodology. Test your knowledge and understanding of quantitative research methods.