This document contains my notes of the knowledge clip, my notes of the lecture, my notes of my workgroup meeting & summaries of the mandatory (and 2 extra) literature.
2023-2024, Block 1 GW4003MV. Advanced Research Methods
WEEK 2
Are you certain?
Moderation, mediation, and statistical
significance
Inhoud
Knowledge clip..................................................................................................................................................2
Knowledge clip 2: OLS regression.............................................................................................................2
Lecture 2 (8 sept)..............................................................................................................................................4
Part 1. OLS and moderation..........................................................................................................................4
Part 2. Mediation..........................................................................................................................................8
Part 3. Statistical significance......................................................................................................................12
Part 4. Beyond p < 0.05...............................................................................................................................14
Workgroup meeting (12 sept).........................................................................................................................17
Homework assignment...............................................................................................................................17
Research case 1: Corrector therapy for infants with Malycosis...............................................................17
Research case 2: Interpreting study results using OLS regression...........................................................22
Literature........................................................................................................................................................29
Wheelan: Chapter 9: Inference...............................................................................................................30
Wheelan: Chapter 11: Regression Analysis.............................................................................................32
Wheelan: Chapter 12: Common Regression Mistakes............................................................................32
Kennedy-Shaffer (2019). Before p < 0.05 to Beyond p < 0.05: Using history to contextualize p-values and
significance testing..................................................................................................................................32
Greenland, et al. (2016). Statistical tests, P-values, confidence intervals, and power: a guide to
misinterpretations..................................................................................................................................32
Wasserstein (2019). Moving to a world beyond “p < 0.05.”....................................................................32
EXTRA LITERATURE: Nuzzo (2014). Scientific Method: Statistical errors.................................................33
EXTRA LITERATURE: Cole, Hernan (2002). Fallibility in estimating direct effects.....................................33
1
,2023-2024, Block 1 GW4003MV. Advanced Research Methods
There are many types of regressions. The 2 types most commonly used are: OLS/linear and logistic
regression. Which regression type you should use, depends on the outcome variable (Y) of interest:
OLS regression Y = continuous.
Logistic regression Y = dichotomous.
Continuous variables can take any value within a
certain range. E.g. age, BMI.
Dichotomous variables only have 2 potential
(often binary) outcomes. E.g. insured/uninsured,
admitted to hospital (yes/no).
Example: RQ: What is the effect of height on weight?
The regression equation describes the relationship
between the exposure variable (X) and the outcome
variable (Y).
The beta coefficients are estimated averages and are
always expressed on the same scale as the outcome (Y).
Running an OLS regression means that we are fitting a
linear curve that is as close to the observation points as
possible.
The name ‘Ordinary Least Squares’ is attributed to the foundation of principle of minimizing the sum of the
squared differences between the fitted/predicted and the observed values. We calculate the squared
2
,2023-2024, Block 1 GW4003MV. Advanced Research Methods
differences because some differences are positive and some are negative, and by calculating the squared
difference you cancel that out.
The intercept/constant (B0) describes
the value of Y at X=0 (in theory ofcourse,
because in practice this is almost
impossible).
Coefficient (B1) describes the slope; this
represent the average increase in weight
with every increase in height.
The difference between the estimated
value by calculating (via the regression
equation) and the observed value is called
the ‘error term’ (ε). The smaller the error
term, the better the estimate.
Coefficients of an OLS regression have
multiple meanings: not only positive and
negative, but also the average size of the
effect.
Usually there are more variables. Look at this example:
3
, 2023-2024, Block 1 GW4003MV. Advanced Research Methods
Lecture 2 (8 sept)
Part 1. OLS and moderation
Slide 3 – 6. Recap week 1
We use DAGs to meet the conditions
(positivity, consistency and exchangeability),
especially for the exchangeability condition
via adjustment in the regression analysis.
Slide 8 + 9
The type of regression analysis you
use is dependent on the outcome
variable. If you have a continuous
variable as outcome, you will use an
OLS regression analysis.
Adjustment in regression analysis
always means: include one or more
confounders (and/or intermediate
variables on causal paths) in
regression analysis at the same time.
So adjustment = including.
There are many terms used for this:
adjustment, controlling, correcting,
accounting, factoring in, …
Slide 10
However, the software doesn’t tell
you how to interpret the results.
DAGs help you with the
interpretation.
4
Voordelen van het kopen van samenvattingen bij Stuvia op een rij:
√ Verzekerd van kwaliteit door reviews
Stuvia-klanten hebben meer dan 700.000 samenvattingen beoordeeld. Zo weet je zeker dat je de beste documenten koopt!
Snel en makkelijk kopen
Je betaalt supersnel en eenmalig met iDeal, Bancontact of creditcard voor de samenvatting. Zonder lidmaatschap.
Focus op de essentie
Samenvattingen worden geschreven voor en door anderen. Daarom zijn de samenvattingen altijd betrouwbaar en actueel. Zo kom je snel tot de kern!
Veelgestelde vragen
Wat krijg ik als ik dit document koop?
Je krijgt een PDF, die direct beschikbaar is na je aankoop. Het gekochte document is altijd, overal en oneindig toegankelijk via je profiel.
Tevredenheidsgarantie: hoe werkt dat?
Onze tevredenheidsgarantie zorgt ervoor dat je altijd een studiedocument vindt dat goed bij je past. Je vult een formulier in en onze klantenservice regelt de rest.
Van wie koop ik deze samenvatting?
Stuvia is een marktplaats, je koop dit document dus niet van ons, maar van verkoper dsmeets123. Stuvia faciliteert de betaling aan de verkoper.
Zit ik meteen vast aan een abonnement?
Nee, je koopt alleen deze samenvatting voor €5,99. Je zit daarna nergens aan vast.
