Question

Asked 4 October 2017

Griffith University

Confused with numerator degrees of freedom. How to calculate sample size using ANCOVA measures in Gpower?

Can anyone please advised me on calculating sample size using Gpower? I want to see the effect of an intervention( independent variable: 2groups) on mental health (continuous) of participants and I have considered baseline outcome measure as a covariate? How can I calculate the sample size in this case? Furthermore, my two secondary outcomes (both are in continuous scale) are also affected by intervention according to the previous literature. In such case, do I have to consider them as a covariate? I am confused on numerator df and don't know what to put in both of these instances?

Griffith University

Thank you

Cite

André I Wierdsma

The way I try to remeber this is to think of the denominator as the size of the cake and the numerator as the topping. The size is a matter of hard work, the topping is the design of the analysis. If you have two conditions and three diagnostic groups and would like to test the interaction of intervention by diagnosis with baseline-scores as co-variate, then in Gpower you get Numerator df= (2-1)*(3-1)=2, Number of groups=6, Number of covariates=1. With power .80 and alpha .05 and an expected effect of medium size you would need a total sample size of 128.

I don't see why you would include other secondary outcomes in this analysis if these outcomes are not correlated with your primary outcome. In another time and place you could have conducted seperate studies for your outcomes.

Cite

27 Recommendations

David Morse

Mississippi State University (Emeritus)

Dhritikesh Chakrabarty

Handique Girls' College

Pradeep Paraman

SEGi University

Connor Tom Keating

University of Oxford

Rainer Duesing

Osnabrück University

Mehmet Sinan Iyisoy

Necmettin Erbakan University

Numerator df should be # of levels of your factor-1 namely 2-1=1. Yes you can consider them as covariates.

1 Recommendation

27 Recommendations

University of the Balearic Islands

Thanks, André, perfect answer. But I think the result of your example is 158, no 128. G*Power setting:

F-Test -> ANCOVA: Fixed effects, main effect and interactions.

A priori...

Effect size F = 0.25 (medium)

alfa = 0.05

Power = 0.80

Numerator df = 2

Number of groups = 6

Number of covariables = 1

...

Total Sample Size = 158

Cite

Mary Joy Secretario Taneo

Department of Health of the Philippines

You are all wonderful people, I just came across this as I was figuring out the same thing: numerator df.

Thank you all!

Cite

1 Recommendation

Nikolche Vasilevski

Bond University

Very helpful thread!!!

Cite

Ahmet Tolgay Akinci

Trakya University

Thank you all. I can't agree more that this thread is very helpful!

Cite

Noga Cohen

University of Haifa

Similarly to the question above, we have 3 groups and 2 covariates. Is the numerator df in this situation 2 (3-1)? or 5 (6-1)?

Cite

Alisa Johnson

University of Florida

Very helpful! Thank you!

Cite

Tahsin Khataei

University of Iowa

Thank you for your Q&A!

Cite

Ronja Haring

University of Pretoria

Cite

Reinaldo Requeiro

University of Cienfuegos

I think it is a serious and reliable tutorial.However You must view it with caution.

https://www.youtube.com/watch?v=WzRW-MTx0Ps

There are other materials that shorten the way.

In these times we need concreteness, speed, but certainty of what is right.

regards

Reinaldo

Cite

1 Recommendation

Simon Fryer

University of Gloucestershire

Really helpful, thank you!

Cite

Begumhan Turhan

Başkent University

https://clincalc.com/stats/samplesize.aspx

Cite

Diksha Sapkota

Griffith University

Thank you

Cite

What should I enter at Numerator df in G*Power?

Question

3 answers

Asked 17 April 2020

Nicky van Doremalen

I'm a little bit confused about what I should enter at Numerator df in G*Power... I'll perform an ANCOVA. I've got 2 experimental conditions (recalling a mastery memory versus recalling a routine memory) and 1 dependent variable (self-esteem). I'll be controlling for 2 covariates (global self-esteem and group identification). Can anyone please help me with this? Thanks!

Can anyone advise on how I can conduct a power analysis for ANCOVA using GPower or another method?

Question

17 answers

Asked 29 April 2015

Amber Muhinyi

Gpower requires that df numerators be specified - can anyone advise how to estimate these in order to determine sample size? Thank you

How to estimate sample size for 2x4 ANOVA in G-Power?

Question

4 answers

Asked 23 November 2020

Skomantas Tamulaitis

Hello,

How would you estimate the required sample size for a 2x4 ANOVA using G-Power based on previous research. I am particularly struggling to understand how to define 'number of groups' and 'number of measurements'.

Thank you!

What is the best way to determine the necessary sample size for a two-way ANOVA in a psychological study?

Question

8 answers

Asked 21 April 2016

Artrina Slabich

I am looking to use a two-way ANOVA and need to know how many participants I should aim for during data collection. Thank you in advance!

Is there a non-parametric equivalent of a two way ANOVA?

Question

48 answers

Asked 24 November 2016

Athanasius Opara

Ordinary two-way ANOVA is based on normal data. When the data is ordinal one would require a non-parametric equivalent of a two way ANOVA. Is there a test like that?

2x2 repeated measures (fully within-subjects) ANOVA power analysis in G*Power?

Question

3 answers

Asked 4 April 2022

Lydia Searle

Hello,

I am trying to do a power analysis for a 2x2 repeated measures design to determine how many participants I need to achieve 80% power. I'm new to the world of power analysis and don't really have a strong stats background.

IV1 = face orientation

Level 1 = upright

Level 2 = inverted

IV2 = context

Level 1 = background present

Level 2 = background removed

This is a fully within-subjects design. I'm trying to use G*Power 3.1 to do the calculation. This is what I have entered into G*Power so far:

Test family: F tests

Statistical test: ANOVA: Repeated measures, within factors

Type of power analysis: A priori...

Effect size f = 0.25 (just assuming a medium effect)

Alpha err prob = 0.05

Power = 0.8

Number of groups = 1

Number of measurements = 4

Corr among rep measures = 0.5 (leaving it at the default)

Nonsphericity correction E = 1 (leaving it at the default)

The number of groups and number of measurements is the part I'm having an issue with. Will G*Power let me calculate n for a 2x2 within design, or is it assuming this is a 1x4 design? From what I've read and watched, number of groups comes into play if you have a between factor, which I don't, so I've set this to 1. As I have a 2x2 design, each participant is being measured 4 times, hence I've put number of measurements to 4.

Sometimes I've read/heard that G*Power DOES allow you to do a 2x2 within design, and sometimes I've read/heard that it does NOT allow you to do this.

I've had a look at GLIMMPSE 3.0.0. as an alternative but there are many fields it requires where I don't know the answer, mainly that there are a list of tests to choose from, none of which are a repeated measures ANOVA. It also wants me to put the means and SDs for each condition, but I haven't run the study yet, plus it's exploratory so I can't even really guess.

Can anyone with some stats / G*Power knowledge help?

Thank you,

Lydia

GPower for Three-Way ANOVA analysis?

Question

4 answers

Asked 18 November 2020

Natalia Karslidou

I want to explore if the amount of time (usage) spent on the Social Media IV1, with two levels , one is light and the other is heavy use, Iv2, body image with negative and positive levels, Iv3 self-esteem with levels of high and low, and my DV is sexual satisfaction. If these variables have an effect on sexual satisfaction and I need to determine my sample size! please send me if you can help me! SOS!

How do I report the results of a linear mixed models analysis?

Question

47 answers

Asked 3 January 2015

Subina Saini

1) Because I am a novice when it comes to reporting the results of a linear mixed models analysis, how do I report the fixed effect, including including the estimate, confidence interval, and p-value in addition to the size of the random effects. I am not sure how to report these in writing. For example, how do I report the confidence interval in APA format and how do I report the size of the random effects?

2) How do you determine the significance of the size of the random effects (i.e. how do you determine if the size of the random effects is too large and how do you determine the implications of that size)?

3) Our study consisted of 16 participants, 8 of which were assigned a technology with a privacy setting and 8 of which were not assigned a technology with a privacy setting. Survey data was collected weekly. Our fixed effect was whether or not participants were assigned the technology. Our random effects were week (for the 8-week study) and participant. How do I justify using a linear mixed model for this study design? Is it accurate to say that we used a linear mixed model to account for missing data (i.e. non-response; technology issues) and participant-level effects (i.e. how frequently each participant used the technology; differences in technology experience; high variability in each individual participant's responses to survey questions across the 8-week period). Is this a sufficient justification?

I am very new to mixed models analyses, and I would appreciate some guidance.

In my g power ap which linear multiple regression should I tick?

Question

3 answers

Asked 27 July 2021

Sonia Zadro

In my g power ap which linear multiple reg should I tick? One says R squared deviation from zero and the other says R squared increase. I'll be doing a Hierarchical multiple regression analysis with a health beliefs questionnaire as my dependent variable and I'll have several independant variables (categorical and continuous) such as sex, education level, and the response to several different questions, and scores on a characteristics scale.

Meta-analysis of continuous outcomes: Using pseudo IPD created from aggregate data to adjust for baseline imbalance and assess treatment-by-baseline modification

Article

Full-text available

Jul 2020

Meta‐analysis of individual participant data (IPD) is considered the "gold‐standard" for synthesizing clinical study evidence. However, gaining access to IPD can be a laborious task (if possible at all) and in practice only summary (aggregate) data are commonly available. In this work we focus on meta‐analytic approaches of comparative studies wher...

Incorporating Baseline Outcome Data in Individual Participant Data Meta-Analysis of Non-randomized Studies

Article

Full-text available

Feb 2022

Background In non-randomized studies (NRSs) where a continuous outcome variable (e.g., depressive symptoms) is assessed at baseline and follow-up, it is common to observe imbalance of the baseline values between the treatment/exposure group and control group. This may bias the study and consequently a meta-analysis (MA) estimate. These estimates ma...

S6 Table

Data

Apr 2016

Results of the ANCOVA of Change from Baseline HbA1c − Clinical Study Part B (Subjects with T2D taking Liraglutide). (DOCX)

Got a technical question?

Get high-quality answers from experts.

Ask a question

Confused with numerator degrees of freedom. How to calculate sample size using ANCOVA measures in Gpower?

Most recent answer

Popular answers (1)

Top contributors to discussions in this field

All Answers (14)

Similar questions and discussions

Related Publications