Questions tagged [change-scores]
A single variable calculated from a variable measured at two different times (post - pre). Also called "gain-" or "difference-scores". Can also be used for other analysis of pre- and post- data.
137
questions
1
vote
1answer
12 views
Compare pre-post change intervention across studies
I have got a question regarding the comparison of the effect size comparing a new (digital) intervention with previous data using a traditional intervention. In summary, we've designed a new (digital -...
0
votes
0answers
27 views
Contribution to Growth for a linear equation
I have this equation
$ Sales = Impressions * CTR * CVR * Price $
I know all the values for two different periods (January 2021, February 2021) and I want to know how much each components (impressions, ...
3
votes
1answer
43 views
How to calculate effect size for a pretest-posttest-control design study?
I am trying to calculate the effect size of exercise on depression. So I have 2 groups (control and intervention) in an RCT setting. I have both mean values and standard deviation of groups at T0 (...
0
votes
0answers
10 views
How to measure whether change in one outcome predicts change in another outcome?
I am studying the effect of a self-compassion intervention on various outcomes (stress, anxiety, depression, etc.). I have pre, post, and follow-up data from my participants. I have already examined ...
0
votes
0answers
12 views
Investigating effect of group on difference scores in mixed ANOVA
I was wondering what is the most elegant way to investigate group differences in change scores? Here's what I'm trying to do. Imagine there are three groups (a,b,c) where each participant is measured ...
1
vote
0answers
20 views
Interpretation when relative gain score is the outcome variable
I have two groups - treatment and control - and I am analyzing the effect of a policy change with multiple treatment periods. My dependent variable is a relative gain score (i.e. yt - yt-1)/yt-1). I ...
0
votes
0answers
19 views
Statistical testing between two time periods to determine a change
I am trying to determine what model to use when testing how an index sector performance changes as we go from environment 1 to environment 2. The environment is based on changes in inflation and is in ...
0
votes
0answers
14 views
Test of normality with normalized change scores
We've done an experiment on the effectiveness of a learning intervention. We have two groups -- a control and experimental/test group where we had the participants do a pretest and posttest.
From the ...
0
votes
0answers
13 views
How to analyze treatment efficacy for small dataset
I have baseline and post-treatment questionnaire data on behavioural treatment and control groups. Each group has less than 10 participants.
I have missing data both on baseline and posttreatment ...
0
votes
0answers
14 views
Binary data of MCQ for paired T test
I am designing an experiment where I need to measure developer awareness after the introduction of a tool. basically taking 4 questions in pre and post-survey to measure increased awareness using the ...
1
vote
0answers
36 views
Compare gain scores of two groups of unequal size and not normal distribution
I am trying to determine the effectiveness of a learning intervention that we developed. We had two groups, a control and experimental group, where we applied the intervention to the experimental ...
0
votes
1answer
56 views
Difference Score as Outcome Variable [duplicate]
I am trying to evaluate the effect of a certain policy on the achievement gains of students between two points in time. However, not all the students are exposed to this policy. I am supposed to use ...
0
votes
0answers
7 views
How to test if performance in Yr1 effects performance in Yr2?
I'm basically trying to compare whether students that perform better (eg; higher test scores) in yr 1 perform better in yr 2 (eg; still achieving the highest test scores). Students did 20 tests each ...
0
votes
0answers
46 views
Why reliable change index instead of using standard deviation of the difference scores?
Let's say I want to see if my patient's medication affects their score on a scale of attention. I test them twice: once on meds, and once off meds. I then want to see if their change in score is ...
0
votes
0answers
23 views
Outlier detection based only on log probability
I have a problem where I have fit a normalizing flow to data which allows me to calculate the log-likelihood of data points. How should I go about defining an outlier in this situation? Or at least a ...
0
votes
0answers
88 views
POMP score in a bidirectional scale
I am working with some data that vary along an arbitrary scale of -1 to 1. More specifically, this scale refers to a difference between two scores (with 0 meaning no difference, 1 being the maximum ...
0
votes
0answers
19 views
About relative and absolute change
I am trying to assess the relationship of change in the level of a marker with the development of a disease. If I assess absolute change, there is a significant association. But if I assess relative ...
0
votes
0answers
6 views
Pretest posttest design with varying time between tests
I have a pre-test post-test design where several subjects were administered a drug. For each subject, I have $p_0$, a physiological measurement taken directly prior to the drug being taken, and $p_t$, ...
0
votes
0answers
15 views
What statistical test to conduct?
We conducted an intervention study (digital intervention) to understand the change in knowledge and various psychological variables (likert scale -- attitudes, beliefs, anxiety) on a group. We first ...
0
votes
0answers
20 views
Appropriate regression model for a learning experiment on alpine skiing
We are running a learning experiment with a between-subjects design on alpine skiing: one group training according to an interleaved schedule whereas the other group train according to a blocked ...
0
votes
0answers
8 views
Question on latent change scores
I went to two different talks that used latent change scores, but the two interpreted the results differently. I am not an expert in this and would like to know which one is correct.
Example: Age ...
1
vote
0answers
21 views
How to compare score differences across time using unpaired data?
An anonymous school climate survey was administered to students in 10 schools in 2017. We have student-level data from that survey, which includes each student's overall satisfaction score (scale of 0 ...
0
votes
0answers
27 views
Binary outcome - what test
I am doing a study where I assess the knowledge of the same group of people before and after a teaching session.
The question ask if the risk of developing cancer is higher or lower in the adult ...
2
votes
0answers
26 views
How to adress the -0.71 correlation artefact in the pre-post analysis of change from baseline in non-randomized trials?
Let me make some introduction first.
It's well known, that in randomized trials, in the pre-post trials, by the formal pharmaceutical regulatory guidelines, both raw post and change scores should be ...
0
votes
0answers
32 views
Paired T-test for a population with positive and negative effects
I have before and after values where the treatment is expected to have a positive effect on a set of instances (I know what they ...
1
vote
2answers
67 views
Mean centering my data for regression
Can I mean-centre my data and then calculate the percentage change or is that redundant?
For instance, I want to perform a regression on my data. I have my participants IQ score, which I mean-centered ...
0
votes
0answers
11 views
How to compare treatment slopes in pre-post with 2 treatments?
I have a pre-post experiment. At t0 both groups start from a comparable values of some parameter. There are two treatments. Treatment A doesn't show improvement over time. Treatment B - does. In the ...
0
votes
1answer
147 views
What is the best analytic approach for two arm randomized pre-post trial?
Study design is a classic pre-post design:
two trt arms (treatment, control). Subjects are randomly assigned into two arms.
outcome is continuous and measured at baseline and a follow-up time point (...
2
votes
1answer
285 views
Analysing change scores via linear mixed effects model with baseline adjustment?
I am still trying to find a model for a large dataset, approximately 1-5 measurements per patient (over time), one is the baseline value at t=0. The researcher is interested in the change over time ...
0
votes
0answers
20 views
Combined equivalence and difference testing
I have some data with two conditions, and a pre- and post-measure for each condition. I would like to know 2 things:
That there was a significant increase from pre to post in both conditions,
That ...
2
votes
0answers
24 views
Why we cannot take baseline as predictor for change in this case
It is generally recommended that baseline should not be kept as predictor if change is outcome variable. Explanations for this have taken both baseline and final values as random (e.g. see here). ...
1
vote
0answers
35 views
Keeping baseline as predictor with change score as outcome in this peculiar scenario
It is generally recommended that baseline should not be kept as predictor if change score ...
10
votes
2answers
631 views
Is there a mathematical proof for change being correlated with baseline value
It is shown in answer here and at other places that difference of 2 random variables will be correlated with baseline. Hence baseline should not be a predictor for change in regression equations. It ...
0
votes
0answers
38 views
Which type of analysis of the change from baseline is better: GLS + Dunnett on post values or GLS + ANOVA on changes?
Dears,
I'm preparing for a project in ecology. We will analyse change from baseline as a reaction to some chemical substance.
Let's assume the data will be collected like this:
...
1
vote
1answer
60 views
Change Score or Regressor Variable Method - Should I regress $Y_1$ over $X$ and $Y_0$ or $(Y_1-Y_0)$ over $X$
I have data about investment preferences 1 year before the Covid and during the Covid lockdown.
Some changes appear using simple T-Test. I want to be able to assess if these changes are particularly ...
2
votes
1answer
86 views
Gain scores as an outcome in HLM?
I'm analyzing data from a single-group, pre-post design, trying to see if student beliefs change after an intervention. Students are nested in classrooms, and there is a significant amount of ...
2
votes
0answers
121 views
Creating Z-Scores for Meta-Analysis
I will be conducting a meta-analysis that compares post-treatment changes in depression between the control and intervention groups. I have the Mean, SD, and N for depression at both time-points. ...
2
votes
1answer
152 views
Why do regression models predicting a change score vs. predicting T2 controlling for T1 yield slightly different results?
I am running multiple regression models testing whether a change from T1 to T2 in my IV predicts a change in my DV (also from T1 to T2). I am running these analyses in R using the glm function.
I ran ...
0
votes
0answers
19 views
Comparing the before and after scores between two groups
In this experiment I'm trying to make, one group of people watches a lecture series and one does not. Before the lecture series, both groups' levels of optimism, knowledge, and anxiety are assessed. ...
1
vote
0answers
179 views
Latent Change Score modeling in Lavaan; Strict vs Scalar Measurement Invariance models
I am new to SEM and currently struggling setting up Latent Change Score models for testing for Measurement Invariance (MI).
I have a model with two latent factors (T1 en T2) with each 2 indicators (...
2
votes
1answer
104 views
Controlling for baseline in difference scores
I have a dataset of participants receiving various frequency of intervention. We want to see if those who received more intervention had greater improvement between pre-intervention and post-...
1
vote
0answers
82 views
How to analyse pre-post ordinal data?
I collected pre-post data from a randomized controlled experiment. The intervention for the experiment group is an educational game and the pre-test and post-test contains 10 multiple-choice ...
1
vote
0answers
161 views
Can controlling for baseline in a regression with change scores be appropriate? (within-subjects design)
I ran a regression model with a change score (post minus pre manipulation) predicting my dependent variable. Initially, I thought it might be also interesting to control for the baseline score (pre ...
0
votes
1answer
76 views
Is there any formal guideline that would indicate the necessity for adjustment for baseline when analysing change from baseline?
As in the topic. I saw many critical discussions along with mathematical explanation on why the baseline shouldn't (or mustn't) be employed as a covariate, when analysing the change from baseline. ...
1
vote
2answers
49 views
Is it valid to use a difference score between sequential timepoints as an independent variable in a longitudinal regression analysis?
Is it valid to use change scores, i.e. like change in body weight taken between consecutive time points in longitudinal analysis where I'm using nlme/gee?
For example,
bodyweight at hour 3 minus ...
0
votes
1answer
26 views
Descriptive statistics for 2 variables grouped by gender with spss
I have 3 variables one categorical gender and the others are the IQBefore and IQAfter which ...
3
votes
0answers
73 views
ANOVA/ANCOVA - how to analyse
In a basic research design where you want to test how some intervention (let's say our IV is 'drinking' with the categories
water;
sprite; and
rum)
affects some continuous measurement (let's say ...
1
vote
0answers
12 views
Relative change of two vectors from a pretreatment value
I have to vectors $\mathbf{y1_{post}}$ and $\mathbf{y2_{post}}$ (post because they were measured after a treatment).
...
1
vote
0answers
17 views
Two Factor ANOVA with different sample sizes but similar variances
I gave an educational intervention to Spanish speaking and English speaking students. I gave a pre and post test to these students. Due to certain issues I was not able to identify students with their ...
1
vote
0answers
28 views
Given a dataset of students' exam scores across 5 years, how can I determine what consists of a significant change in score? [closed]
Suppose I have the data below, of student's scores changes between 2013-2016 in :
...
