Covid Fear issueshttps://git.mpib-berlin.mpg.de/zika/covid-fear/-/issues2021-05-12T08:29:06Zhttps://git.mpib-berlin.mpg.de/zika/covid-fear/-/issues/9FA Read relevant reading2021-05-12T08:29:06ZOndrej ZikaFA Read relevant reading- [ ] https://cran.r-project.org/web/packages/psychTools/vignettes/factor.pdf
- [ ] https://stats.idre.ucla.edu/spss/seminars/introduction-to-factor-analysis/a-practical-introduction-to-factor-analysis/
- [ ] https://www.r-bloggers.com/2018/05/exploratory-factor-analysis-in-r/
- [ ] https://www.geo.fu-berlin.de/en/v/soga/Geodata-analysis/factor-analysis/A-simple-example-of-FA/index.html
[VIF_paper_DRAFT.pdf](/uploads/d9c070b4e4278a83e307911162cbff2d/VIF_paper_DRAFT.pdf)
[Mair2018_Chapter_FactorAnalysis.pdf](/uploads/a04b7e60c06e2ccc7ae398bd1799f8e7/Mair2018_Chapter_FactorAnalysis.pdf)
[Gillan2016.pdf](/uploads/229de6962b50b6049985f0e77bf456e9/Gillan2016.pdf)- [ ] https://cran.r-project.org/web/packages/psychTools/vignettes/factor.pdf
- [ ] https://stats.idre.ucla.edu/spss/seminars/introduction-to-factor-analysis/a-practical-introduction-to-factor-analysis/
- [ ] https://www.r-bloggers.com/2018/05/exploratory-factor-analysis-in-r/
- [ ] https://www.geo.fu-berlin.de/en/v/soga/Geodata-analysis/factor-analysis/A-simple-example-of-FA/index.html
[VIF_paper_DRAFT.pdf](/uploads/d9c070b4e4278a83e307911162cbff2d/VIF_paper_DRAFT.pdf)
[Mair2018_Chapter_FactorAnalysis.pdf](/uploads/a04b7e60c06e2ccc7ae398bd1799f8e7/Mair2018_Chapter_FactorAnalysis.pdf)
[Gillan2016.pdf](/uploads/229de6962b50b6049985f0e77bf456e9/Gillan2016.pdf)https://git.mpib-berlin.mpg.de/zika/covid-fear/-/issues/8FA: notes from meeting with Claire and Nico2021-05-11T14:14:01ZOndrej ZikaFA: notes from meeting with Claire and Nico- factors shouldnt necessary be orthogonal
- bleak rotation
- ELB0 sng_test in R
- decide questions to include
- dealing with binary data - - claire will send
- in dates use month
- maybe leave the binary questions out of the factor anlaysis - they start a bit later, and the factors can still be related to them
- factor anlaysis at different time points, see how it changes ,is it trait , dependein, do at first time point and then on other time points
- maybe kick out measures if they chagne tloading over time
- show how stable are "stable" compared to volatile measures
- normalize to the first time point?
- sensitivty to starting levels
- factor analysis on worry and prob est measures, think about individual questions - lockin to the peak
- objective measure - what happens to ppl after they have been infected
- get in touch with toby abotu the questions
---
#### From Claire
Further to conversation Friday, here is some code snippets. Basically in our work we use the psych package for factor analysis (fa()). You need polycor to create the correlation matrix out of mixed data (from R documentation: “Computes a heterogenous correlation matrix, consisting of Pearson product-moment correlations between numeric variables, polyserial correlations between numeric and ordinal variables, and polychoric correlations between ordinal variables.”)
Then you plug that corelation matrix into the fa. Also attaching code to make that plot we did in eLife.
---
### From Gagne paper
The Schmid-Leiman (SL) procedure was used to estimate the loadings of individual questionnaire
items on each factor (Schmid and Leiman, 1957). This procedure performs oblique factor analysis
followed by a higher order factor analysis on the lower order factor correlations to extract a general
factor. All three factors are forced to be orthogonal to one another, which allows for easier interpretability. In line with previous findings (Clark et al., 1994; Steer et al., 1995; Zinbarg and Barlow,
1996; Steer et al., 1999; Simms et al., 2008; Steer et al., 2008; Brodbeck et al., 2011), the general factor had high loadings (>0.4) for multiple anxiety-related and depression-related items and
moderately high loadings (>0.2) across almost all items. One specific factor had high loadings (>0.4)
for questions related to anhedonia and depressed mood. The other specific factor had high loadings
(>0.4) for questions related to worry and anxiety.- factors shouldnt necessary be orthogonal
- bleak rotation
- ELB0 sng_test in R
- decide questions to include
- dealing with binary data - - claire will send
- in dates use month
- maybe leave the binary questions out of the factor anlaysis - they start a bit later, and the factors can still be related to them
- factor anlaysis at different time points, see how it changes ,is it trait , dependein, do at first time point and then on other time points
- maybe kick out measures if they chagne tloading over time
- show how stable are "stable" compared to volatile measures
- normalize to the first time point?
- sensitivty to starting levels
- factor analysis on worry and prob est measures, think about individual questions - lockin to the peak
- objective measure - what happens to ppl after they have been infected
- get in touch with toby abotu the questions
---
#### From Claire
Further to conversation Friday, here is some code snippets. Basically in our work we use the psych package for factor analysis (fa()). You need polycor to create the correlation matrix out of mixed data (from R documentation: “Computes a heterogenous correlation matrix, consisting of Pearson product-moment correlations between numeric variables, polyserial correlations between numeric and ordinal variables, and polychoric correlations between ordinal variables.”)
Then you plug that corelation matrix into the fa. Also attaching code to make that plot we did in eLife.
---
### From Gagne paper
The Schmid-Leiman (SL) procedure was used to estimate the loadings of individual questionnaire
items on each factor (Schmid and Leiman, 1957). This procedure performs oblique factor analysis
followed by a higher order factor analysis on the lower order factor correlations to extract a general
factor. All three factors are forced to be orthogonal to one another, which allows for easier interpretability. In line with previous findings (Clark et al., 1994; Steer et al., 1995; Zinbarg and Barlow,
1996; Steer et al., 1999; Simms et al., 2008; Steer et al., 2008; Brodbeck et al., 2011), the general factor had high loadings (>0.4) for multiple anxiety-related and depression-related items and
moderately high loadings (>0.2) across almost all items. One specific factor had high loadings (>0.4)
for questions related to anhedonia and depressed mood. The other specific factor had high loadings
(>0.4) for questions related to worry and anxiety.https://git.mpib-berlin.mpg.de/zika/covid-fear/-/issues/6If you think back to the first survey (mid April 2020), what did you think wa...2021-01-13T13:23:48ZOndrej ZikaIf you think back to the first survey (mid April 2020), what did you think was the probability that:In session 3, the rating scale was wrong (from strongly disagree to strongly agree), and it was cnaaged for session 4, thus the data are incompatibleIn session 3, the rating scale was wrong (from strongly disagree to strongly agree), and it was cnaaged for session 4, thus the data are incompatiblehttps://git.mpib-berlin.mpg.de/zika/covid-fear/-/issues/3Summary of participants responses from sessions 9 - 142020-11-30T08:54:46ZOndrej ZikaSummary of participants responses from sessions 9 - 14As we discussed, please create a similar list as you did last time @yasynska.
Thank you!
https://zika.mpib.berlin/covid-fear/documentation/#/Participant_comments_4_8As we discussed, please create a similar list as you did last time @yasynska.
Thank you!
https://zika.mpib.berlin/covid-fear/documentation/#/Participant_comments_4_8Kateryna YasynskaKateryna Yasynskahttps://git.mpib-berlin.mpg.de/zika/covid-fear/-/issues/2Dropout payments2020-07-27T14:39:48ZOndrej ZikaDropout paymentsIn the covid study, some participants withdraw without being paid the promised 9 EUR/hr on average. We have to identify those that dropped out and weren't paid enough, and pay them accordingly.
@yasynska, @zika and @krippner discuss who would like to have a go - this should be a python script so that we can later plug in the remaining sessions.
There is one tricky scenario: if they time-out we don't want to pay them for the time that they were not responding, this might require manual checking but it *might* also be possible to infer it from the data.In the covid study, some participants withdraw without being paid the promised 9 EUR/hr on average. We have to identify those that dropped out and weren't paid enough, and pay them accordingly.
@yasynska, @zika and @krippner discuss who would like to have a go - this should be a python script so that we can later plug in the remaining sessions.
There is one tricky scenario: if they time-out we don't want to pay them for the time that they were not responding, this might require manual checking but it *might* also be possible to infer it from the data.