R software for statistical computing : useful in finance ?

Let's say I have the total number of household of each zone in a particular city. I want to explore the driving forces of crimes (count data). As candidate's independent variables a have a set of variables i.e, percentage of head of household that are unemployed in that particular zone, percentage of head of household with low education etc.

I have the possibility to get the absolute value of head of household unemployed by multiplying it percentages by total number of household. However, I think if I use this absolute values it might be correlate with total population, since it is a possible candidate independent variable. Zones with more population tends to also have more absolute values of unemployment.

Please, I would like to hear some feedback from you.

Best regards,

Patrik

For any model, considering time-series data, structural stability test CUSUM and CUSUM SQ are now frequently used.

I would like to use correlation analysis to check the co-occurrence of HMs in the sediments and visualize the results using a grid showing the connections between the different HMs within the dataset by qgraph package in R(with the correlation values shown as in the attached figure).

How can i from that ?

Thanks

Im my quasi-experimental study, I've conducted a Likert-scale survey which investigates attitudes towards statements about a certain teaching method, and an achievement test following the implementation of the method. Both survey and achievement test include a pre and post-test.Two groups are investigated, but one is given an experimental treatment

The response alternatives are all marked by numbers 1-5, but only 1 and 5 are labelled only at the extremes with with Strongly Disagree and Strongly Agree respectively. The scale includes 11 statements, which could be further divided into two categories (1.general motivation and 2. outcome expectations)

In addition to analyzing the survey responses (pre and post) from both groups, I would also like to check for correlation between the achievement test and Likert-survey. Problem is, I have no idea how.

As of now, I've summated the scores 1-5 on all 11 statements – resulting in a final "score" for each participant.

1. How do I present descriptive data from such a Likert scale (mentioned above) and compare with another group? a. What statistics should be included? b. Parametic or nonparametric?

2. What tests should I run to investigate correlation between Likert scale and achievement test?

I've tried to read up on the subject, but it seems to be a lot of discussion about how the data should be treated, i.e ordinal/interval - parametic tests/nonparametic and so on. On the achievement test a t-test is fine.

Thanks.

Our research has three groups in which we obtained the correlation coefficients of the variables.

Group 1 (Presence of both parents) - 100 participants

Group 2 (Only mothers) - 100 participants

Group 3 (Only fathers) - 38 participants

Is it possible to compare these three through Fisher's z-transformation, especially with one group having an unequal sample size? Thank you so much.

My study is looking at factors affecting walking in stroke survivors. The dependent variable of the regression model is steps per day taken by the participant and the independent variables are distance walking during the six minute walk test, depression scores and knee extensor strength. I built a hierarchical regression model with controlling for the confounding variables (age, sex, time since stroke and severity of stroke) in the first block , distance walking during the six minute walk test in the second block, depression scores in the third block and knee extensor strength in the last block . In my final model , the beta value for knee extensor strength is negative which is counterintuitive. I deleted potential outliers detected by cook's distance and leverage values. In the correlational analysis the correlation between steps per day and knee extensor strength is positive but in the regression model it's the opposite .What steps should I take to tackle this problem ?

The results showed low expression of A and overexpression of B in Tumor tissues.

We expect them to show a negative correlation, but they show a significant positive correlation. Can you explain this situation?

Can we say the more A decreases, the less B increases?

Have you ever seen such a situation?

Thank you

I have a dataset for 500 participants and their total sleep time for a period of 10 days, some of these participants do not have data for all the days, e.g. 10 of them have data only for 4 days instead of 10. Can I perform a correlation analysis on this data for sleep time and temperature, without excluding these participants? What other methods can I use for this analysis? Can I use linear regression to explain the effect of temperature on sleep?