Factor Analysis issue (PCA) - data validity issue?

Psychometric tools in psychological studies and research activities

Can some one share references that how much minimum and maximum time duration is required to conduct or apply experimental research design in Educational Research.

question

Dear all,

For my graduation research, I am trying to create a composite score about household resilience out of data collected through a household survey. However, this data consists of ordinal variables (5-point Likert scale), binary variables (yes-no questions), and ratio variables (in proportions between 0-1).

My plan was to recode the data on the 5-point Likert scale into scores from 0-1 and do the same for the yes-no questions, with yes = 1 and no = 0 (since answering yes would mean a household is more resilient and thus have a higher score). However, this seems very off.

At this moment I am aware that it wasn't the best idea to create a survey with both types of questions, but I am unable to recollect the data.

Therefore my **question** is as follows: do you have any tips on how to create a composite score composed of both interval and binary variables?

Thank you in advance and have a lovely day.

Best,

Nina

Hello dear all!

I combined items from different sources to make a scale of 41items. I conducted the pilot with a sample size of 30 (which is recommended by many previous studies) and reported the reliability and content validity. But the professor requested to run factor analysis to address construct validity. A sample size of 30 is not sufficient for factor analysis. Do you have any advice to solve the problem? Thanks a lot!

Dissolved Oxygen (DO) is an important water parameters for detecting pollutants. My question is, Where is the most dissolved oxygen (DO)? Is it in the sea or the river?

Hi all,

Trust this finds you well.

Please assist with the above question. I am specifically interested in the medical domain (however, I guess the 'rule' / best practice will be irrespective of domain).

Thanks!

Hi,

I am using a secondary dataset for a project and using path analysis (SEM) to test a model based on a theoretical framework. As the dataset does not have clear validated scales for each construct that I am trying to include, I have to combine different items from the survey to create a composite score for each construct I am interested.

My main concern is related to the weighing of items on composite scores that I am creating based on the available data from a secondary dataset I am using for the project. For example, to measure objective caregiver burden, I am planning on including items that ask about the care recipient's cognitive functioning and ADL/IADL support and caregiving activity rate. However, given the different number of items and scales that measure each aspect of burden (cognitive functioning 19 items, 30 points, MMSE; ADL/IADL support 7 items vs. 10 items, 0-2 points each; caregiving activity rate 4 items, 0-5 points each tapping at different frequencies), it does seem appropriate to just create a total sum and/or mean score for the composite as it can end up weighing the variables that have more items more heavily than those with fewer items. Is there a way to create a meaningful composite score considering these differences??? Any possible and feasible solution???

Thank you so much!!!