I'm new to the forum and new to statistics in general. I have been having some problems with my thesis paper analysis and was hoping someone will point me in the right direction.
Paper Topic - ''Culture and Risk Tolerance''; cross cultural analysis comparing Western European, Eastern European and East-Asian cultures to investigate how differences in cultural background effect risk attitudes (one culture is more risk seeking than the other and etc.)
I have gathered 127 observations (no missing values) from 21 different nationalities. Nationalities are then grouped up in to 3 groups (Western, Eastern and East-Asian) depending on geographical location and whether or not the country has been part of the Soviet Union. I employed Hoftede's 5 cultural dimensions/variables to measure for culture. Hence, my dataset contains 5 different numeric values related to culture for every respondent. Problem is, I don't know how to assign these observations to the corresponding culture, therefore I cannot compare anything or analyse how these values influence different cultures.
I tried the following steps:
- Filter up data; create 3 different excel sheets and run 3 separate regressions in SPSS for each sheet.Compare results from all 3 regressions and determine, which culture has highest risk tolerance. Unfortunately, 2 of the datasets have 30 observations per variable each and this method does not produce any good output (weak correlations, low adjusted r-squared and no statistical significance of the model).
- Insert cultural variables for each culture into the main dataset and run the regression this way. This way my dependent variable has 127 observations and the explanatory variables have 60 at best. Again not a good fit and very week correlations between variables.
In addition, my dependent variable ("risk index", numeric) contains observations from all 3 cultures and represents the risk index for the entire sample. I'm wondering, should I divide it into 3 parts and if so, how do I assign the correct values for each culture ? I can see in the excel that the risk index average for Eastern Europe is the highest among the three but don't know how to do it in SPSS.
Thanks in advance !