1. You are treated with less courtesy or respect than other people
  2. You receive poorer service than other people at restaurants or stores
  3. People act as if they think you are not clever
  4. You are threatened or harassed
  5. You receive poorer service or treatment than other people from doctors or hospitals
These perceived ageism frequency information combined with the other variables in the data set(age, marital status, income, education level) can be used to find the answer of whether older people experienced ageism and what factors leads to more serious ageism problem.
UK Data Service provide ELSA data in sas, sav and dta format, I transformed the sav file into csv file by R, and used pandas in python to extract and manipulate the parameters I want, for the purposes of this research, here I only select 'Age', 'gender', 'financial status', 'work status', 'perceived discrimination frequency' and 'self reported reason for discrimination' in the final dataset.
The raw data contains 5 column for ‘frequency of discrimination’, to convert the column into a format that can be used in computational models, the 5 conditions('Never', 'Less than once a year', 'A few times a year', 'At least once a week', 'Almost every day', 'A few times a month') each was assigned a score from 0 - 5, and sum up into a new column named 'DisScore', the higher the value is, the server the discrimination the person perceived. After data cleaning, the data frame has 3545 observations.