Dear Team,
Is there away to compare observations of two string variables and conclude a match if the match is over 95%. For example if observation 9 in variable J has a value "Fred Orw 15aug1996 Male" and Observation 9 for variable K has a value "Fred Orwa 15aug1996 Male". I want to compare the two variables at observation 9, and since the only difference between the two variables at observation 9 is the "a" in Orwa, I presume this is the same person except one has spelling error i.e word "a" left out and therefore I expect very high match (maybe 99%).Can stata rate the match so that I conclude same person if match is more than 95%.
Regards,
Fred Orwa
Is there away to compare observations of two string variables and conclude a match if the match is over 95%. For example if observation 9 in variable J has a value "Fred Orw 15aug1996 Male" and Observation 9 for variable K has a value "Fred Orwa 15aug1996 Male". I want to compare the two variables at observation 9, and since the only difference between the two variables at observation 9 is the "a" in Orwa, I presume this is the same person except one has spelling error i.e word "a" left out and therefore I expect very high match (maybe 99%).Can stata rate the match so that I conclude same person if match is more than 95%.
Regards,
Fred Orwa
Comment