0

This is probably really basic but any help would be greatly appreciated. I am trying to remove multiple rows from a dataset because of one missing piece of information. The attached picture includes the data set. I have percentile ranked each row however I now need to delete the rows that have no percentile rank and there are roughly 26,000 rows so a quick way to filter and delete would be very beneficial I have both Minitab and R so preferably a fix in there would be great as excel keeps crashing when I try it in there!

Thank you in advance :)

How the data looks

Grant Birchmeier
  • 17,809
  • 11
  • 63
  • 98
Callum94
  • 9
  • 1
  • 2
    In R, have you tried `complete.cases`? – r2evans Apr 12 '22 at 21:37
  • If you read data in R, it should fill in the empty cells as NA. You can then use `dat[complete.cases(dat), ]` which will remove all rows which has any of the columns as NA – 89_Simple Apr 12 '22 at 21:41
  • I don't have minitab (and haven't used it for years), so I don't know for certain if that image of data is saying that the `C18` column is empty, has `NA`s (R thing), has the literal `*` asterisk, or something else. While `complete.cases` will check all columns, if you want to subset based on just one column, you should read [`?subset`](https://stat.ethz.ch/R-manual/R-devel/library/base/html/subset.html) or [`?Extract`](https://stat.ethz.ch/R-manual/R-devel/library/base/html/Extract.html) and like the `is.na(.)` function. – r2evans Apr 12 '22 at 21:42

1 Answers1

0

The comments to your question should work in R. However, for those who have a similar problem and only have Minitab (and for whatever reason don't wish to / can't simply download R), the following method should work for Minitab 19 (there may be differences in different versions of the software):

  1. Navigate to Data > Subset Worksheet...

  2. Select "Use rows that match a condition" and "Exclude rows that match the condition" from the first two boxes

  3. Select the column that contains missing values (C18 in this particular case) in the Column box

  4. Select "Equals" in the Condition box and * in the Value box

This should create a new worksheet, excluding the rows with missing values in that column.

Tom
  • 1