For example, when you pre-order a movie ticket, the price of the ticket becomes a sunk cost. Even if you decide that you'd rather not go to the movie, there is no way to get back the money you originally paid and you have a sunk cost on your hands. This assumes, of course, that you can't simply return the movie ticket for a refund, and that the odds that you are able to resell the ticket are essentially zero.
Sometimes only part of the price of a purchase ends up being a sunk cost. For example, when you purchase a car, you will be able to resell it later, though you will almost certainly not fetch the original price for it. In this case, your sunk cost with respect to the car at any given time is the difference between how much you originally paid and how much you could sell it for now.
Many people have strong misgivings about "wasting" resources. Many people, for example, would feel obligated to go to the movie despite not really wanting to, because doing otherwise would be wasting the ticket price; they feel they passed the point of no return. This is sometimes called the Sunk Cost Fallacy. Economists would label this behavior "irrational": It is inefficient because it misallocates resources by depending on information that is irrelevant to the business decision being made.
This line of thinking, in turn, may reflect a nonstandard measure of utility, which is ultimately subjective and unique to the consumer. If you buy a ticket in advance to a movie you find is bad, you have still made a semi-public commitment to watching it. You may feel that you "save face" by sticking it out, a satisfaction you cannot draw if you leave. To leave early is to make your lapse of judgment manifest to strangers, an appearance you may rationally choose to avoid. You may in fact find some amusement in how bad the movie turned out to be, and take pride that you recognise it to be bad.
The idea of sunk costs is often employed when analyzing business decisions. An common example of a sunk cost for a business is the promotion of a brand name. This type of marketing incurs costs that cannot normally be recovered - it is not typically possible to later "demote" one's brand names in exchange for cash. Decisions about future investments, sales or more advertising should be made based on future possibilities, not biased by the recent large investment in the advertising that the company made last year (or even last week).